| 155 73 190 190 169 189 169 169 169 169 189 188 32 32 32 97 97 97 97 128 128 128 128 128 128 128 42 97 97 97 97 97 97 97 42 128 128 128 59 60 60 60 159 155 154 155 12 120 74 73 74 68 169 122 115 122 4 119 19 169 169 120 8 4 4 120 120 120 120 59 42 139 139 32 32 32 5 5 5 169 169 5 169 169 169 169 169 169 169 5 14 14 14 14 13 14 14 14 215 229 228 140 227 241 9 3 5 1 3 3 227 240 85 85 6 16 79 86 48 6 49 84 84 86 49 86 85 120 120 150 96 96 96 128 128 128 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 | // SPDX-License-Identifier: GPL-2.0-only /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux hook function implementations. * * Authors: Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com> * Eric Paris <eparis@redhat.com> * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * <dgoeddel@trustedcs.com> * Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2007 Hitachi Software Engineering Co., Ltd. * Yuichi Nakamura <ynakam@hitachisoft.jp> * Copyright (C) 2016 Mellanox Technologies */ #include <linux/init.h> #include <linux/kd.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/lsm_hooks.h> #include <linux/xattr.h> #include <linux/capability.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/swap.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/dcache.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ #include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/structs.h> #include <linux/quota.h> #include <linux/un.h> /* for Unix socket types */ #include <net/af_unix.h> /* for Unix socket types */ #include <linux/parser.h> #include <linux/nfs_mount.h> #include <net/ipv6.h> #include <linux/hugetlb.h> #include <linux/personality.h> #include <linux/audit.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/posix-timers.h> #include <linux/syslog.h> #include <linux/user_namespace.h> #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> #include <uapi/linux/shm.h> #include <linux/bpf.h> #include <linux/kernfs.h> #include <linux/stringhash.h> /* for hashlen_string() */ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> #include <linux/io_uring/cmd.h> #include <uapi/linux/lsm.h> #include "avc.h" #include "objsec.h" #include "netif.h" #include "netnode.h" #include "netport.h" #include "ibpkey.h" #include "xfrm.h" #include "netlabel.h" #include "audit.h" #include "avc_ss.h" #define SELINUX_INODE_INIT_XATTRS 1 struct selinux_state selinux_state; /* SECMARK reference count */ static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static int selinux_enforcing_boot __initdata; static int __init enforcing_setup(char *str) { unsigned long enforcing; if (!kstrtoul(str, 0, &enforcing)) selinux_enforcing_boot = enforcing ? 1 : 0; return 1; } __setup("enforcing=", enforcing_setup); #else #define selinux_enforcing_boot 1 #endif int selinux_enabled_boot __initdata = 1; #ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM static int __init selinux_enabled_setup(char *str) { unsigned long enabled; if (!kstrtoul(str, 0, &enabled)) selinux_enabled_boot = enabled ? 1 : 0; return 1; } __setup("selinux=", selinux_enabled_setup); #endif static int __init checkreqprot_setup(char *str) { unsigned long checkreqprot; if (!kstrtoul(str, 0, &checkreqprot)) { if (checkreqprot) pr_err("SELinux: checkreqprot set to 1 via kernel parameter. This is no longer supported.\n"); } return 1; } __setup("checkreqprot=", checkreqprot_setup); /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * * Description: * This function checks the SECMARK reference counter to see if any SECMARK * targets are currently configured, if the reference counter is greater than * zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is * enabled, false (0) if SECMARK is disabled. If the always_check_network * policy capability is enabled, SECMARK is always considered enabled. * */ static int selinux_secmark_enabled(void) { return (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } /** * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled * * Description: * This function checks if NetLabel or labeled IPSEC is enabled. Returns true * (1) if any are enabled or false (0) if neither are enabled. If the * always_check_network policy capability is enabled, peer labeling * is always considered enabled. * */ static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_netif_flush(); sel_netnode_flush(); sel_netport_flush(); synchronize_net(); } return 0; } static int selinux_lsm_notifier_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_ib_pkey_flush(); call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); } return 0; } /* * initialise the security for the init task */ static void cred_init_security(void) { struct task_security_struct *tsec; tsec = selinux_cred(unrcu_pointer(current->real_cred)); tsec->osid = tsec->sid = SECINITSID_KERNEL; } /* * get the security ID of a set of credentials */ static inline u32 cred_sid(const struct cred *cred) { const struct task_security_struct *tsec; tsec = selinux_cred(cred); return tsec->sid; } static void __ad_net_init(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, struct sock *sk, u16 family) { ad->type = LSM_AUDIT_DATA_NET; ad->u.net = net; net->netif = ifindex; net->sk = sk; net->family = family; } static void ad_net_init_from_sk(struct common_audit_data *ad, struct lsm_network_audit *net, struct sock *sk) { __ad_net_init(ad, net, 0, sk, 0); } static void ad_net_init_from_iif(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, u16 family) { __ad_net_init(ad, net, ifindex, NULL, family); } /* * get the objective security ID of a task */ static inline u32 task_sid_obj(const struct task_struct *task) { u32 sid; rcu_read_lock(); sid = cred_sid(__task_cred(task)); rcu_read_unlock(); return sid; } static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* * Try reloading inode security labels that have been marked as invalid. The * @may_sleep parameter indicates when sleeping and thus reloading labels is * allowed; when set to false, returns -ECHILD when the label is * invalid. The @dentry parameter should be set to a dentry of the inode. */ static int __inode_security_revalidate(struct inode *inode, struct dentry *dentry, bool may_sleep) { struct inode_security_struct *isec = selinux_inode(inode); might_sleep_if(may_sleep); if (selinux_initialized() && isec->initialized != LABEL_INITIALIZED) { if (!may_sleep) return -ECHILD; /* * Try reloading the inode security label. This will fail if * @opt_dentry is NULL and no dentry for this inode can be * found; in that case, continue using the old label. */ inode_doinit_with_dentry(inode, dentry); } return 0; } static struct inode_security_struct *inode_security_novalidate(struct inode *inode) { return selinux_inode(inode); } static struct inode_security_struct *inode_security_rcu(struct inode *inode, bool rcu) { int error; error = __inode_security_revalidate(inode, NULL, !rcu); if (error) return ERR_PTR(error); return selinux_inode(inode); } /* * Get the security label of an inode. */ static struct inode_security_struct *inode_security(struct inode *inode) { __inode_security_revalidate(inode, NULL, true); return selinux_inode(inode); } static struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); return selinux_inode(inode); } /* * Get the security label of a dentry's backing inode. */ static struct inode_security_struct *backing_inode_security(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); __inode_security_revalidate(inode, dentry, true); return selinux_inode(inode); } static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); struct superblock_security_struct *sbsec; if (!isec) return; sbsec = selinux_superblock(inode->i_sb); /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste * time taking a lock doing nothing. * * The list_del_init() function can be safely called more than once. * It should not be possible for this function to be called with * concurrent list_add(), but for better safety against future changes * in the code, we use list_empty_careful() here. */ if (!list_empty_careful(&isec->list)) { spin_lock(&sbsec->isec_lock); list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } } struct selinux_mnt_opts { u32 fscontext_sid; u32 context_sid; u32 rootcontext_sid; u32 defcontext_sid; }; static void selinux_free_mnt_opts(void *mnt_opts) { kfree(mnt_opts); } enum { Opt_error = -1, Opt_context = 0, Opt_defcontext = 1, Opt_fscontext = 2, Opt_rootcontext = 3, Opt_seclabel = 4, }; #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg} static const struct { const char *name; int len; int opt; bool has_arg; } tokens[] = { A(context, true), A(fscontext, true), A(defcontext, true), A(rootcontext, true), A(seclabel, false), }; #undef A static int match_opt_prefix(char *s, int l, char **arg) { int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; if (len > l || memcmp(s, tokens[i].name, len)) continue; if (tokens[i].has_arg) { if (len == l || s[len] != '=') continue; *arg = s + len + 1; } else if (len != l) continue; return tokens[i].opt; } return Opt_error; } #define SEL_MOUNT_FAIL_MSG "SELinux: duplicate or incompatible mount options\n" static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, NULL); return rc; } static int selinux_is_genfs_special_handling(struct super_block *sb) { /* Special handling. Genfs but also in-core setxattr handler */ return !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs") || (selinux_policycap_cgroupseclabel() && (!strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2"))); } static int selinux_is_sblabel_mnt(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * IMPORTANT: Double-check logic in this function when adding a new * SECURITY_FS_USE_* definition! */ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); switch (sbsec->behavior) { case SECURITY_FS_USE_XATTR: case SECURITY_FS_USE_TRANS: case SECURITY_FS_USE_TASK: case SECURITY_FS_USE_NATIVE: return 1; case SECURITY_FS_USE_GENFS: return selinux_is_genfs_special_handling(sb); /* Never allow relabeling on context mounts */ case SECURITY_FS_USE_MNTPOINT: case SECURITY_FS_USE_NONE: default: return 0; } } static int sb_check_xattr_support(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); u32 sid; int rc; /* * Make sure that the xattr handler exists and that no * error other than -ENODATA is returned by getxattr on * the root directory. -ENODATA is ok, as this may be * the first boot of the SELinux kernel before we have * assigned xattr values to the filesystem. */ if (!(root_inode->i_opflags & IOP_XATTR)) { pr_warn("SELinux: (dev %s, type %s) has no xattr support\n", sb->s_id, sb->s_type->name); goto fallback; } rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) { pr_warn("SELinux: (dev %s, type %s) has no security xattr handler\n", sb->s_id, sb->s_type->name); goto fallback; } else { pr_warn("SELinux: (dev %s, type %s) getxattr errno %d\n", sb->s_id, sb->s_type->name, -rc); return rc; } } return 0; fallback: /* No xattr support - try to fallback to genfs if possible. */ rc = security_genfs_sid(sb->s_type->name, "/", SECCLASS_DIR, &sid); if (rc) return -EOPNOTSUPP; pr_warn("SELinux: (dev %s, type %s) falling back to genfs\n", sb->s_id, sb->s_type->name); sbsec->behavior = SECURITY_FS_USE_GENFS; sbsec->sid = sid; return 0; } static int sb_finish_set_opts(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); int rc = 0; if (sbsec->behavior == SECURITY_FS_USE_XATTR) { rc = sb_check_xattr_support(sb); if (rc) return rc; } sbsec->flags |= SE_SBINITIALIZED; /* * Explicitly set or clear SBLABEL_MNT. It's not sufficient to simply * leave the flag untouched because sb_clone_mnt_opts might be handing * us a superblock that needs the flag to be cleared. */ if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; else sbsec->flags &= ~SBLABEL_MNT; /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); /* Initialize any other inodes associated with the superblock, e.g. inodes created prior to initial policy load or inodes created during get_sb by a pseudo filesystem that directly populates itself. */ spin_lock(&sbsec->isec_lock); while (!list_empty(&sbsec->isec_head)) { struct inode_security_struct *isec = list_first_entry(&sbsec->isec_head, struct inode_security_struct, list); struct inode *inode = isec->inode; list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { if (!IS_PRIVATE(inode)) inode_doinit_with_dentry(inode, NULL); iput(inode); } spin_lock(&sbsec->isec_lock); } spin_unlock(&sbsec->isec_lock); return rc; } static int bad_option(struct superblock_security_struct *sbsec, char flag, u32 old_sid, u32 new_sid) { char mnt_flags = sbsec->flags & SE_MNTMASK; /* check if the old mount command had the same options */ if (sbsec->flags & SE_SBINITIALIZED) if (!(sbsec->flags & flag) || (old_sid != new_sid)) return 1; /* check if we were passed the same options twice, * aka someone passed context=a,context=b */ if (!(sbsec->flags & SE_SBINITIALIZED)) if (mnt_flags & flag) return 1; return 0; } /* * Allow filesystems with binary mount data to explicitly set mount point * labeling information. */ static int selinux_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct selinux_mnt_opts *opts = mnt_opts; struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; int rc = 0; /* * Specifying internal flags without providing a place to * place the results is not allowed */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&sbsec->lock); if (!selinux_initialized()) { if (!opts) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { sbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } rc = -EINVAL; pr_warn("SELinux: Unable to set superblock options " "before the security server is initialized\n"); goto out; } /* * Binary mount data FS will come through this function twice. Once * from an explicit call and once from the generic calls from the vfs. * Since the generic VFS calls will not contain any security mount data * we need to skip the double mount verification. * * This does open a hole in which we will not notice if the first * mount using this sb set explicit options and a second mount using * this sb does not set any security options. (The first options * will be used for both mounts) */ if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA) && !opts) goto out; root_isec = backing_inode_security_novalidate(root); /* * parse the mount options, check if they are valid sids. * also check if someone is trying to mount the same sb more * than once with different security options. */ if (opts) { if (opts->fscontext_sid) { fscontext_sid = opts->fscontext_sid; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, fscontext_sid)) goto out_double_mount; sbsec->flags |= FSCONTEXT_MNT; } if (opts->context_sid) { context_sid = opts->context_sid; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, context_sid)) goto out_double_mount; sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext_sid) { rootcontext_sid = opts->rootcontext_sid; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, rootcontext_sid)) goto out_double_mount; sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext_sid) { defcontext_sid = opts->defcontext_sid; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, defcontext_sid)) goto out_double_mount; sbsec->flags |= DEFCONTEXT_MNT; } } if (sbsec->flags & SE_SBINITIALIZED) { /* previously mounted with options, but not on this attempt? */ if ((sbsec->flags & SE_MNTMASK) && !opts) goto out_double_mount; rc = 0; goto out; } if (strcmp(sb->s_type->name, "proc") == 0) sbsec->flags |= SE_SBPROC | SE_SBGENFS; if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "bpf") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "securityfs")) sbsec->flags |= SE_SBGENFS; if (!strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2")) sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR; if (!sbsec->behavior) { /* * Determine the labeling behavior to use for this * filesystem type. */ rc = security_fs_use(sb); if (rc) { pr_warn("%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); goto out; } } /* * If this is a user namespace mount and the filesystem type is not * explicitly whitelisted, then no contexts are allowed on the command * line and security labels must be ignored. */ if (sb->s_user_ns != &init_user_ns && strcmp(sb->s_type->name, "tmpfs") && strcmp(sb->s_type->name, "ramfs") && strcmp(sb->s_type->name, "devpts") && strcmp(sb->s_type->name, "overlay")) { if (context_sid || fscontext_sid || rootcontext_sid || defcontext_sid) { rc = -EACCES; goto out; } if (sbsec->behavior == SECURITY_FS_USE_XATTR) { sbsec->behavior = SECURITY_FS_USE_MNTPOINT; rc = security_transition_sid(current_sid(), current_sid(), SECCLASS_FILE, NULL, &sbsec->mntpoint_sid); if (rc) goto out; } goto out_set_opts; } /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; sbsec->sid = fscontext_sid; } /* * Switch to using mount point labeling behavior. * sets the label used on all file below the mountpoint, and will set * the superblock context if not already set. */ if (sbsec->flags & SE_SBNATIVE) { /* * This means we are initializing a superblock that has been * mounted before the SELinux was initialized and the * filesystem requested native labeling. We had already * returned SECURITY_LSM_NATIVE_LABELS in *set_kern_flags * in the original mount attempt, so now we just need to set * the SECURITY_FS_USE_NATIVE behavior. */ sbsec->behavior = SECURITY_FS_USE_NATIVE; } else if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) { sbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (context_sid) { if (!fscontext_sid) { rc = may_context_mount_sb_relabel(context_sid, sbsec, cred); if (rc) goto out; sbsec->sid = context_sid; } else { rc = may_context_mount_inode_relabel(context_sid, sbsec, cred); if (rc) goto out; } if (!rootcontext_sid) rootcontext_sid = context_sid; sbsec->mntpoint_sid = context_sid; sbsec->behavior = SECURITY_FS_USE_MNTPOINT; } if (rootcontext_sid) { rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, cred); if (rc) goto out; root_isec->sid = rootcontext_sid; root_isec->initialized = LABEL_INITIALIZED; } if (defcontext_sid) { if (sbsec->behavior != SECURITY_FS_USE_XATTR && sbsec->behavior != SECURITY_FS_USE_NATIVE) { rc = -EINVAL; pr_warn("SELinux: defcontext option is " "invalid for this filesystem type\n"); goto out; } if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, sbsec, cred); if (rc) goto out; } sbsec->def_sid = defcontext_sid; } out_set_opts: rc = sb_finish_set_opts(sb); out: mutex_unlock(&sbsec->lock); return rc; out_double_mount: rc = -EINVAL; pr_warn("SELinux: mount invalid. Same superblock, different " "security settings for (dev %s, type %s)\n", sb->s_id, sb->s_type->name); goto out; } static int selinux_cmp_sb_context(const struct super_block *oldsb, const struct super_block *newsb) { struct superblock_security_struct *old = selinux_superblock(oldsb); struct superblock_security_struct *new = selinux_superblock(newsb); char oldflags = old->flags & SE_MNTMASK; char newflags = new->flags & SE_MNTMASK; if (oldflags != newflags) goto mismatch; if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid) goto mismatch; if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid) goto mismatch; if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid) goto mismatch; if (oldflags & ROOTCONTEXT_MNT) { struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root); struct inode_security_struct *newroot = backing_inode_security(newsb->s_root); if (oldroot->sid != newroot->sid) goto mismatch; } return 0; mismatch: pr_warn("SELinux: mount invalid. Same superblock, " "different security settings for (dev %s, " "type %s)\n", newsb->s_id, newsb->s_type->name); return -EBUSY; } static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { int rc = 0; const struct superblock_security_struct *oldsbsec = selinux_superblock(oldsb); struct superblock_security_struct *newsbsec = selinux_superblock(newsb); int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT); int set_context = (oldsbsec->flags & CONTEXT_MNT); int set_rootcontext = (oldsbsec->flags & ROOTCONTEXT_MNT); /* * Specifying internal flags without providing a place to * place the results is not allowed. */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&newsbsec->lock); /* * if the parent was able to be mounted it clearly had no special lsm * mount options. thus we can safely deal with this superblock later */ if (!selinux_initialized()) { if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { newsbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } /* how can we clone if the old one wasn't set up?? */ BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED)); /* if fs is reusing a sb, make sure that the contexts match */ if (newsbsec->flags & SE_SBINITIALIZED) { mutex_unlock(&newsbsec->lock); if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; return selinux_cmp_sb_context(oldsb, newsb); } newsbsec->flags = oldsbsec->flags; newsbsec->sid = oldsbsec->sid; newsbsec->def_sid = oldsbsec->def_sid; newsbsec->behavior = oldsbsec->behavior; if (newsbsec->behavior == SECURITY_FS_USE_NATIVE && !(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) { rc = security_fs_use(newsb); if (rc) goto out; } if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) { newsbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (set_context) { u32 sid = oldsbsec->mntpoint_sid; if (!set_fscontext) newsbsec->sid = sid; if (!set_rootcontext) { struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = sid; } newsbsec->mntpoint_sid = sid; } if (set_rootcontext) { const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root); struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = oldisec->sid; } sb_finish_set_opts(newsb); out: mutex_unlock(&newsbsec->lock); return rc; } /* * NOTE: the caller is responsible for freeing the memory even if on error. */ static int selinux_add_opt(int token, const char *s, void **mnt_opts) { struct selinux_mnt_opts *opts = *mnt_opts; u32 *dst_sid; int rc; if (token == Opt_seclabel) /* eaten and completely ignored */ return 0; if (!s) return -EINVAL; if (!selinux_initialized()) { pr_warn("SELinux: Unable to set superblock options before the security server is initialized\n"); return -EINVAL; } if (!opts) { opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; *mnt_opts = opts; } switch (token) { case Opt_context: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->context_sid; break; case Opt_fscontext: if (opts->fscontext_sid) goto err; dst_sid = &opts->fscontext_sid; break; case Opt_rootcontext: if (opts->rootcontext_sid) goto err; dst_sid = &opts->rootcontext_sid; break; case Opt_defcontext: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->defcontext_sid; break; default: WARN_ON(1); return -EINVAL; } rc = security_context_str_to_sid(s, dst_sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid (%s) failed with errno=%d\n", s, rc); return rc; err: pr_warn(SEL_MOUNT_FAIL_MSG); return -EINVAL; } static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; u32 len; int rc; rc = security_sid_to_context(sid, &context, &len); if (!rc) { bool has_comma = strchr(context, ','); seq_putc(m, '='); if (has_comma) seq_putc(m, '\"'); seq_escape(m, context, "\"\n\\"); if (has_comma) seq_putc(m, '\"'); } kfree(context); return rc; } static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!selinux_initialized()) return 0; if (sbsec->flags & FSCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, FSCONTEXT_STR); rc = show_sid(m, sbsec->sid); if (rc) return rc; } if (sbsec->flags & CONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, CONTEXT_STR); rc = show_sid(m, sbsec->mntpoint_sid); if (rc) return rc; } if (sbsec->flags & DEFCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, DEFCONTEXT_STR); rc = show_sid(m, sbsec->def_sid); if (rc) return rc; } if (sbsec->flags & ROOTCONTEXT_MNT) { struct dentry *root = sb->s_root; struct inode_security_struct *isec = backing_inode_security(root); seq_putc(m, ','); seq_puts(m, ROOTCONTEXT_STR); rc = show_sid(m, isec->sid); if (rc) return rc; } if (sbsec->flags & SBLABEL_MNT) { seq_putc(m, ','); seq_puts(m, SECLABEL_STR); } return 0; } static inline u16 inode_mode_to_security_class(umode_t mode) { switch (mode & S_IFMT) { case S_IFSOCK: return SECCLASS_SOCK_FILE; case S_IFLNK: return SECCLASS_LNK_FILE; case S_IFREG: return SECCLASS_FILE; case S_IFBLK: return SECCLASS_BLK_FILE; case S_IFDIR: return SECCLASS_DIR; case S_IFCHR: return SECCLASS_CHR_FILE; case S_IFIFO: return SECCLASS_FIFO_FILE; } return SECCLASS_FILE; } static inline int default_protocol_stream(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP || protocol == IPPROTO_MPTCP); } static inline int default_protocol_dgram(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP); } static inline u16 socket_type_to_security_class(int family, int type, int protocol) { bool extsockclass = selinux_policycap_extsockclass(); switch (family) { case PF_UNIX: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: return SECCLASS_UNIX_STREAM_SOCKET; case SOCK_DGRAM: case SOCK_RAW: return SECCLASS_UNIX_DGRAM_SOCKET; } break; case PF_INET: case PF_INET6: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: if (default_protocol_stream(protocol)) return SECCLASS_TCP_SOCKET; else if (extsockclass && protocol == IPPROTO_SCTP) return SECCLASS_SCTP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DGRAM: if (default_protocol_dgram(protocol)) return SECCLASS_UDP_SOCKET; else if (extsockclass && (protocol == IPPROTO_ICMP || protocol == IPPROTO_ICMPV6)) return SECCLASS_ICMP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DCCP: return SECCLASS_DCCP_SOCKET; default: return SECCLASS_RAWIP_SOCKET; } break; case PF_NETLINK: switch (protocol) { case NETLINK_ROUTE: return SECCLASS_NETLINK_ROUTE_SOCKET; case NETLINK_SOCK_DIAG: return SECCLASS_NETLINK_TCPDIAG_SOCKET; case NETLINK_NFLOG: return SECCLASS_NETLINK_NFLOG_SOCKET; case NETLINK_XFRM: return SECCLASS_NETLINK_XFRM_SOCKET; case NETLINK_SELINUX: return SECCLASS_NETLINK_SELINUX_SOCKET; case NETLINK_ISCSI: return SECCLASS_NETLINK_ISCSI_SOCKET; case NETLINK_AUDIT: return SECCLASS_NETLINK_AUDIT_SOCKET; case NETLINK_FIB_LOOKUP: return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET; case NETLINK_CONNECTOR: return SECCLASS_NETLINK_CONNECTOR_SOCKET; case NETLINK_NETFILTER: return SECCLASS_NETLINK_NETFILTER_SOCKET; case NETLINK_DNRTMSG: return SECCLASS_NETLINK_DNRT_SOCKET; case NETLINK_KOBJECT_UEVENT: return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET; case NETLINK_GENERIC: return SECCLASS_NETLINK_GENERIC_SOCKET; case NETLINK_SCSITRANSPORT: return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET; case NETLINK_RDMA: return SECCLASS_NETLINK_RDMA_SOCKET; case NETLINK_CRYPTO: return SECCLASS_NETLINK_CRYPTO_SOCKET; default: return SECCLASS_NETLINK_SOCKET; } case PF_PACKET: return SECCLASS_PACKET_SOCKET; case PF_KEY: return SECCLASS_KEY_SOCKET; case PF_APPLETALK: return SECCLASS_APPLETALK_SOCKET; } if (extsockclass) { switch (family) { case PF_AX25: return SECCLASS_AX25_SOCKET; case PF_IPX: return SECCLASS_IPX_SOCKET; case PF_NETROM: return SECCLASS_NETROM_SOCKET; case PF_ATMPVC: return SECCLASS_ATMPVC_SOCKET; case PF_X25: return SECCLASS_X25_SOCKET; case PF_ROSE: return SECCLASS_ROSE_SOCKET; case PF_DECnet: return SECCLASS_DECNET_SOCKET; case PF_ATMSVC: return SECCLASS_ATMSVC_SOCKET; case PF_RDS: return SECCLASS_RDS_SOCKET; case PF_IRDA: return SECCLASS_IRDA_SOCKET; case PF_PPPOX: return SECCLASS_PPPOX_SOCKET; case PF_LLC: return SECCLASS_LLC_SOCKET; case PF_CAN: return SECCLASS_CAN_SOCKET; case PF_TIPC: return SECCLASS_TIPC_SOCKET; case PF_BLUETOOTH: return SECCLASS_BLUETOOTH_SOCKET; case PF_IUCV: return SECCLASS_IUCV_SOCKET; case PF_RXRPC: return SECCLASS_RXRPC_SOCKET; case PF_ISDN: return SECCLASS_ISDN_SOCKET; case PF_PHONET: return SECCLASS_PHONET_SOCKET; case PF_IEEE802154: return SECCLASS_IEEE802154_SOCKET; case PF_CAIF: return SECCLASS_CAIF_SOCKET; case PF_ALG: return SECCLASS_ALG_SOCKET; case PF_NFC: return SECCLASS_NFC_SOCKET; case PF_VSOCK: return SECCLASS_VSOCK_SOCKET; case PF_KCM: return SECCLASS_KCM_SOCKET; case PF_QIPCRTR: return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; case PF_MCTP: return SECCLASS_MCTP_SOCKET; #if PF_MAX > 46 #error New address family defined, please update this function. #endif } } return SECCLASS_SOCKET; } static int selinux_genfs_get_sid(struct dentry *dentry, u16 tclass, u16 flags, u32 *sid) { int rc; struct super_block *sb = dentry->d_sb; char *buffer, *path; buffer = (char *)__get_free_page(GFP_KERNEL); if (!buffer) return -ENOMEM; path = dentry_path_raw(dentry, buffer, PAGE_SIZE); if (IS_ERR(path)) rc = PTR_ERR(path); else { if (flags & SE_SBPROC) { /* each process gets a /proc/PID/ entry. Strip off the * PID part to get a valid selinux labeling. * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */ while (path[1] >= '0' && path[1] <= '9') { path[1] = '/'; path++; } } rc = security_genfs_sid(sb->s_type->name, path, tclass, sid); if (rc == -ENOENT) { /* No match in policy, mark as unlabeled. */ *sid = SECINITSID_UNLABELED; rc = 0; } } free_page((unsigned long)buffer); return rc; } static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry, u32 def_sid, u32 *sid) { #define INITCONTEXTLEN 255 char *context; unsigned int len; int rc; len = INITCONTEXTLEN; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { kfree(context); /* Need a larger buffer. Query for the right size. */ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0) return rc; len = rc; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); } if (rc < 0) { kfree(context); if (rc != -ENODATA) { pr_warn("SELinux: %s: getxattr returned %d for dev=%s ino=%ld\n", __func__, -rc, inode->i_sb->s_id, inode->i_ino); return rc; } *sid = def_sid; return 0; } rc = security_context_to_sid_default(context, rc, sid, def_sid, GFP_NOFS); if (rc) { char *dev = inode->i_sb->s_id; unsigned long ino = inode->i_ino; if (rc == -EINVAL) { pr_notice_ratelimited("SELinux: inode=%lu on dev=%s was found to have an invalid context=%s. This indicates you may need to relabel the inode or the filesystem in question.\n", ino, dev, context); } else { pr_warn("SELinux: %s: context_to_sid(%s) returned %d for dev=%s ino=%ld\n", __func__, context, -rc, dev, ino); } } kfree(context); return 0; } /* The inode's security attributes must be initialized before first use. */ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry) { struct superblock_security_struct *sbsec = NULL; struct inode_security_struct *isec = selinux_inode(inode); u32 task_sid, sid = 0; u16 sclass; struct dentry *dentry; int rc = 0; if (isec->initialized == LABEL_INITIALIZED) return 0; spin_lock(&isec->lock); if (isec->initialized == LABEL_INITIALIZED) goto out_unlock; if (isec->sclass == SECCLASS_FILE) isec->sclass = inode_mode_to_security_class(inode->i_mode); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SE_SBINITIALIZED)) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ spin_lock(&sbsec->isec_lock); if (list_empty(&isec->list)) list_add(&isec->list, &sbsec->isec_head); spin_unlock(&sbsec->isec_lock); goto out_unlock; } sclass = isec->sclass; task_sid = isec->task_sid; sid = isec->sid; isec->initialized = LABEL_PENDING; spin_unlock(&isec->lock); switch (sbsec->behavior) { /* * In case of SECURITY_FS_USE_NATIVE we need to re-fetch the labels * via xattr when called from delayed_superblock_init(). */ case SECURITY_FS_USE_NATIVE: case SECURITY_FS_USE_XATTR: if (!(inode->i_opflags & IOP_XATTR)) { sid = sbsec->def_sid; break; } /* Need a dentry, since the xattr API requires one. Life would be simpler if we could just pass the inode. */ if (opt_dentry) { /* Called from d_instantiate or d_splice_alias. */ dentry = dget(opt_dentry); } else { /* * Called from selinux_complete_init, try to find a dentry. * Some filesystems really want a connected one, so try * that first. We could split SECURITY_FS_USE_XATTR in * two, depending upon that... */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } if (!dentry) { /* * this is can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as these * will get fixed up the next time we go through * inode_doinit with a dentry, before these inodes could * be used again by userspace. */ goto out_invalid; } rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid, &sid); dput(dentry); if (rc) goto out; break; case SECURITY_FS_USE_TASK: sid = task_sid; break; case SECURITY_FS_USE_TRANS: /* Default to the fs SID. */ sid = sbsec->sid; /* Try to obtain a transition SID. */ rc = security_transition_sid(task_sid, sid, sclass, NULL, &sid); if (rc) goto out; break; case SECURITY_FS_USE_MNTPOINT: sid = sbsec->mntpoint_sid; break; default: /* Default to the fs superblock SID. */ sid = sbsec->sid; if ((sbsec->flags & SE_SBGENFS) && (!S_ISLNK(inode->i_mode) || selinux_policycap_genfs_seclabel_symlinks())) { /* We must have a dentry to determine the label on * procfs inodes */ if (opt_dentry) { /* Called from d_instantiate or * d_splice_alias. */ dentry = dget(opt_dentry); } else { /* Called from selinux_complete_init, try to * find a dentry. Some filesystems really want * a connected one, so try that first. */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } /* * This can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as * these will get fixed up the next time we go through * inode_doinit() with a dentry, before these inodes * could be used again by userspace. */ if (!dentry) goto out_invalid; rc = selinux_genfs_get_sid(dentry, sclass, sbsec->flags, &sid); if (rc) { dput(dentry); goto out; } if ((sbsec->flags & SE_SBGENFS_XATTR) && (inode->i_opflags & IOP_XATTR)) { rc = inode_doinit_use_xattr(inode, dentry, sid, &sid); if (rc) { dput(dentry); goto out; } } dput(dentry); } break; } out: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { if (rc) { isec->initialized = LABEL_INVALID; goto out_unlock; } isec->initialized = LABEL_INITIALIZED; isec->sid = sid; } out_unlock: spin_unlock(&isec->lock); return rc; out_invalid: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { isec->initialized = LABEL_INVALID; isec->sid = sid; } spin_unlock(&isec->lock); return 0; } /* Convert a Linux signal to an access vector. */ static inline u32 signal_to_av(int sig) { u32 perm = 0; switch (sig) { case SIGCHLD: /* Commonly granted from child to parent. */ perm = PROCESS__SIGCHLD; break; case SIGKILL: /* Cannot be caught or ignored */ perm = PROCESS__SIGKILL; break; case SIGSTOP: /* Cannot be caught or ignored */ perm = PROCESS__SIGSTOP; break; default: /* All other signals. */ perm = PROCESS__SIGNAL; break; } return perm; } #if CAP_LAST_CAP > 63 #error Fix SELinux to handle capabilities > 63. #endif /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; u16 sclass; u32 sid = cred_sid(cred); u32 av = CAP_TO_MASK(cap); int rc; ad.type = LSM_AUDIT_DATA_CAP; ad.u.cap = cap; switch (CAP_TO_INDEX(cap)) { case 0: sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS; break; case 1: sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS; break; default: pr_err("SELinux: out of range capability %d\n", cap); BUG(); return -EINVAL; } rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad); if (rc2) return rc2; } return rc; } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; if (unlikely(IS_PRIVATE(inode))) return 0; sid = cred_sid(cred); isec = selinux_inode(inode); return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ static inline int dentry_has_perm(const struct cred *cred, struct dentry *dentry, u32 av) { struct inode *inode = d_backing_inode(dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; __inode_security_revalidate(inode, dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, const struct path *path, u32 av) { struct inode *inode = d_backing_inode(path->dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; __inode_security_revalidate(inode, path->dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ static inline int file_path_has_perm(const struct cred *cred, struct file *file, u32 av) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return inode_has_perm(cred, file_inode(file), av, &ad); } #ifdef CONFIG_BPF_SYSCALL static int bpf_fd_pass(const struct file *file, u32 sid); #endif /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to check a particular permission to the file. Access to the descriptor is implicitly granted if it has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ static int file_has_perm(const struct cred *cred, struct file *file, u32 av) { struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct common_audit_data ad; u32 sid = cred_sid(cred); int rc; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, cred_sid(cred)); if (rc) return rc; #endif /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) rc = inode_has_perm(cred, inode, av, &ad); out: return rc; } /* * Determine the label for an inode that might be unioned. */ static int selinux_determine_inode_label(const struct task_security_struct *tsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) { const struct superblock_security_struct *sbsec = selinux_superblock(dir->i_sb); if ((sbsec->flags & SE_SBINITIALIZED) && (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && tsec->create_sid) { *_new_isid = tsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); return security_transition_sid(tsec->sid, dsec->sid, tclass, name, _new_isid); } return 0; } /* Check whether a task can create a file. */ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; struct common_audit_data ad; int rc; dsec = inode_security(dir); sbsec = selinux_superblock(dir->i_sb); sid = tsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } #define MAY_LINK 0 #define MAY_UNLINK 1 #define MAY_RMDIR 2 /* Check whether a task can link, unlink, or rmdir a file/directory. */ static int may_link(struct inode *dir, struct dentry *dentry, int kind) { struct inode_security_struct *dsec, *isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int rc; dsec = inode_security(dir); isec = backing_inode_security(dentry); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; switch (kind) { case MAY_LINK: av = FILE__LINK; break; case MAY_UNLINK: av = FILE__UNLINK; break; case MAY_RMDIR: av = DIR__RMDIR; break; default: pr_warn("SELinux: %s: unrecognized kind %d\n", __func__, kind); return 0; } rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad); return rc; } static inline int may_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; old_dsec = inode_security(old_dir); old_isec = backing_inode_security(old_dentry); old_is_dir = d_is_dir(old_dentry); new_dsec = inode_security(new_dir); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = old_dentry; rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; } ad.u.dentry = new_dentry; av = DIR__ADD_NAME | DIR__SEARCH; if (d_is_positive(new_dentry)) av |= DIR__REMOVE_NAME; rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (d_is_positive(new_dentry)) { new_isec = backing_inode_security(new_dentry); new_is_dir = d_is_dir(new_dentry); rc = avc_has_perm(sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) return rc; } return 0; } /* Check whether a task can perform a filesystem operation. */ static int superblock_has_perm(const struct cred *cred, const struct super_block *sb, u32 perms, struct common_audit_data *ad) { struct superblock_security_struct *sbsec; u32 sid = cred_sid(cred); sbsec = selinux_superblock(sb); return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ static inline u32 file_mask_to_av(int mode, int mask) { u32 av = 0; if (!S_ISDIR(mode)) { if (mask & MAY_EXEC) av |= FILE__EXECUTE; if (mask & MAY_READ) av |= FILE__READ; if (mask & MAY_APPEND) av |= FILE__APPEND; else if (mask & MAY_WRITE) av |= FILE__WRITE; } else { if (mask & MAY_EXEC) av |= DIR__SEARCH; if (mask & MAY_WRITE) av |= DIR__WRITE; if (mask & MAY_READ) av |= DIR__READ; } return av; } /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(const struct file *file) { u32 av = 0; if (file->f_mode & FMODE_READ) av |= FILE__READ; if (file->f_mode & FMODE_WRITE) { if (file->f_flags & O_APPEND) av |= FILE__APPEND; else av |= FILE__WRITE; } if (!av) { /* * Special file opened with flags 3 for ioctl-only use. */ av = FILE__IOCTL; } return av; } /* * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) { u32 av = file_to_av(file); struct inode *inode = file_inode(file); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC) av |= FILE__OPEN; return av; } /* Hook functions begin here. */ static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } static int selinux_binder_transaction(const struct cred *from, const struct cred *to) { u32 mysid = current_sid(); u32 fromsid = cred_sid(from); u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL); if (rc) return rc; } return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } static int selinux_binder_transfer_binder(const struct cred *from, const struct cred *to) { return avc_has_perm(cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } static int selinux_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; struct common_audit_data ad; int rc; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, sid); if (rc) return rc; #endif if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; isec = backing_inode_security(dentry); return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file), &ad); } static int selinux_ptrace_access_check(struct task_struct *child, unsigned int mode) { u32 sid = current_sid(); u32 csid = task_sid_obj(child); if (mode & PTRACE_MODE_READ) return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL); return avc_has_perm(sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(task_sid_obj(parent), task_sid_obj(current), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return avc_has_perm(current_sid(), task_sid_obj(target), SECCLASS_PROCESS, PROCESS__GETCAP, NULL); } static int selinux_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return avc_has_perm(cred_sid(old), cred_sid(new), SECCLASS_PROCESS, PROCESS__SETCAP, NULL); } /* * (This comment used to live with the selinux_task_setuid hook, * which was removed). * * Since setuid only affects the current process, and since the SELinux * controls are not based on the Linux identity attributes, SELinux does not * need to control this operation. However, SELinux does control the use of * the CAP_SETUID and CAP_SETGID capabilities using the capable hook. */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, const struct super_block *sb) { const struct cred *cred = current_cred(); int rc = 0; if (!sb) return 0; switch (cmds) { case Q_SYNC: case Q_QUOTAON: case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: case Q_XQUOTAOFF: case Q_XQUOTAON: case Q_XSETQLIM: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: case Q_XGETQUOTA: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETNEXTQUOTA: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ break; } return rc; } static int selinux_quota_on(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) { switch (type) { case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL); case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, NULL); } /* All other syslog types */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL); } /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { int rc, cap_sys_admin = 0; rc = cred_has_capability(current_cred(), CAP_SYS_ADMIN, CAP_OPT_NOAUDIT, true); if (rc == 0) cap_sys_admin = 1; return cap_sys_admin; } /* binprm security operations */ static u32 ptrace_parent_sid(void) { u32 sid = 0; struct task_struct *tracer; rcu_read_lock(); tracer = ptrace_parent(current); if (tracer) sid = task_sid_obj(tracer); rcu_read_unlock(); return sid; } static int check_nnp_nosuid(const struct linux_binprm *bprm, const struct task_security_struct *old_tsec, const struct task_security_struct *new_tsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); int rc; u32 av; if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ if (new_tsec->sid == old_tsec->sid) return 0; /* No change in credentials */ /* * If the policy enables the nnp_nosuid_transition policy capability, * then we permit transitions under NNP or nosuid if the * policy allows the corresponding permission between * the old and new contexts. */ if (selinux_policycap_nnp_nosuid_transition()) { av = 0; if (nnp) av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; } /* * We also permit NNP or nosuid transitions to bounded SIDs, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ rc = security_bounded_transition(old_tsec->sid, new_tsec->sid); if (!rc) return 0; /* * On failure, preserve the errno values for NNP vs nosuid. * NNP: Operation not permitted for caller. * nosuid: Permission denied to file. */ if (nnp) return -EPERM; return -EACCES; } static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { const struct task_security_struct *old_tsec; struct task_security_struct *new_tsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); int rc; /* SELinux context only depends on initial program or script and not * the script interpreter */ old_tsec = selinux_cred(current_cred()); new_tsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ new_tsec->sid = old_tsec->sid; new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ new_tsec->create_sid = 0; new_tsec->keycreate_sid = 0; new_tsec->sockcreate_sid = 0; /* * Before policy is loaded, label any task outside kernel space * as SECINITSID_INIT, so that any userspace tasks surviving from * early boot end up with a label different from SECINITSID_KERNEL * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL). */ if (!selinux_initialized()) { new_tsec->sid = SECINITSID_INIT; /* also clear the exec_sid just in case */ new_tsec->exec_sid = 0; return 0; } if (old_tsec->exec_sid) { new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ new_tsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ rc = security_transition_sid(old_tsec->sid, isec->sid, SECCLASS_PROCESS, NULL, &new_tsec->sid); if (rc) return rc; /* * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) new_tsec->sid = old_tsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; if (new_tsec->sid == old_tsec->sid) { rc = avc_has_perm(old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; rc = avc_has_perm(new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) return -EPERM; } /* Make sure that anyone attempting to ptrace over a task that * changes its SID has the appropriate permit */ if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { rc = avc_has_perm(ptsid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) return -EPERM; } } /* Clear any possibly unsafe personality bits on exec: */ bprm->per_clear |= PER_CLEAR_ON_SETID; /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; } return 0; } static int match_file(const void *p, struct file *file, unsigned fd) { return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0; } /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) { struct file *file, *devnull = NULL; struct tty_struct *tty; int drop_tty = 0; unsigned n; tty = get_current_tty(); if (tty) { spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; /* Revalidate access to controlling tty. Use file_path_has_perm on the tty path directly rather than using file_has_perm, as this particular open file may belong to another process and we are only interested in the inode-based check here. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); } /* Reset controlling tty. */ if (drop_tty) no_tty(); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, cred); if (!n) /* none found? */ return; devnull = dentry_open(&selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); if (devnull) fput(devnull); } /* * Prepare a process for imminent new credential changes due to exec */ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) { struct task_security_struct *new_tsec; struct rlimit *rlim, *initrlim; int rc, i; new_tsec = selinux_cred(bprm->cred); if (new_tsec->sid == new_tsec->osid) return; /* Close files for which the new task SID is not authorized. */ flush_unauthorized_files(bprm->cred, current->files); /* Always clear parent death signal on SID transitions. */ current->pdeath_signal = 0; /* Check whether the new SID can inherit resource limits from the old * SID. If not, reset all soft limits to the lower of the current * task's hard limit and the init task's soft limit. * * Note that the setting of hard limits (even to lower them) can be * controlled by the setrlimit check. The inclusion of the init task's * soft limit into the computation is to avoid resetting soft limits * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ task_lock(current); for (i = 0; i < RLIM_NLIMITS; i++) { rlim = current->signal->rlim + i; initrlim = init_task.signal->rlim + i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } task_unlock(current); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(current, rlimit(RLIMIT_CPU)); } } /* * Clean up the process immediately after the installation of new credentials * due to exec */ static void selinux_bprm_committed_creds(const struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 osid, sid; int rc; osid = tsec->osid; sid = tsec->sid; if (sid == osid) return; /* Check whether the new SID can inherit signal state from the old SID. * If not, clear itimers to avoid subsequent signal generation and * flush and unblock signals. * * This must occur _after_ the task SID has been updated so that any * kill done after the flush will be checked against the new SID. */ rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { clear_itimer(); spin_lock_irq(&unrcu_pointer(current->sighand)->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); flush_sigqueue(¤t->signal->shared_pending); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); } spin_unlock_irq(&unrcu_pointer(current->sighand)->siglock); } /* Wake up the parent if it is waiting so that it can recheck * wait permission to the new task SID. */ read_lock(&tasklist_lock); __wake_up_parent(current, unrcu_pointer(current->real_parent)); read_unlock(&tasklist_lock); } /* superblock security operations */ static int selinux_sb_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); mutex_init(&sbsec->lock); INIT_LIST_HEAD(&sbsec->isec_head); spin_lock_init(&sbsec->isec_lock); sbsec->sid = SECINITSID_UNLABELED; sbsec->def_sid = SECINITSID_FILE; sbsec->mntpoint_sid = SECINITSID_UNLABELED; return 0; } static inline int opt_len(const char *s) { bool open_quote = false; int len; char c; for (len = 0; (c = s[len]) != '\0'; len++) { if (c == '"') open_quote = !open_quote; if (c == ',' && !open_quote) break; } return len; } static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) { char *from = options; char *to = options; bool first = true; int rc; while (1) { int len = opt_len(from); int token; char *arg = NULL; token = match_opt_prefix(from, len, &arg); if (token != Opt_error) { char *p, *q; /* strip quotes */ if (arg) { for (p = q = arg; p < from + len; p++) { char c = *p; if (c != '"') *q++ = c; } arg = kmemdup_nul(arg, q - arg, GFP_KERNEL); if (!arg) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, arg, mnt_opts); kfree(arg); arg = NULL; if (unlikely(rc)) { goto free_opt; } } else { if (!first) { // copy with preceding comma from--; len++; } if (to != from) memmove(to, from, len); to += len; first = false; } if (!from[len]) break; from += len + 1; } *to = '\0'; return 0; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * Superblock not initialized (i.e. no options) - reject if any * options specified, otherwise accept. */ if (!(sbsec->flags & SE_SBINITIALIZED)) return opts ? 1 : 0; /* * Superblock initialized and no options specified - reject if * superblock has any options set, otherwise accept. */ if (!opts) return (sbsec->flags & SE_MNTMASK) ? 1 : 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) return 1; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) return 1; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) return 1; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) return 1; } return 0; } static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!opts) return 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) goto out_bad_option; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) goto out_bad_option; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) goto out_bad_option; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) goto out_bad_option; } return 0; out_bad_option: pr_warn("SELinux: unable to change security options " "during remount (dev %s, type=%s)\n", sb->s_id, sb->s_type->name); return -EINVAL; } static int selinux_sb_kern_mount(const struct super_block *sb) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = sb->s_root; return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry->d_sb->s_root; return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { const struct cred *cred = current_cred(); if (flags & MS_REMOUNT) return superblock_has_perm(cred, path->dentry->d_sb, FILESYSTEM__REMOUNT, NULL); else return path_has_perm(cred, path, FILE__MOUNTON); } static int selinux_move_mount(const struct path *from_path, const struct path *to_path) { const struct cred *cred = current_cred(); return path_has_perm(cred, to_path, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { const struct cred *cred = current_cred(); return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } static int selinux_fs_context_submount(struct fs_context *fc, struct super_block *reference) { const struct superblock_security_struct *sbsec = selinux_superblock(reference); struct selinux_mnt_opts *opts; /* * Ensure that fc->security remains NULL when no options are set * as expected by selinux_set_mnt_opts(). */ if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT))) return 0; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; if (sbsec->flags & FSCONTEXT_MNT) opts->fscontext_sid = sbsec->sid; if (sbsec->flags & CONTEXT_MNT) opts->context_sid = sbsec->mntpoint_sid; if (sbsec->flags & DEFCONTEXT_MNT) opts->defcontext_sid = sbsec->def_sid; fc->security = opts; return 0; } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { const struct selinux_mnt_opts *src = src_fc->security; if (!src) return 0; fc->security = kmemdup(src, sizeof(*src), GFP_KERNEL); return fc->security ? 0 : -ENOMEM; } static const struct fs_parameter_spec selinux_fs_parameters[] = { fsparam_string(CONTEXT_STR, Opt_context), fsparam_string(DEFCONTEXT_STR, Opt_defcontext), fsparam_string(FSCONTEXT_STR, Opt_fscontext), fsparam_string(ROOTCONTEXT_STR, Opt_rootcontext), fsparam_flag (SECLABEL_STR, Opt_seclabel), {} }; static int selinux_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; int opt; opt = fs_parse(fc, selinux_fs_parameters, param, &result); if (opt < 0) return opt; return selinux_add_opt(opt, param->string, &fc->security); } /* inode security operations */ static int selinux_inode_alloc_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; return 0; } static void selinux_inode_free_security(struct inode *inode) { inode_free_security(inode); } static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) { u32 newsid; int rc; rc = selinux_determine_inode_label(selinux_cred(current_cred()), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; if (xattr_name) *xattr_name = XATTR_NAME_SELINUX; return security_sid_to_context(newsid, (char **)ctx, ctxlen); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { u32 newsid; int rc; struct task_security_struct *tsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; tsec = selinux_cred(new); tsec->create_sid = newsid; return 0; } static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); u32 newsid, clen; u16 newsclass; int rc; char *context; sbsec = selinux_superblock(dir->i_sb); newsid = tsec->create_sid; newsclass = inode_mode_to_security_class(inode->i_mode); rc = selinux_determine_inode_label(tsec, dir, qstr, newsclass, &newsid); if (rc) return rc; /* Possibly defer initialization to selinux_complete_init. */ if (sbsec->flags & SE_SBINITIALIZED) { struct inode_security_struct *isec = selinux_inode(inode); isec->sclass = newsclass; isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; } if (!selinux_initialized() || !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (xattr) { rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; xattr->value = context; xattr->value_len = clen; xattr->name = XATTR_SELINUX_SUFFIX; } return 0; } static int selinux_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { u32 sid = current_sid(); struct common_audit_data ad; struct inode_security_struct *isec; int rc; if (unlikely(!selinux_initialized())) return 0; isec = selinux_inode(inode); /* * We only get here once per ephemeral inode. The inode has * been initialized via inode_alloc_security but is otherwise * untouched. */ if (context_inode) { struct inode_security_struct *context_isec = selinux_inode(context_inode); if (context_isec->initialized != LABEL_INITIALIZED) { pr_err("SELinux: context_inode is not initialized\n"); return -EACCES; } isec->sclass = context_isec->sclass; isec->sid = context_isec->sid; } else { isec->sclass = SECCLASS_ANON_INODE; rc = security_transition_sid( sid, sid, isec->sclass, name, &isec->sid); if (rc) return rc; } isec->initialized = LABEL_INITIALIZED; /* * Now that we've initialized security, check whether we're * allowed to actually create this type of anonymous inode. */ ad.type = LSM_AUDIT_DATA_ANONINODE; ad.u.anonclass = name ? (const char *)name->name : "?"; return avc_has_perm(sid, isec->sid, isec->sclass, FILE__CREATE, &ad); } static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { return may_create(dir, dentry, SECCLASS_FILE); } static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { return may_link(dir, old_dentry, MAY_LINK); } static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_UNLINK); } static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name) { return may_create(dir, dentry, SECCLASS_LNK_FILE); } static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask) { return may_create(dir, dentry, SECCLASS_DIR); } static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_RMDIR); } static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return may_create(dir, dentry, inode_mode_to_security_class(mode)); } static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry, struct inode *new_inode, struct dentry *new_dentry) { return may_rename(old_inode, old_dentry, new_inode, new_dentry); } static int selinux_inode_readlink(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { struct common_audit_data ad; struct inode_security_struct *isec; u32 sid = current_sid(); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = inode_security_rcu(inode, rcu); if (IS_ERR(isec)) return PTR_ERR(isec); return avc_has_perm(sid, isec->sid, isec->sclass, FILE__READ, &ad); } static noinline int audit_inode_permission(struct inode *inode, u32 perms, u32 audited, u32 denied, int result) { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; return slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); } static int selinux_inode_permission(struct inode *inode, int mask) { u32 perms; bool from_access; bool no_block = mask & MAY_NOT_BLOCK; struct inode_security_struct *isec; u32 sid = current_sid(); struct av_decision avd; int rc, rc2; u32 audited, denied; from_access = mask & MAY_ACCESS; mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND); /* No permission to check. Existence test. */ if (!mask) return 0; if (unlikely(IS_PRIVATE(inode))) return 0; perms = file_mask_to_av(inode->i_mode, mask); isec = inode_security_rcu(inode, no_block); if (IS_ERR(isec)) return PTR_ERR(isec); rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; return rc; } static int selinux_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; __u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE | ATTR_FORCE); if (!ia_valid) return 0; } if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC && (ia_valid & ATTR_SIZE) && !(ia_valid & ATTR_FILE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); } static int selinux_inode_getattr(const struct path *path) { return path_has_perm(current_cred(), path, FILE__GETATTR); } static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } static int selinux_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; struct superblock_security_struct *sbsec; struct common_audit_data ad; u32 newsid, sid = current_sid(); int rc = 0; if (strcmp(name, XATTR_NAME_SELINUX)) { rc = cap_inode_setxattr(dentry, name, value, size, flags); if (rc) return rc; /* Not an attribute we recognize, so just check the ordinary setattr permission. */ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } if (!selinux_initialized()) return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = backing_inode_security(dentry); rc = avc_has_perm(sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (value) { const char *str = value; if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; } else { audit_size = 0; } ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return rc; audit_log_format(ab, "op=setxattr invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return rc; } rc = security_context_to_sid_force(value, size, &newsid); } if (rc) return rc; rc = avc_has_perm(sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; rc = security_validate_transition(isec->sid, newsid, sid, isec->sclass); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } static int selinux_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static int selinux_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__GETATTR); } static int selinux_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; u32 newsid; int rc; if (strcmp(name, XATTR_NAME_SELINUX)) { /* Not an attribute we recognize, so nothing to do. */ return; } if (!selinux_initialized()) { /* If we haven't even been initialized, then we can't validate * against a policy, so leave the label as invalid. It may * resolve to a valid label on the next revalidation try if * we've since initialized. */ return; } rc = security_context_to_sid_force(value, size, &newsid); if (rc) { pr_err("SELinux: unable to map context to SID" "for (%s, %lu), rc=%d\n", inode->i_sb->s_id, inode->i_ino, -rc); return; } isec = backing_inode_security(dentry); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { if (strcmp(name, XATTR_NAME_SELINUX)) { int rc = cap_inode_removexattr(idmap, dentry, name); if (rc) return rc; /* Not an attribute we recognize, so just check the ordinary setattr permission. */ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } if (!selinux_initialized()) return 0; /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; } static int selinux_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { int ret; u32 perm; struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; /* * Set permission needed based on the type of mark being set. * Performs an additional check for sb watches. */ switch (obj_type) { case FSNOTIFY_OBJ_TYPE_VFSMOUNT: perm = FILE__WATCH_MOUNT; break; case FSNOTIFY_OBJ_TYPE_SB: perm = FILE__WATCH_SB; ret = superblock_has_perm(current_cred(), path->dentry->d_sb, FILESYSTEM__WATCH, &ad); if (ret) return ret; break; case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; default: return -EINVAL; } /* blocking watches require the file:watch_with_perm permission */ if (mask & (ALL_FSNOTIFY_PERM_EVENTS)) perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); } /* * Copy the inode security context value to the user. * * Permission check is handled by selinux_inode_getxattr hook. */ static int selinux_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { u32 size; int error; char *context = NULL; struct inode_security_struct *isec; /* * If we're not initialized yet, then we can't validate contexts, so * just let vfs_getxattr fall back to using the on-disk xattr. */ if (!selinux_initialized() || strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; /* * If the caller has CAP_MAC_ADMIN, then get the raw context * value even if it is not defined by current policy; otherwise, * use the in-core value under current policy. * Use the non-auditing forms of the permission checks since * getxattr may be called by unprivileged processes commonly * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ isec = inode_security(inode); if (has_cap_mac_admin(false)) error = security_sid_to_context_force(isec->sid, &context, &size); else error = security_sid_to_context(isec->sid, &context, &size); if (error) return error; error = size; if (alloc) { *buffer = context; goto out_nofree; } kfree(context); out_nofree: return error; } static int selinux_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct inode_security_struct *isec = inode_security_novalidate(inode); struct superblock_security_struct *sbsec; u32 newsid; int rc; if (strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!value || !size) return -EACCES; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc) return rc; spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return 0; } static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { const int len = sizeof(XATTR_NAME_SELINUX); if (!selinux_initialized()) return 0; if (buffer && len <= buffer_size) memcpy(buffer, XATTR_NAME_SELINUX, len); return len; } static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { u32 sid; struct task_security_struct *tsec; struct cred *new_creds = *new; if (new_creds == NULL) { new_creds = prepare_creds(); if (!new_creds) return -ENOMEM; } tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getsecid(d_inode(src), &sid); tsec->create_sid = sid; *new = new_creds; return 0; } static int selinux_inode_copy_up_xattr(struct dentry *dentry, const char *name) { /* The copy_up hook above sets the initial context on an inode, but we * don't then want to overwrite it by blindly copying all the lower * xattrs up. Instead, filter out SELinux-related xattrs following * policy load. */ if (selinux_initialized() && strcmp(name, XATTR_NAME_SELINUX) == 0) return 1; /* Discard */ /* * Any other attribute apart from SELINUX is not claimed, supported * by selinux. */ return -EOPNOTSUPP; } /* kernfs node operations */ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0); if (rc == -ENODATA) return 0; else if (rc < 0) return rc; clen = (u32)rc; context = kmalloc(clen, GFP_KERNEL); if (!context) return -ENOMEM; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen); if (rc < 0) { kfree(context); return rc; } rc = security_context_to_sid(context, clen, &parent_sid, GFP_KERNEL); kfree(context); if (rc) return rc; if (tsec->create_sid) { newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); struct qstr q; q.name = kn->name; q.hash_len = hashlen_string(kn_dir, kn->name); rc = security_transition_sid(tsec->sid, parent_sid, secclass, &q, &newsid); if (rc) return rc; } rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen, XATTR_CREATE); kfree(context); return rc; } /* file security operations */ static int selinux_revalidate_file_permission(struct file *file, int mask) { const struct cred *cred = current_cred(); struct inode *inode = file_inode(file); /* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */ if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; return file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); } static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file_inode(file); struct file_security_struct *fsec = selinux_file(file); struct inode_security_struct *isec; u32 sid = current_sid(); if (!mask) /* No permission to check. Existence test. */ return 0; isec = inode_security(inode); if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno()) /* No change since file_open check. */ return 0; return selinux_revalidate_file_permission(file, mask); } static int selinux_file_alloc_security(struct file *file) { struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); fsec->sid = sid; fsec->fown_sid = sid; return 0; } /* * Check whether a task has the ioctl permission and cmd * operation to an inode. */ static int ioctl_has_perm(const struct cred *cred, struct file *file, u32 requested, u16 cmd) { struct common_audit_data ad; struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct inode_security_struct *isec; struct lsm_ioctlop_audit ioctl; u32 ssid = cred_sid(cred); int rc; u8 driver = cmd >> 8; u8 xperm = cmd & 0xff; ad.type = LSM_AUDIT_DATA_IOCTL_OP; ad.u.op = &ioctl; ad.u.op->cmd = cmd; ad.u.op->path = file->f_path; if (ssid != fsec->sid) { rc = avc_has_perm(ssid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } if (unlikely(IS_PRIVATE(inode))) return 0; isec = inode_security(inode); rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, driver, xperm, &ad); out: return rc; } static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int error = 0; switch (cmd) { case FIONREAD: case FIBMAP: case FIGETBSZ: case FS_IOC_GETFLAGS: case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: case FIOASYNC: error = file_has_perm(cred, file, 0); break; case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, CAP_OPT_NONE, true); break; case FIOCLEX: case FIONCLEX: if (!selinux_policycap_ioctl_skip_cloexec()) error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); break; /* default case assumes that the command will go * to the file's ioctl() function. */ default: error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); } return error; } static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { /* * If we are in a 64-bit kernel running 32-bit userspace, we need to * make sure we don't compare 32-bit flags to 64-bit flags. */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; break; case FS_IOC32_SETFLAGS: cmd = FS_IOC_SETFLAGS; break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case FS_IOC32_SETVERSION: cmd = FS_IOC_SETVERSION; break; default: break; } return selinux_file_ioctl(file, cmd, arg); } static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); int rc = 0; if (default_noexec && (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) || (!shared && (prot & PROT_WRITE)))) { /* * We are making executable an anonymous mapping or a * private file mapping that will also be writable. * This has an additional check. */ rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM, NULL); if (rc) goto error; } if (file) { /* read access is always possible with a mapping */ u32 av = FILE__READ; /* write access only matters if the mapping is shared */ if (shared && (prot & PROT_WRITE)) av |= FILE__WRITE; if (prot & PROT_EXEC) av |= FILE__EXECUTE; return file_has_perm(cred, file, av); } error: return rc; } static int selinux_mmap_addr(unsigned long addr) { int rc = 0; if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { u32 sid = current_sid(); rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); } return rc; } static int selinux_mmap_file(struct file *file, unsigned long reqprot __always_unused, unsigned long prot, unsigned long flags) { struct common_audit_data ad; int rc; if (file) { ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; rc = inode_has_perm(current_cred(), file_inode(file), FILE__MAP, &ad); if (rc) return rc; } return file_map_prot_check(file, prot, (flags & MAP_TYPE) == MAP_SHARED); } static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot __always_unused, unsigned long prot) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; if (vma_is_initial_heap(vma)) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || vma_is_stack_for_current(vma))) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECSTACK, NULL); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has * had some COW done. Since pages might have been * written, check ability to execute the possibly * modified content. This typically should only * occur for text relocations. */ rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; } return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED); } static int selinux_file_lock(struct file *file, unsigned int cmd) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int err = 0; switch (cmd) { case F_SETFL: if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { err = file_has_perm(cred, file, FILE__WRITE); break; } fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: case F_GETOWN: case F_GETSIG: case F_GETOWNER_UIDS: /* Just check FD__USE permission */ err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: case F_SETLKW: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: case F_SETLKW64: #endif err = file_has_perm(cred, file, FILE__LOCK); break; } return err; } static void selinux_file_set_fowner(struct file *file) { struct file_security_struct *fsec; fsec = selinux_file(file); fsec->fown_sid = current_sid(); } static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; u32 sid = task_sid_obj(tsk); u32 perm; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = container_of(fown, struct file, f_owner); fsec = selinux_file(file); if (!signum) perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */ else perm = signal_to_av(signum); return avc_has_perm(fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, file_to_av(file)); } static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; fsec = selinux_file(file); isec = inode_security(file_inode(file)); /* * Save inode label and policy sequence number * at open-time so that selinux_file_permission * can determine whether revalidation is necessary. * Task label is already saved in the file security * struct as its SID. */ fsec->isid = isec->sid; fsec->pseqno = avc_policy_seqno(); /* * Since the inode label or policy seqno may have changed * between the selinux_inode_permission check and the saving * of state above, recheck that access is still permitted. * Otherwise, access might never be revalidated against the * new inode label or new policy. * This check is not redundant - do not remove. */ return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ static int selinux_task_alloc(struct task_struct *task, unsigned long clone_flags) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; return 0; } /* * transfer the SELinux data to a blank set of creds */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) { *secid = cred_sid(c); } /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, secid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { tsec->sid = secid; tsec->create_sid = 0; tsec->keycreate_sid = 0; tsec->sockcreate_sid = 0; } return ret; } /* * set the file creation context in a security record to the same as the * objective context of the specified inode */ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, isec->sid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, NULL); if (ret == 0) tsec->create_sid = isec->sid; return ret; } static int selinux_kernel_module_request(char *kmod_name) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_KMOD; ad.u.kmod_name = kmod_name; return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, &ad); } static int selinux_kernel_module_from_file(struct file *file) { struct common_audit_data ad; struct inode_security_struct *isec; struct file_security_struct *fsec; u32 sid = current_sid(); int rc; /* init_module */ if (file == NULL) return avc_has_perm(sid, sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, NULL); /* finit_module */ ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; fsec = selinux_file(file); if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } isec = inode_security(file_inode(file)); return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, &ad); } static int selinux_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int rc = 0; switch (id) { case READING_MODULE: rc = selinux_kernel_module_from_file(contents ? file : NULL); break; default: break; } return rc; } static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents) { int rc = 0; switch (id) { case LOADING_MODULE: rc = selinux_kernel_module_from_file(NULL); break; default: break; } return rc; } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETPGID, NULL); } static int selinux_task_getpgid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETPGID, NULL); } static int selinux_task_getsid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSESSION, NULL); } static void selinux_current_getsecid_subj(u32 *secid) { *secid = current_sid(); } static void selinux_task_getsecid_obj(struct task_struct *p, u32 *secid) { *secid = task_sid_obj(p); } static int selinux_task_setnice(struct task_struct *p, int nice) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getioprio(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { u32 av = 0; if (!flags) return 0; if (flags & LSM_PRLIMIT_WRITE) av |= PROCESS__SETRLIMIT; if (flags & LSM_PRLIMIT_READ) av |= PROCESS__GETRLIMIT; return avc_has_perm(cred_sid(cred), cred_sid(tcred), SECCLASS_PROCESS, av, NULL); } static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { struct rlimit *old_rlim = p->signal->rlim + resource; /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL); return 0; } static int selinux_task_setscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_movememory(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; u32 perm; if (!sig) perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); if (!cred) secid = current_sid(); else secid = cred_sid(cred); return avc_has_perm(secid, task_sid_obj(p), SECCLASS_PROCESS, perm, NULL); } static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = task_sid_obj(p); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = sid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_userns_create(const struct cred *cred) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_USER_NAMESPACE, USER_NAMESPACE__CREATE, NULL); } /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ihlen, ret = -EINVAL; struct iphdr _iph, *ih; offset = skb_network_offset(skb); ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) goto out; ihlen = ih->ihl * 4; if (ihlen < sizeof(_iph)) goto out; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; ret = 0; if (proto) *proto = ih->protocol; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif default: break; } out: return ret; } #if IS_ENABLED(CONFIG_IPV6) /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv6(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { u8 nexthdr; int ret = -EINVAL, offset; struct ipv6hdr _ipv6h, *ip6; __be16 frag_off; offset = skb_network_offset(skb); ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (ip6 == NULL) goto out; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; ret = 0; nexthdr = ip6->nexthdr; offset += sizeof(_ipv6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) goto out; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif /* includes fragments */ default: break; } out: return ret; } #endif /* IPV6 */ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad, char **_addrp, int src, u8 *proto) { char *addrp; int ret; switch (ad->u.net->family) { case PF_INET: ret = selinux_parse_skb_ipv4(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v4info.saddr : &ad->u.net->v4info.daddr); goto okay; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: ret = selinux_parse_skb_ipv6(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v6info.saddr : &ad->u.net->v6info.daddr); goto okay; #endif /* IPV6 */ default: addrp = NULL; goto okay; } parse_error: pr_warn( "SELinux: failure in selinux_parse_skb()," " unable to parse packet\n"); return ret; okay: if (_addrp) *_addrp = addrp; return 0; } /** * selinux_skb_peerlbl_sid - Determine the peer label of a packet * @skb: the packet * @family: protocol family * @sid: the packet's peer label SID * * Description: * Check the various different forms of network peer labeling and determine * the peer label/SID for the packet; most of the magic actually occurs in * the security server function security_net_peersid_cmp(). The function * returns zero if the value in @sid is valid (although it may be SECSID_NULL) * or -EACCES if @sid is invalid due to inconsistencies with the different * peer labels. * */ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) { int err; u32 xfrm_sid; u32 nlbl_sid; u32 nlbl_type; err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); if (unlikely(err)) return -EACCES; err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid); if (unlikely(err)) { pr_warn( "SELinux: failure in selinux_skb_peerlbl_sid()," " unable to determine packet's peer label\n"); return -EACCES; } return 0; } /** * selinux_conn_sid - Determine the child socket label for a connection * @sk_sid: the parent socket's SID * @skb_sid: the packet's SID * @conn_sid: the resulting connection SID * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) { int err = 0; if (skb_sid != SECSID_NULL) err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid); else *conn_sid = sk_sid; return err; } /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, u16 secclass, u32 *socksid) { if (tsec->sockcreate_sid > SECSID_NULL) { *socksid = tsec->sockcreate_sid; return 0; } return security_transition_sid(tsec->sid, tsec->sid, secclass, NULL, socksid); } static int sock_has_perm(struct sock *sk, u32 perms) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; if (sksec->sid == SECINITSID_KERNEL) return 0; /* * Before POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT, sockets that * inherited the kernel context from early boot used to be skipped * here, so preserve that behavior unless the capability is set. * * By setting the capability the policy signals that it is ready * for this quirk to be fixed. Note that sockets created by a kernel * thread or a usermode helper executed without a transition will * still be skipped in this check regardless of the policycap * setting. */ if (!selinux_policycap_userspace_initial_context() && sksec->sid == SECINITSID_INIT) return 0; ad_net_init_from_sk(&ad, &net, sk); return avc_has_perm(current_sid(), sksec->sid, sksec->sclass, perms, &ad); } static int selinux_socket_create(int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; if (kern) return 0; secclass = socket_type_to_security_class(family, type, protocol); rc = socket_sockcreate_sid(tsec, secclass, &newsid); if (rc) return rc; return avc_has_perm(tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); u32 sid = SECINITSID_KERNEL; int err = 0; if (!kern) { err = socket_sockcreate_sid(tsec, sclass, &sid); if (err) return err; } isec->sclass = sclass; isec->sid = sid; isec->initialized = LABEL_INITIALIZED; if (sock->sk) { sksec = sock->sk->sk_security; sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) sksec->sctp_assoc_state = SCTP_ASSOC_UNSET; err = selinux_netlbl_socket_post_create(sock->sk, family); } return err; } static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { struct sk_security_struct *sksec_a = socka->sk->sk_security; struct sk_security_struct *sksec_b = sockb->sk->sk_security; sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; return 0; } /* Range of port numbers used to automatically bind. Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; u16 family; int err; err = sock_has_perm(sk, SOCKET__BIND); if (err) goto out; /* If PF_INET or PF_INET6, check name_bind permission for the port. */ family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; u16 family_sa; unsigned short snum; u32 sid, node_perm; /* * sctp_bindx(3) calls via selinux_sctp_bind_connect() * that validates multiple binding addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; family_sa = address->sa_family; switch (family_sa) { case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { if (family == PF_INET6) { /* Length check from inet6_bind_sk() */ if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; /* Family check from __inet6_bind() */ goto err_af; } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) goto err_af; family_sa = AF_INET; } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; case AF_INET6: if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; addr6 = (struct sockaddr_in6 *)address; snum = ntohs(addr6->sin6_port); addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: goto err_af; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sport = htons(snum); ad.u.net->family = family_sa; if (snum) { int low, high; inet_get_local_port_range(sock_net(sk), &low, &high); if (inet_port_requires_bind_service(sock_net(sk), snum) || snum < low || snum > high) { err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) goto out; err = avc_has_perm(sksec->sid, sid, sksec->sclass, SOCKET__NAME_BIND, &ad); if (err) goto out; } } switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: node_perm = TCP_SOCKET__NODE_BIND; break; case SECCLASS_UDP_SOCKET: node_perm = UDP_SOCKET__NODE_BIND; break; case SECCLASS_DCCP_SOCKET: node_perm = DCCP_SOCKET__NODE_BIND; break; case SECCLASS_SCTP_SOCKET: node_perm = SCTP_SOCKET__NODE_BIND; break; default: node_perm = RAWIP_SOCKET__NODE_BIND; break; } err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; err = avc_has_perm(sksec->sid, sid, sksec->sclass, node_perm, &ad); if (err) goto out; } out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; int err; err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* connect(AF_UNSPEC) has special handling, as it is a documented * way to disconnect the socket */ if (address->sa_family == AF_UNSPEC) return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission * for the port. */ if (sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_DCCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) { struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; unsigned short snum; u32 sid, perm; /* sctp_connectx(3) calls via selinux_sctp_bind_connect() * that validates multiple connect addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; snum = ntohs(addr4->sin_port); break; case AF_INET6: addr6 = (struct sockaddr_in6 *)address; if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; snum = ntohs(addr6->sin6_port); break; default: /* Note that SCTP services expect -EINVAL, whereas * others expect -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; else return -EAFNOSUPPORT; } err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) return err; switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: perm = TCP_SOCKET__NAME_CONNECT; break; case SECCLASS_DCCP_SOCKET: perm = DCCP_SOCKET__NAME_CONNECT; break; case SECCLASS_SCTP_SOCKET: perm = SCTP_SOCKET__NAME_CONNECT; break; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); ad.u.net->family = address->sa_family; err = avc_has_perm(sksec->sid, sid, sksec->sclass, perm, &ad); if (err) return err; } return 0; } /* Supports connect(2), see comments in selinux_socket_connect_helper() */ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { int err; struct sock *sk = sock->sk; err = selinux_socket_connect_helper(sock, address, addrlen); if (err) return err; return selinux_netlbl_socket_connect(sk, address); } static int selinux_socket_listen(struct socket *sock, int backlog) { return sock_has_perm(sock->sk, SOCKET__LISTEN); } static int selinux_socket_accept(struct socket *sock, struct socket *newsock) { int err; struct inode_security_struct *isec; struct inode_security_struct *newisec; u16 sclass; u32 sid; err = sock_has_perm(sock->sk, SOCKET__ACCEPT); if (err) return err; isec = inode_security_novalidate(SOCK_INODE(sock)); spin_lock(&isec->lock); sclass = isec->sclass; sid = isec->sid; spin_unlock(&isec->lock); newisec = inode_security_novalidate(SOCK_INODE(newsock)); newisec->sclass = sclass; newisec->sid = sid; newisec->initialized = LABEL_INITIALIZED; return 0; } static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return sock_has_perm(sock->sk, SOCKET__WRITE); } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return sock_has_perm(sock->sk, SOCKET__READ); } static int selinux_socket_getsockname(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_getpeername(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_setsockopt(struct socket *sock, int level, int optname) { int err; err = sock_has_perm(sock->sk, SOCKET__SETOPT); if (err) return err; return selinux_netlbl_socket_setsockopt(sock, level, optname); } static int selinux_socket_getsockopt(struct socket *sock, int level, int optname) { return sock_has_perm(sock->sk, SOCKET__GETOPT); } static int selinux_socket_shutdown(struct socket *sock, int how) { return sock_has_perm(sock->sk, SOCKET__SHUTDOWN); } static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { struct sk_security_struct *sksec_sock = sock->sk_security; struct sk_security_struct *sksec_other = other->sk_security; struct sk_security_struct *sksec_new = newsk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; int err; ad_net_init_from_sk(&ad, &net, other); err = avc_has_perm(sksec_sock->sid, sksec_other->sid, sksec_other->sclass, UNIX_STREAM_SOCKET__CONNECTTO, &ad); if (err) return err; /* server child socket */ sksec_new->peer_sid = sksec_sock->sid; err = security_sid_mls_copy(sksec_other->sid, sksec_sock->sid, &sksec_new->sid); if (err) return err; /* connecting socket */ sksec_sock->peer_sid = sksec_new->sid; return 0; } static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { struct sk_security_struct *ssec = sock->sk->sk_security; struct sk_security_struct *osec = other->sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; ad_net_init_from_sk(&ad, &net, other->sk); return avc_has_perm(ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO, &ad); } static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex, char *addrp, u16 family, u32 peer_sid, struct common_audit_data *ad) { int err; u32 if_sid; u32 node_sid; err = sel_netif_sid(ns, ifindex, &if_sid); if (err) return err; err = avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__INGRESS, ad); if (err) return err; err = sel_netnode_sid(addrp, family, &node_sid); if (err) return err; return avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__RECVFROM, ad); } static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; struct sk_security_struct *sksec = sk->sk_security; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (selinux_secmark_enabled()) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad); if (err) return err; err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad); return err; } static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err, peerlbl_active, secmark_active; struct sk_security_struct *sksec = sk->sk_security; u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; if (family != PF_INET && family != PF_INET6) return 0; /* Handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_sock_rcv_skb_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_sock_rcv_skb_compat(sk, skb, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return 0; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (peerlbl_active) { u32 peer_sid; err = selinux_skb_peerlbl_sid(skb, family, &peer_sid); if (err) return err; err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } } if (secmark_active) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } return err; } static int selinux_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { int err = 0; char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = sock->sk->sk_security; u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) peer_sid = sksec->peer_sid; if (peer_sid == SECSID_NULL) return -ENOPROTOOPT; err = security_sid_to_context(peer_sid, &scontext, &scontext_len); if (err) return err; if (scontext_len > len) { err = -ERANGE; goto out_len; } if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; out_len: if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; } static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { u32 peer_secid = SECSID_NULL; u16 family; if (skb && skb->protocol == htons(ETH_P_IP)) family = PF_INET; else if (skb && skb->protocol == htons(ETH_P_IPV6)) family = PF_INET6; else if (sock) family = sock->sk->sk_family; else { *secid = SECSID_NULL; return -EINVAL; } if (sock && family == PF_UNIX) { struct inode_security_struct *isec; isec = inode_security_novalidate(SOCK_INODE(sock)); peer_secid = isec->sid; } else if (skb) selinux_skb_peerlbl_sid(skb, family, &peer_secid); *secid = peer_secid; if (peer_secid == SECSID_NULL) return -ENOPROTOOPT; return 0; } static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *sksec; sksec = kzalloc(sizeof(*sksec), priority); if (!sksec) return -ENOMEM; sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); sk->sk_security = sksec; return 0; } static void selinux_sk_free_security(struct sock *sk) { struct sk_security_struct *sksec = sk->sk_security; sk->sk_security = NULL; selinux_netlbl_sk_security_free(sksec); kfree(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; newsksec->sclass = sksec->sclass; selinux_netlbl_sk_security_reset(newsksec); } static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { const struct sk_security_struct *sksec = sk->sk_security; *secid = sksec->sid; } } static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); struct sk_security_struct *sksec = sk->sk_security; if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; } /* * Determines peer_secid for the asoc and updates socket's peer label * if it's the first association on the socket. */ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, struct sk_buff *skb) { struct sock *sk = asoc->base.sk; u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; int err; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; if (selinux_peerlbl_enabled()) { asoc->peer_secid = SECSID_NULL; /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ err = selinux_skb_peerlbl_sid(skb, family, &asoc->peer_secid); if (err) return err; if (asoc->peer_secid == SECSID_NULL) asoc->peer_secid = SECINITSID_UNLABELED; } else { asoc->peer_secid = SECINITSID_UNLABELED; } if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) { sksec->sctp_assoc_state = SCTP_ASSOC_SET; /* Here as first association on socket. As the peer SID * was allowed by peer recv (and the netif/node checks), * then it is approved by policy and used as the primary * peer SID for getpeercon(3). */ sksec->peer_sid = asoc->peer_secid; } else if (sksec->peer_sid != asoc->peer_secid) { /* Other association peer SIDs are checked to enforce * consistency among the peer SIDs. */ ad_net_init_from_sk(&ad, &net, asoc->base.sk); err = avc_has_perm(sksec->peer_sid, asoc->peer_secid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); if (err) return err; } return 0; } /* Called whenever SCTP receives an INIT or COOKIE ECHO chunk. This * happens on an incoming connect(2), sctp_connectx(3) or * sctp_sendmsg(3) (with no association already present). */ static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = asoc->base.sk->sk_security; u32 conn_sid; int err; if (!selinux_policycap_extsockclass()) return 0; err = selinux_sctp_process_new_assoc(asoc, skb); if (err) return err; /* Compute the MLS component for the connection and store * the information in asoc. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. */ err = selinux_conn_sid(sksec->sid, asoc->peer_secid, &conn_sid); if (err) return err; asoc->secid = conn_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ return selinux_netlbl_sctp_assoc_request(asoc, skb); } /* Called when SCTP receives a COOKIE ACK chunk as the final * response to an association request (initited by us). */ static int selinux_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = asoc->base.sk->sk_security; if (!selinux_policycap_extsockclass()) return 0; /* Inherit secid from the parent socket - this will be picked up * by selinux_sctp_sk_clone() if the association gets peeled off * into a new socket. */ asoc->secid = sksec->sid; return selinux_sctp_process_new_assoc(asoc, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting * based on their @optname. */ static int selinux_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { if (walk_size + sizeof(sa_family_t) > addrlen) return -EINVAL; addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; case AF_INET6: len = sizeof(struct sockaddr_in6); break; default: return -EINVAL; } if (walk_size + len > addrlen) return -EINVAL; err = -EINVAL; switch (optname) { /* Bind checks */ case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: err = selinux_socket_bind(sock, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: err = selinux_socket_connect_helper(sock, addr, len); if (err) return err; /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new * primary address is selected. * Note that an SCTP connect(2) call happens before * the SCTP protocol layer and is handled via * selinux_socket_connect(). */ err = selinux_netlbl_socket_connect_locked(sk, addr); break; } if (err) return err; addr_buf += len; walk_size += len; } return 0; } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. */ if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); newsksec->sid = asoc->secid; newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { struct sk_security_struct *ssksec = ssk->sk_security; struct sk_security_struct *sksec = sk->sk_security; ssksec->sclass = sksec->sclass; ssksec->sid = sksec->sid; /* replace the existing subflow label deleting the existing one * and re-recreating a new label using the updated context */ selinux_netlbl_sk_security_free(ssksec); return selinux_netlbl_socket_post_create(ssk, ssk->sk_family); } static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct sk_security_struct *sksec = sk->sk_security; int err; u16 family = req->rsk_ops->family; u32 connsid; u32 peersid; err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; err = selinux_conn_sid(sksec->sid, peersid, &connsid); if (err) return err; req->secid = connsid; req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; /* NOTE: Ideally, we should also get the isec->sid for the new socket in sync, but we don't have the isec available yet. So we will wait until sock_graft to do it, by which time it will have been created and available. */ /* We don't need to take any sort of lock here as we are the only * thread with access to newsksec */ selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family); } static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } static int selinux_secmark_relabel_packet(u32 sid) { return avc_has_perm(current_sid(), sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } static void selinux_secmark_refcount_inc(void) { atomic_inc(&selinux_secmark_refcount); } static void selinux_secmark_refcount_dec(void) { atomic_dec(&selinux_secmark_refcount); } static void selinux_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { flic->flowic_secid = req->secid; } static int selinux_tun_dev_alloc_security(void **security) { struct tun_security_struct *tunsec; tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL); if (!tunsec) return -ENOMEM; tunsec->sid = current_sid(); *security = tunsec; return 0; } static void selinux_tun_dev_free_security(void *security) { kfree(security); } static int selinux_tun_dev_create(void) { u32 sid = current_sid(); /* we aren't taking into account the "sockcreate" SID since the socket * that is being created here is not a socket in the traditional sense, * instead it is a private sock, accessible only to the kernel, and * representing a wide range of network traffic spanning multiple * connections unlike traditional sockets - check the TUN driver to * get a better understanding of why this socket is special */ return avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE, NULL); } static int selinux_tun_dev_attach_queue(void *security) { struct tun_security_struct *tunsec = security; return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); } static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = security; struct sk_security_struct *sksec = sk->sk_security; /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply * labeling without the support of the TUN user the resulting labeled * traffic from the other end of the connection would almost certainly * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; return 0; } static int selinux_tun_dev_open(void *security) { struct tun_security_struct *tunsec = security; u32 sid = current_sid(); int err; err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; err = avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELTO, NULL); if (err) return err; tunsec->sid = sid; return 0; } #ifdef CONFIG_NETFILTER static unsigned int selinux_ip_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int ifindex; u16 family; char *addrp; u32 peer_sid; struct common_audit_data ad; struct lsm_network_audit net; int secmark_active, peerlbl_active; if (!selinux_policycap_netpeer()) return NF_ACCEPT; secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; family = state->pf; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0) return NF_DROP; ifindex = state->in->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0) return NF_DROP; if (peerlbl_active) { int err; err = selinux_inet_sys_rcv_skb(state->net, ifindex, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 1); return NF_DROP; } } if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; if (netlbl_enabled()) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH * protection */ if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; u32 sid; if (!netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ sk = skb->sk; if (sk) { struct sk_security_struct *sksec; if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and * not the parent socket. unfortunately, we can't * lookup the request_sock yet as it isn't queued on * the parent socket until after the SYN-ACK is sent. * the "solution" is to simply pass the packet as-is * as any IP option based labeling should be copied * from the initial connection request (in the IP * layer). it is far from ideal, but until we get a * security label in the packet itself this is the * best we can do. */ return NF_ACCEPT; /* standard practice, label using the parent socket */ sksec = sk->sk_security; sid = sksec->sid; } else sid = SECINITSID_KERNEL; if (selinux_netlbl_skbuff_setsid(skb, state->pf, sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; struct sk_security_struct *sksec; struct common_audit_data ad; struct lsm_network_audit net; u8 proto = 0; sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; sksec = sk->sk_security; ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf); if (selinux_parse_skb(skb, &ad, NULL, 0, &proto)) return NF_DROP; if (selinux_secmark_enabled()) if (avc_has_perm(sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) return NF_DROP_ERR(-ECONNREFUSED); return NF_ACCEPT; } static unsigned int selinux_ip_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { u16 family; u32 secmark_perm; u32 peer_sid; int ifindex; struct sock *sk; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; int secmark_active, peerlbl_active; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_ip_postroute_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_ip_postroute_compat(skb, state); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; sk = skb_to_full_sk(skb); #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. * NOTE: if this is a local socket (skb->sk != NULL) that is in the * TCP listening state we cannot wait until the XFRM processing * is done as we will miss out on the SA label if we do; * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && !(sk && sk_listener(sk))) return NF_ACCEPT; #endif family = state->pf; if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet * to determine which and if the packet is being forwarded * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) return NF_DROP; } else { secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned * to the connection/request_sock but unfortunately we can't * query the request_sock as it isn't queued on the parent * socket until after the SYN-ACK packet is sent; the only * viable choice is to regenerate the label like we do in * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; struct sk_security_struct *sksec; sksec = sk->sk_security; if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL * and the packet has been through at least one XFRM * transformation then we must be dealing with the "final" * form of labeled IPsec packet; since we've already applied * all of our access controls on this packet we can safely * pass the packet. */ if (skb_sid == SECSID_NULL) { switch (family) { case PF_INET: if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; case PF_INET6: if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; default: return NF_DROP_ERR(-ECONNREFUSED); } } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; } else { /* Locally generated packet, fetch the security label from the * associated socket. */ struct sk_security_struct *sksec = sk->sk_security; peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } ifindex = state->out->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL)) return NF_DROP; if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, secmark_perm, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (peerlbl_active) { u32 if_sid; u32 node_sid; if (sel_netif_sid(state->net, ifindex, &if_sid)) return NF_DROP; if (avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__EGRESS, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (sel_netnode_sid(addrp, family, &node_sid)) return NF_DROP; if (avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__SENDTO, &ad)) return NF_DROP_ERR(-ECONNREFUSED); } return NF_ACCEPT; } #endif /* CONFIG_NETFILTER */ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { int rc = 0; unsigned int msg_len; unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = sk->sk_security; u16 sclass = sksec->sclass; u32 perm; while (data_len >= nlmsg_total_size(0)) { nlh = (struct nlmsghdr *)data; /* NOTE: the nlmsg_len field isn't reliably set by some netlink * users which means we can't reject skb's with bogus * length fields; our solution is to follow what * netlink_rcv_skb() does and simply skip processing at * messages with length fields that are clearly junk */ if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) return 0; rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); if (rc == 0) { rc = sock_has_perm(sk, perm); if (rc) return rc; } else if (rc == -EINVAL) { /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" " message: protocol=%hu nlmsg_type=%hu sclass=%s" " pid=%d comm=%s\n", sk->sk_protocol, nlh->nlmsg_type, secclass_map[sclass - 1].name, task_pid_nr(current), current->comm); if (enforcing_enabled() && !security_get_allow_unknown()) return rc; rc = 0; } else if (rc == -ENOENT) { /* -ENOENT is a missing socket/class mapping, ignore */ rc = 0; } else { return rc; } /* move to the next message after applying netlink padding */ msg_len = NLMSG_ALIGN(nlh->nlmsg_len); if (msg_len >= data_len) return 0; data_len -= msg_len; data += msg_len; } return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { isec->sclass = sclass; isec->sid = current_sid(); } static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(ipc_perms); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = ipc_perms->key; return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; return 0; } /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case MSG_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: perms = MSGQ__GETATTR | MSGQ__ASSOCIATE; break; case IPC_SET: perms = MSGQ__SETATTR; break; case IPC_RMID: perms = MSGQ__DESTROY; break; default: return 0; } return ipc_has_perm(msq, perms); } static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); /* * First time through, need to assign label to the message */ if (msec->sid == SECINITSID_UNLABELED) { /* * Compute new sid based on current process and * message queue this message will be stored in */ rc = security_transition_sid(sid, isec->sid, SECCLASS_MSG, NULL, &msec->sid); if (rc) return rc; } ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; /* Can this process write to the queue? */ rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ rc = avc_has_perm(msec->sid, isec->sid, SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); return rc; } static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = task_sid_obj(target); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } /* Note, at this point, shp is locked down */ static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case SHM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case SHM_STAT: case SHM_STAT_ANY: perms = SHM__GETATTR | SHM__ASSOCIATE; break; case IPC_SET: perms = SHM__SETATTR; break; case SHM_LOCK: case SHM_UNLOCK: perms = SHM__LOCK; break; case IPC_RMID: perms = SHM__DESTROY; break; default: return 0; } return ipc_has_perm(shp, perms); } static int selinux_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { u32 perms; if (shmflg & SHM_RDONLY) perms = SHM__READ; else perms = SHM__READ | SHM__WRITE; return ipc_has_perm(shp, perms); } /* Semaphore security operations */ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } /* Note, at this point, sma is locked down */ static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd) { int err; u32 perms; switch (cmd) { case IPC_INFO: case SEM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case GETPID: case GETNCNT: case GETZCNT: perms = SEM__GETATTR; break; case GETVAL: case GETALL: perms = SEM__READ; break; case SETVAL: case SETALL: perms = SEM__WRITE; break; case IPC_RMID: perms = SEM__DESTROY; break; case IPC_SET: perms = SEM__SETATTR; break; case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: perms = SEM__GETATTR | SEM__ASSOCIATE; break; default: return 0; } err = ipc_has_perm(sma, perms); return err; } static int selinux_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { u32 perms; if (alter) perms = SEM__READ | SEM__WRITE; else perms = SEM__READ; return ipc_has_perm(sma, perms); } static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { u32 av = 0; av = 0; if (flag & S_IRUGO) av |= IPC__UNIX_READ; if (flag & S_IWUGO) av |= IPC__UNIX_WRITE; if (av == 0) return 0; return ipc_has_perm(ipcp, av); } static void selinux_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { struct ipc_security_struct *isec = selinux_ipc(ipcp); *secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) { if (inode) inode_doinit_with_dentry(inode, dentry); } static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p, char **value) { const struct task_security_struct *tsec; int error; u32 sid; u32 len; rcu_read_lock(); tsec = selinux_cred(__task_cred(p)); if (p != current) { error = avc_has_perm(current_sid(), tsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto err_unlock; } switch (attr) { case LSM_ATTR_CURRENT: sid = tsec->sid; break; case LSM_ATTR_PREV: sid = tsec->osid; break; case LSM_ATTR_EXEC: sid = tsec->exec_sid; break; case LSM_ATTR_FSCREATE: sid = tsec->create_sid; break; case LSM_ATTR_KEYCREATE: sid = tsec->keycreate_sid; break; case LSM_ATTR_SOCKCREATE: sid = tsec->sockcreate_sid; break; default: error = -EOPNOTSUPP; goto err_unlock; } rcu_read_unlock(); if (sid == SECSID_NULL) { *value = NULL; return 0; } error = security_sid_to_context(sid, value, &len); if (error) return error; return len; err_unlock: rcu_read_unlock(); return error; } static int selinux_lsm_setattr(u64 attr, void *value, size_t size) { struct task_security_struct *tsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; char *str = value; /* * Basic control over ability to set these attributes at all. */ switch (attr) { case LSM_ATTR_EXEC: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETEXEC, NULL); break; case LSM_ATTR_FSCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETFSCREATE, NULL); break; case LSM_ATTR_KEYCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETKEYCREATE, NULL); break; case LSM_ATTR_SOCKCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, NULL); break; case LSM_ATTR_CURRENT: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETCURRENT, NULL); break; default: error = -EOPNOTSUPP; break; } if (error) return error; /* Obtain a SID for the context, if one was specified. */ if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; } error = security_context_to_sid(value, size, &sid, GFP_KERNEL); if (error == -EINVAL && attr == LSM_ATTR_FSCREATE) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, * otherwise the context contains a nul and * we should audit that */ if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return error; audit_log_format(ab, "op=fscreate invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return error; } error = security_context_to_sid_force(value, size, &sid); } if (error) return error; } new = prepare_creds(); if (!new) return -ENOMEM; /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ tsec = selinux_cred(new); if (attr == LSM_ATTR_EXEC) { tsec->exec_sid = sid; } else if (attr == LSM_ATTR_FSCREATE) { tsec->create_sid = sid; } else if (attr == LSM_ATTR_KEYCREATE) { if (sid) { error = avc_has_perm(mysid, sid, SECCLASS_KEY, KEY__CREATE, NULL); if (error) goto abort_change; } tsec->keycreate_sid = sid; } else if (attr == LSM_ATTR_SOCKCREATE) { tsec->sockcreate_sid = sid; } else if (attr == LSM_ATTR_CURRENT) { error = -EINVAL; if (sid == 0) goto abort_change; if (!current_is_single_threaded()) { error = security_bounded_transition(tsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ error = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = ptrace_parent_sid(); if (ptsid != 0) { error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (error) goto abort_change; } tsec->sid = sid; } else { error = -EINVAL; goto abort_change; } commit_creds(new); return size; abort_change: abort_creds(new); return error; } /** * selinux_getselfattr - Get SELinux current task attributes * @attr: the requested attribute * @ctx: buffer to receive the result * @size: buffer size (input), buffer size used (output) * @flags: unused * * Fill the passed user space @ctx with the details of the requested * attribute. * * Returns the number of attributes on success, an error code otherwise. * There will only ever be one attribute. */ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) { int rc; char *val = NULL; int val_len; val_len = selinux_lsm_getattr(attr, current, &val); if (val_len < 0) return val_len; rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0); kfree(val); return (!rc ? 1 : rc); } static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) { int rc; rc = selinux_lsm_setattr(attr, ctx->ctx, ctx->ctx_len); if (rc > 0) return 0; return rc; } static int selinux_getprocattr(struct task_struct *p, const char *name, char **value) { unsigned int attr = lsm_name_to_attr(name); int rc; if (attr) { rc = selinux_lsm_getattr(attr, p, value); if (rc != -EOPNOTSUPP) return rc; } return -EINVAL; } static int selinux_setprocattr(const char *name, void *value, size_t size) { int attr = lsm_name_to_attr(name); if (attr) return selinux_lsm_setattr(attr, value, size); return -EINVAL; } static int selinux_ismaclabel(const char *name) { return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return security_sid_to_context(secid, secdata, seclen); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) { kfree(secdata); } static void selinux_inode_invalidate_secctx(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); spin_lock(&isec->lock); isec->initialized = LABEL_INVALID; spin_unlock(&isec->lock); } /* * called with inode->i_mutex locked */ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, ctxlen, 0); /* Do not return error when suppressing label (SBLABEL_MNT not set). */ return rc == -EOPNOTSUPP ? 0 : rc; } /* * called with inode->i_mutex locked */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; return 0; } #ifdef CONFIG_KEYS static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; struct key_security_struct *ksec; ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); if (!ksec) return -ENOMEM; tsec = selinux_cred(cred); if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; k->security = ksec; return 0; } static void selinux_key_free(struct key *k) { struct key_security_struct *ksec = k->security; k->security = NULL; kfree(ksec); } static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; struct key_security_struct *ksec; u32 perm, sid; switch (need_perm) { case KEY_NEED_VIEW: perm = KEY__VIEW; break; case KEY_NEED_READ: perm = KEY__READ; break; case KEY_NEED_WRITE: perm = KEY__WRITE; break; case KEY_NEED_SEARCH: perm = KEY__SEARCH; break; case KEY_NEED_LINK: perm = KEY__LINK; break; case KEY_NEED_SETATTR: perm = KEY__SETATTR; break; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: return 0; default: WARN_ON(1); return -EPERM; } sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); ksec = key->security; return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { struct key_security_struct *ksec = key->security; char *context = NULL; unsigned len; int rc; rc = security_sid_to_context(ksec->sid, &context, &len); if (!rc) rc = len; *_buffer = context; return rc; } #ifdef CONFIG_KEY_NOTIFICATIONS static int selinux_watch_key(struct key *key) { struct key_security_struct *ksec = key->security; u32 sid = current_sid(); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL); } #endif #endif #ifdef CONFIG_SECURITY_INFINIBAND static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibpkey_audit ibpkey; err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBPKEY; ibpkey.subnet_prefix = subnet_prefix; ibpkey.pkey = pkey_val; ad.u.ibpkey = &ibpkey; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_PKEY, INFINIBAND_PKEY__ACCESS, &ad); } static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, u8 port_num) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibendport_audit ibendport; err = security_ib_endport_sid(dev_name, port_num, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; ibendport.dev_name = dev_name; ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_ENDPORT, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } static int selinux_ib_alloc_security(void **ib_sec) { struct ib_security_struct *sec; sec = kzalloc(sizeof(*sec), GFP_KERNEL); if (!sec) return -ENOMEM; sec->sid = current_sid(); *ib_sec = sec; return 0; } static void selinux_ib_free_security(void *ib_sec) { kfree(ib_sec); } #endif #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, unsigned int size) { u32 sid = current_sid(); int ret; switch (cmd) { case BPF_MAP_CREATE: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); break; case BPF_PROG_LOAD: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); break; default: ret = 0; break; } return ret; } static u32 bpf_map_fmode_to_av(fmode_t fmode) { u32 av = 0; if (fmode & FMODE_READ) av |= BPF__MAP_READ; if (fmode & FMODE_WRITE) av |= BPF__MAP_WRITE; return av; } /* This function will check the file pass through unix socket or binder to see * if it is a bpf related object. And apply corresponding checks on the bpf * object based on the type. The bpf maps and programs, not like other files and * socket, are using a shared anonymous inode inside the kernel as their inode. * So checking that inode cannot identify if the process have privilege to * access the bpf object and that's why we have to add this additional check in * selinux_file_receive and selinux_binder_transfer_files. */ static int bpf_fd_pass(const struct file *file, u32 sid) { struct bpf_security_struct *bpfsec; struct bpf_prog *prog; struct bpf_map *map; int ret; if (file->f_op == &bpf_map_fops) { map = file->private_data; bpfsec = map->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(file->f_mode), NULL); if (ret) return ret; } else if (file->f_op == &bpf_prog_fops) { prog = file->private_data; bpfsec = prog->aux->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); if (ret) return ret; } return 0; } static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = map->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(fmode), NULL); } static int selinux_bpf_prog(struct bpf_prog *prog) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = prog->aux->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); } static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); map->security = bpfsec; return 0; } static void selinux_bpf_map_free(struct bpf_map *map) { struct bpf_security_struct *bpfsec = map->security; map->security = NULL; kfree(bpfsec); } static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); prog->aux->security = bpfsec; return 0; } static void selinux_bpf_prog_free(struct bpf_prog *prog) { struct bpf_security_struct *bpfsec = prog->aux->security; prog->aux->security = NULL; kfree(bpfsec); } static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, struct path *path) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); token->security = bpfsec; return 0; } static void selinux_bpf_token_free(struct bpf_token *token) { struct bpf_security_struct *bpfsec = token->security; token->security = NULL; kfree(bpfsec); } #endif struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, }; #ifdef CONFIG_PERF_EVENTS static int selinux_perf_event_open(struct perf_event_attr *attr, int type) { u32 requested, sid = current_sid(); if (type == PERF_SECURITY_OPEN) requested = PERF_EVENT__OPEN; else if (type == PERF_SECURITY_CPU) requested = PERF_EVENT__CPU; else if (type == PERF_SECURITY_KERNEL) requested = PERF_EVENT__KERNEL; else if (type == PERF_SECURITY_TRACEPOINT) requested = PERF_EVENT__TRACEPOINT; else return -EINVAL; return avc_has_perm(sid, sid, SECCLASS_PERF_EVENT, requested, NULL); } static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; perfsec = kzalloc(sizeof(*perfsec), GFP_KERNEL); if (!perfsec) return -ENOMEM; perfsec->sid = current_sid(); event->security = perfsec; return 0; } static void selinux_perf_event_free(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; event->security = NULL; kfree(perfsec); } static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); } static int selinux_perf_event_write(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); } #endif #ifdef CONFIG_IO_URING /** * selinux_uring_override_creds - check the requested cred override * @new: the target creds * * Check to see if the current task is allowed to override it's credentials * to service an io_uring operation. */ static int selinux_uring_override_creds(const struct cred *new) { return avc_has_perm(current_sid(), cred_sid(new), SECCLASS_IO_URING, IO_URING__OVERRIDE_CREDS, NULL); } /** * selinux_uring_sqpoll - check if a io_uring polling thread can be created * * Check to see if the current task is allowed to create a new io_uring * kernel polling thread. */ static int selinux_uring_sqpoll(void) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_IO_URING, IO_URING__SQPOLL, NULL); } /** * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed * @ioucmd: the io_uring command structure * * Check to see if the current domain is allowed to execute an * IORING_OP_URING_CMD against the device/file specified in @ioucmd. * */ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) { struct file *file = ioucmd->file; struct inode *inode = file_inode(file); struct inode_security_struct *isec = selinux_inode(inode); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return avc_has_perm(current_sid(), isec->sid, SECCLASS_IO_URING, IO_URING__CMD, &ad); } #endif /* CONFIG_IO_URING */ static const struct lsm_id selinux_lsmid = { .name = "selinux", .id = LSM_ID_SELINUX, }; /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, * 2. hooks that both access structures allocated by other hooks, and allocate * structures that can be later accessed by other hooks (mostly "cloning" * hooks), * 3. hooks that only allocate structures that can be later accessed by other * hooks ("allocating" hooks). * * Please follow block comment delimiters in the list to keep this order. */ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder), LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file), LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme), LSM_HOOK_INIT(capget, selinux_capget), LSM_HOOK_INIT(capset, selinux_capset), LSM_HOOK_INIT(capable, selinux_capable), LSM_HOOK_INIT(quotactl, selinux_quotactl), LSM_HOOK_INIT(quota_on, selinux_quota_on), LSM_HOOK_INIT(syslog, selinux_syslog), LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory), LSM_HOOK_INIT(netlink_send, selinux_netlink_send), LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds), LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts), LSM_HOOK_INIT(sb_mnt_opts_compat, selinux_sb_mnt_opts_compat), LSM_HOOK_INIT(sb_remount, selinux_sb_remount), LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount), LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options), LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs), LSM_HOOK_INIT(sb_mount, selinux_mount), LSM_HOOK_INIT(sb_umount, selinux_umount), LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts), LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts), LSM_HOOK_INIT(move_mount, selinux_move_mount), LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security), LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as), LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security), LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security), LSM_HOOK_INIT(inode_init_security_anon, selinux_inode_init_security_anon), LSM_HOOK_INIT(inode_create, selinux_inode_create), LSM_HOOK_INIT(inode_link, selinux_inode_link), LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink), LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink), LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir), LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir), LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod), LSM_HOOK_INIT(inode_rename, selinux_inode_rename), LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink), LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link), LSM_HOOK_INIT(inode_permission, selinux_inode_permission), LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr), LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr), LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr), LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr), LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr), LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr), LSM_HOOK_INIT(inode_set_acl, selinux_inode_set_acl), LSM_HOOK_INIT(inode_get_acl, selinux_inode_get_acl), LSM_HOOK_INIT(inode_remove_acl, selinux_inode_remove_acl), LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), LSM_HOOK_INIT(inode_getsecid, selinux_inode_getsecid), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security), LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), LSM_HOOK_INIT(file_lock, selinux_file_lock), LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl), LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner), LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask), LSM_HOOK_INIT(file_receive, selinux_file_receive), LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data), LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), LSM_HOOK_INIT(current_getsecid_subj, selinux_current_getsecid_subj), LSM_HOOK_INIT(task_getsecid_obj, selinux_task_getsecid_obj), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit), LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit), LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler), LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler), LSM_HOOK_INIT(task_movememory, selinux_task_movememory), LSM_HOOK_INIT(task_kill, selinux_task_kill), LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode), LSM_HOOK_INIT(userns_create, selinux_userns_create), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate), LSM_HOOK_INIT(getselfattr, selinux_getselfattr), LSM_HOOK_INIT(setselfattr, selinux_setselfattr), LSM_HOOK_INIT(getprocattr, selinux_getprocattr), LSM_HOOK_INIT(setprocattr, selinux_setprocattr), LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel), LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid), LSM_HOOK_INIT(release_secctx, selinux_release_secctx), LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx), LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx), LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send), LSM_HOOK_INIT(socket_create, selinux_socket_create), LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create), LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair), LSM_HOOK_INIT(socket_bind, selinux_socket_bind), LSM_HOOK_INIT(socket_connect, selinux_socket_connect), LSM_HOOK_INIT(socket_listen, selinux_socket_listen), LSM_HOOK_INIT(socket_accept, selinux_socket_accept), LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown), LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb), LSM_HOOK_INIT(socket_getpeersec_stream, selinux_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security), LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security), LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid), LSM_HOOK_INIT(sock_graft, selinux_sock_graft), LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established), LSM_HOOK_INIT(mptcp_add_subflow, selinux_mptcp_add_subflow), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet), LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), LSM_HOOK_INIT(tun_dev_free_security, selinux_tun_dev_free_security), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), LSM_HOOK_INIT(ib_free_security, selinux_ib_free_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete), LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free), LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete), LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup), LSM_HOOK_INIT(xfrm_state_pol_flow_match, selinux_xfrm_state_pol_flow_match), LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_free, selinux_key_free), LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS LSM_HOOK_INIT(watch_key, selinux_watch_key), #endif #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), LSM_HOOK_INIT(perf_event_free, selinux_perf_event_free), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll), LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd), #endif /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ LSM_HOOK_INIT(fs_context_submount, selinux_fs_context_submount), LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif /* * PUT "ALLOCATING" HOOKS HERE */ LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc), LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc), LSM_HOOK_INIT(xfrm_state_alloc_acquire, selinux_xfrm_state_alloc_acquire), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, selinux_key_alloc), #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), #endif }; static __init int selinux_init(void) { pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(selinux_enforcing_boot); selinux_avc_init(); mutex_init(&selinux_state.status_lock); mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); if (!default_noexec) pr_notice("SELinux: virtual memory is executable by default\n"); avc_init(); avtab_cache_init(); ebitmap_cache_init(); hashtab_cache_init(); security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), &selinux_lsmid); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC LSM notifier callback\n"); if (selinux_enforcing_boot) pr_debug("SELinux: Starting in enforcing mode\n"); else pr_debug("SELinux: Starting in permissive mode\n"); fs_validate_description("selinux", selinux_fs_parameters); return 0; } static void delayed_superblock_init(struct super_block *sb, void *unused) { selinux_set_mnt_opts(sb, NULL, 0, NULL); } void selinux_complete_init(void) { pr_debug("SELinux: Completing initialization.\n"); /* Set up any superblocks initialized prior to the policy load. */ pr_debug("SELinux: Setting up existing superblocks.\n"); iterate_supers(delayed_superblock_init, NULL); } /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled_boot, .blobs = &selinux_blob_sizes, .init = selinux_init, }; #if defined(CONFIG_NETFILTER) static const struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif /* IPV6 */ }; static int __net_init selinux_nf_register(struct net *net) { return nf_register_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static void __net_exit selinux_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, }; static int __init selinux_nf_ip_init(void) { int err; if (!selinux_enabled_boot) return 0; pr_debug("SELinux: Registering netfilter hooks\n"); err = register_pernet_subsys(&selinux_net_ops); if (err) panic("SELinux: register_pernet_subsys: error %d\n", err); return 0; } __initcall(selinux_nf_ip_init); #endif /* CONFIG_NETFILTER */ |
| 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/atomic.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2002 Deep Blue Solutions Ltd. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_ATOMIC_LL_SC_H #define __ASM_ATOMIC_LL_SC_H #include <linux/stringify.h> #ifndef CONFIG_CC_HAS_K_CONSTRAINT #define K #endif /* * AArch64 UP and SMP safe atomic ops. We use load exclusive and * store exclusive to ensure that these are atomic. We may loop * to ensure that the update happens. */ #define ATOMIC_OP(op, asm_op, constraint) \ static __always_inline void \ __ll_sc_atomic_##op(int i, atomic_t *v) \ { \ unsigned long tmp; \ int result; \ \ asm volatile("// atomic_" #op "\n" \ " prfm pstl1strm, %2\n" \ "1: ldxr %w0, %2\n" \ " " #asm_op " %w0, %w0, %w3\n" \ " stxr %w1, %w0, %2\n" \ " cbnz %w1, 1b\n" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } #define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ static __always_inline int \ __ll_sc_atomic_##op##_return##name(int i, atomic_t *v) \ { \ unsigned long tmp; \ int result; \ \ asm volatile("// atomic_" #op "_return" #name "\n" \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr %w0, %2\n" \ " " #asm_op " %w0, %w0, %w3\n" \ " st" #rel "xr %w1, %w0, %2\n" \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ } #define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ static __always_inline int \ __ll_sc_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ unsigned long tmp; \ int val, result; \ \ asm volatile("// atomic_fetch_" #op #name "\n" \ " prfm pstl1strm, %3\n" \ "1: ld" #acq "xr %w0, %3\n" \ " " #asm_op " %w1, %w0, %w4\n" \ " st" #rel "xr %w2, %w1, %3\n" \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ } #define ATOMIC_OPS(...) \ ATOMIC_OP(__VA_ARGS__) \ ATOMIC_OP_RETURN( , dmb ish, , l, "memory", __VA_ARGS__)\ ATOMIC_OP_RETURN(_relaxed, , , , , __VA_ARGS__)\ ATOMIC_OP_RETURN(_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_OP_RETURN(_release, , , l, "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP ( , dmb ish, , l, "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_relaxed, , , , , __VA_ARGS__)\ ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) ATOMIC_OPS(add, add, I) ATOMIC_OPS(sub, sub, J) #undef ATOMIC_OPS #define ATOMIC_OPS(...) \ ATOMIC_OP(__VA_ARGS__) \ ATOMIC_FETCH_OP ( , dmb ish, , l, "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_relaxed, , , , , __VA_ARGS__)\ ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) ATOMIC_OPS(and, and, K) ATOMIC_OPS(or, orr, K) ATOMIC_OPS(xor, eor, K) /* * GAS converts the mysterious and undocumented BIC (immediate) alias to * an AND (immediate) instruction with the immediate inverted. We don't * have a constraint for this, so fall back to register. */ ATOMIC_OPS(andnot, bic, ) #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP #define ATOMIC64_OP(op, asm_op, constraint) \ static __always_inline void \ __ll_sc_atomic64_##op(s64 i, atomic64_t *v) \ { \ s64 result; \ unsigned long tmp; \ \ asm volatile("// atomic64_" #op "\n" \ " prfm pstl1strm, %2\n" \ "1: ldxr %0, %2\n" \ " " #asm_op " %0, %0, %3\n" \ " stxr %w1, %0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i)); \ } #define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ static __always_inline long \ __ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v) \ { \ s64 result; \ unsigned long tmp; \ \ asm volatile("// atomic64_" #op "_return" #name "\n" \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr %0, %2\n" \ " " #asm_op " %0, %0, %3\n" \ " st" #rel "xr %w1, %0, %2\n" \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ } #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ static __always_inline long \ __ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ { \ s64 result, val; \ unsigned long tmp; \ \ asm volatile("// atomic64_fetch_" #op #name "\n" \ " prfm pstl1strm, %3\n" \ "1: ld" #acq "xr %0, %3\n" \ " " #asm_op " %1, %0, %4\n" \ " st" #rel "xr %w2, %1, %3\n" \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ : __stringify(constraint) "r" (i) \ : cl); \ \ return result; \ } #define ATOMIC64_OPS(...) \ ATOMIC64_OP(__VA_ARGS__) \ ATOMIC64_OP_RETURN(, dmb ish, , l, "memory", __VA_ARGS__) \ ATOMIC64_OP_RETURN(_relaxed,, , , , __VA_ARGS__) \ ATOMIC64_OP_RETURN(_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_OP_RETURN(_release,, , l, "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (, dmb ish, , l, "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_relaxed,, , , , __VA_ARGS__) \ ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) ATOMIC64_OPS(add, add, I) ATOMIC64_OPS(sub, sub, J) #undef ATOMIC64_OPS #define ATOMIC64_OPS(...) \ ATOMIC64_OP(__VA_ARGS__) \ ATOMIC64_FETCH_OP (, dmb ish, , l, "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_relaxed,, , , , __VA_ARGS__) \ ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) ATOMIC64_OPS(and, and, L) ATOMIC64_OPS(or, orr, L) ATOMIC64_OPS(xor, eor, L) /* * GAS converts the mysterious and undocumented BIC (immediate) alias to * an AND (immediate) instruction with the immediate inverted. We don't * have a constraint for this, so fall back to register. */ ATOMIC64_OPS(andnot, bic, ) #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP static __always_inline s64 __ll_sc_atomic64_dec_if_positive(atomic64_t *v) { s64 result; unsigned long tmp; asm volatile("// atomic64_dec_if_positive\n" " prfm pstl1strm, %2\n" "1: ldxr %0, %2\n" " subs %0, %0, #1\n" " b.lt 2f\n" " stlxr %w1, %0, %2\n" " cbnz %w1, 1b\n" " dmb ish\n" "2:" : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) : : "cc", "memory"); return result; } #define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ static __always_inline u##sz \ __ll_sc__cmpxchg_case_##name##sz(volatile void *ptr, \ unsigned long old, \ u##sz new) \ { \ unsigned long tmp; \ u##sz oldval; \ \ /* \ * Sub-word sizes require explicit casting so that the compare \ * part of the cmpxchg doesn't end up interpreting non-zero \ * upper bits of the register containing "old". \ */ \ if (sz < 32) \ old = (u##sz)old; \ \ asm volatile( \ " prfm pstl1strm, %[v]\n" \ "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ " cbnz %" #w "[tmp], 2f\n" \ " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ [v] "+Q" (*(u##sz *)ptr) \ : [old] __stringify(constraint) "r" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ } /* * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly * handle the 'K' constraint for the value 4294967295 - thus we use no * constraint for 32 bit operations. */ __CMPXCHG_CASE(w, b, , 8, , , , , K) __CMPXCHG_CASE(w, h, , 16, , , , , K) __CMPXCHG_CASE(w, , , 32, , , , , K) __CMPXCHG_CASE( , , , 64, , , , , L) __CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory", K) __CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory", K) __CMPXCHG_CASE(w, , acq_, 32, , a, , "memory", K) __CMPXCHG_CASE( , , acq_, 64, , a, , "memory", L) __CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory", K) __CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory", K) __CMPXCHG_CASE(w, , rel_, 32, , , l, "memory", K) __CMPXCHG_CASE( , , rel_, 64, , , l, "memory", L) __CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory", K) __CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory", K) __CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory", K) __CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE union __u128_halves { u128 full; struct { u64 low, high; }; }; #define __CMPXCHG128(name, mb, rel, cl...) \ static __always_inline u128 \ __ll_sc__cmpxchg128##name(volatile u128 *ptr, u128 old, u128 new) \ { \ union __u128_halves r, o = { .full = (old) }, \ n = { .full = (new) }; \ unsigned int tmp; \ \ asm volatile("// __cmpxchg128" #name "\n" \ " prfm pstl1strm, %[v]\n" \ "1: ldxp %[rl], %[rh], %[v]\n" \ " cmp %[rl], %[ol]\n" \ " ccmp %[rh], %[oh], 0, eq\n" \ " b.ne 2f\n" \ " st" #rel "xp %w[tmp], %[nl], %[nh], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ "2:" \ : [v] "+Q" (*(u128 *)ptr), \ [rl] "=&r" (r.low), [rh] "=&r" (r.high), \ [tmp] "=&r" (tmp) \ : [ol] "r" (o.low), [oh] "r" (o.high), \ [nl] "r" (n.low), [nh] "r" (n.high) \ : "cc", ##cl); \ \ return r.full; \ } __CMPXCHG128( , , ) __CMPXCHG128(_mb, dmb ish, l, "memory") #undef __CMPXCHG128 #undef K #endif /* __ASM_ATOMIC_LL_SC_H */ |
| 122 122 122 258 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 ARM Ltd. */ #ifndef __ASM_WORD_AT_A_TIME_H #define __ASM_WORD_AT_A_TIME_H #include <linux/uaccess.h> #ifndef __AARCH64EB__ #include <linux/bitops.h> #include <linux/wordpart.h> struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } #define prep_zero_mask(a, bits, c) (bits) static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } static inline unsigned long find_zero(unsigned long mask) { return fls64(mask) >> 3; } #define zero_bytemask(mask) (mask) #else /* __AARCH64EB__ */ #include <asm-generic/word-at-a-time.h> #endif /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret; __mte_enable_tco_async(); /* Load word from unaligned pointer addr */ asm( "1: ldr %0, %2\n" "2:\n" _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1) : "=&r" (ret) : "r" (addr), "Q" (*(unsigned long *)addr)); __mte_disable_tco_async(); return ret; } #endif /* __ASM_WORD_AT_A_TIME_H */ |
| 101 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 56 10 10 10 10 10 10 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 18 10 5 18 18 10 15 9 18 18 18 18 130 18 130 130 10 10 10 10 10 10 10 10 10 5 5 5 5 5 5 5 2 5 5 7 7 7 7 2 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/mlock.c * * (C) Copyright 1995 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig */ #include <linux/capability.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/sched/user.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/pagewalk.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> #include <linux/export.h> #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/secretmem.h> #include "internal.h" struct mlock_fbatch { local_lock_t lock; struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = { .lock = INIT_LOCAL_LOCK(lock), }; bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) return true; if (capable(CAP_IPC_LOCK)) return true; return false; } EXPORT_SYMBOL(can_do_mlock); /* * Mlocked folios are marked with the PG_mlocked flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * * An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it * will be ostensibly placed on the LRU "unevictable" list (actually no such * list exists), rather than the [in]active lists. PG_unevictable is set to * indicate the unevictable state. */ static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec) { /* There is nothing more we can do while it's off LRU */ if (!folio_test_clear_lru(folio)) return lruvec; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (unlikely(folio_evictable(folio))) { /* * This is a little surprising, but quite possible: PG_mlocked * must have got cleared already by another CPU. Could this * folio be unevictable? I'm not sure, but move it now if so. */ if (folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, folio_nr_pages(folio)); } goto out; } if (folio_test_unevictable(folio)) { if (folio_test_mlocked(folio)) folio->mlock_count++; goto out; } lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: folio_set_lru(folio); return lruvec; } static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); lruvec = folio_lruvec_relock_irq(folio, lruvec); /* As above, this is a little surprising, but possible */ if (unlikely(folio_evictable(folio))) goto out; folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: lruvec_add_folio(lruvec, folio); folio_set_lru(folio); return lruvec; } static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec) { int nr_pages = folio_nr_pages(folio); bool isolated = false; if (!folio_test_clear_lru(folio)) goto munlock; isolated = true; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_test_unevictable(folio)) { /* Then mlock_count is maintained, but might undercount */ if (folio->mlock_count) folio->mlock_count--; if (folio->mlock_count) goto out; } /* else assume that was the last mlock: reclaim will fix it if not */ munlock: if (folio_test_clear_mlocked(folio)) { __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); if (isolated || !folio_test_unevictable(folio)) __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); else __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); } /* folio_evictable() has to be checked *after* clearing Mlocked */ if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } out: if (isolated) folio_set_lru(folio); return lruvec; } /* * Flags held in the low bits of a struct folio pointer on the mlock_fbatch. */ #define LRU_FOLIO 0x1 #define NEW_FOLIO 0x2 static inline struct folio *mlock_lru(struct folio *folio) { return (struct folio *)((unsigned long)folio + LRU_FOLIO); } static inline struct folio *mlock_new(struct folio *folio) { return (struct folio *)((unsigned long)folio + NEW_FOLIO); } /* * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can * make use of such folio pointer flags in future, but for now just keep it for * mlock. We could use three separate folio batches instead, but one feels * better (munlocking a full folio batch does not need to drain mlocking folio * batches first). */ static void mlock_folio_batch(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; unsigned long mlock; struct folio *folio; int i; for (i = 0; i < folio_batch_count(fbatch); i++) { folio = fbatch->folios[i]; mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO); folio = (struct folio *)((unsigned long)folio - mlock); fbatch->folios[i] = folio; if (mlock & LRU_FOLIO) lruvec = __mlock_folio(folio, lruvec); else if (mlock & NEW_FOLIO) lruvec = __mlock_new_folio(folio, lruvec); else lruvec = __munlock_folio(folio, lruvec); } if (lruvec) unlock_page_lruvec_irq(lruvec); folios_put(fbatch); } void mlock_drain_local(void) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } void mlock_drain_remote(int cpu) { struct folio_batch *fbatch; WARN_ON_ONCE(cpu_online(cpu)); fbatch = &per_cpu(mlock_fbatch.fbatch, cpu); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); } bool need_mlock_drain(int cpu) { return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu)); } /** * mlock_folio - mlock a folio already on (or temporarily off) LRU * @folio: folio to be mlocked. */ void mlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * mlock_new_folio - mlock a newly allocated folio not yet on LRU * @folio: folio to be mlocked, either normal or a THP head. */ void mlock_new_folio(struct folio *folio) { struct folio_batch *fbatch; int nr_pages = folio_nr_pages(folio); local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); folio_set_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * munlock_folio - munlock a folio * @folio: folio to be munlocked, either normal or a THP head. */ void munlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); /* * folio_test_clear_mlocked(folio) must be left to __munlock_folio(), * which will check whether the folio is multiply mlocked. */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } static inline unsigned int folio_mlock_step(struct folio *folio, pte_t *pte, unsigned long addr, unsigned long end) { unsigned int count, i, nr = folio_nr_pages(folio); unsigned long pfn = folio_pfn(folio); pte_t ptent = ptep_get(pte); if (!folio_test_large(folio)) return 1; count = pfn + nr - pte_pfn(ptent); count = min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT); for (i = 0; i < count; i++, pte++) { pte_t entry = ptep_get(pte); if (!pte_present(entry)) break; if (pte_pfn(entry) - pfn >= nr) break; } return i; } static inline bool allow_mlock_munlock(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned int step) { /* * For unlock, allow munlock large folio which is partially * mapped to VMA. As it's possible that large folio is * mlocked and VMA is split later. * * During memory pressure, such kind of large folio can * be split. And the pages are not in VM_LOCKed VMA * can be reclaimed. */ if (!(vma->vm_flags & VM_LOCKED)) return true; /* folio_within_range() cannot take KSM, but any small folio is OK */ if (!folio_test_large(folio)) return true; /* folio not in range [start, end), skip mlock */ if (!folio_within_range(folio, vma, start, end)) return false; /* folio is not fully mapped, skip mlock */ if (step != folio_nr_pages(folio)) return false; return true; } static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; unsigned int step = 1; unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (!pmd_present(*pmd)) goto out; if (is_huge_zero_pmd(*pmd)) goto out; folio = pmd_folio(*pmd); if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); goto out; } start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) { walk->action = ACTION_AGAIN; return 0; } for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; step = folio_mlock_step(folio, pte, addr, end); if (!allow_mlock_munlock(folio, vma, start, end, step)) goto next_entry; if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); next_entry: pte += step - 1; addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: spin_unlock(ptl); cond_resched(); return 0; } /* * mlock_vma_pages_range() - mlock any pages already in the range, * or munlock all pages in the range. * @vma - vma containing range to be mlock()ed or munlock()ed * @start - start address in @vma of the range * @end - end of range in @vma * @newflags - the new set of flags for @vma. * * Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED; * called for munlock() and munlockall(), to clear VM_LOCKED from @vma. */ static void mlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, vm_flags_t newflags) { static const struct mm_walk_ops mlock_walk_ops = { .pmd_entry = mlock_pte_range, .walk_lock = PGWALK_WRLOCK_VERIFY, }; /* * There is a slight chance that concurrent page migration, * or page reclaim finding a page of this now-VM_LOCKED vma, * will call mlock_vma_folio() and raise page's mlock_count: * double counting, leaving the page unevictable indefinitely. * Communicate this danger to mlock_vma_folio() with VM_IO, * which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas. * mmap_lock is held in write mode here, so this weird * combination should not be visible to other mmap_lock users; * but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED. */ if (newflags & VM_LOCKED) newflags |= VM_IO; vma_start_write(vma); vm_flags_reset_once(vma, newflags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); lru_add_drain(); if (newflags & VM_IO) { newflags &= ~VM_IO; vm_flags_reset_once(vma, newflags); } } /* * mlock_fixup - handle mlock[all]/munlock[all] requests. * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; int nr_pages; int ret = 0; vm_flags_t oldflags = vma->vm_flags; if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || vma_is_dax(vma) || vma_is_secretmem(vma)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; if (!(newflags & VM_LOCKED)) nr_pages = -nr_pages; else if (oldflags & VM_LOCKED) nr_pages = 0; mm->locked_vm += nr_pages; /* * vm_flags is protected by the mmap_lock held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) { /* No work to do, and mlocking twice would be wrong */ vma_start_write(vma); vm_flags_reset(vma, newflags); } else { mlock_vma_pages_range(vma, start, end, newflags); } out: *prev = vma; return ret; } static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; struct vm_area_struct *vma, *prev; VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; vma = vma_iter_load(&vmi); if (!vma) return -ENOMEM; prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; nstart = start; tmp = vma->vm_start; for_each_vma_range(vmi, vma, end) { int error; vm_flags_t newflags; if (vma->vm_start != tmp) return -ENOMEM; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) return error; tmp = vma_iter_end(&vmi); nstart = tmp; } if (tmp < end) return -ENOMEM; return 0; } /* * Go through vma areas and sum size of mlocked * vma pages, as return value. * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) * is also counted. * Return value: previously mlocked page counts */ static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; unsigned long count = 0; unsigned long end; VMA_ITERATOR(vmi, mm, start); /* Don't overflow past ULONG_MAX */ if (unlikely(ULONG_MAX - len < start)) end = ULONG_MAX; else end = start + len; for_each_vma_range(vmi, vma, end) { if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); if (end < vma->vm_end) { count += end - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; } } return count >> PAGE_SHIFT; } /* * convert get_user_pages() return value to posix mlock() error */ static int __mlock_posix_error_return(long retval) { if (retval == -EFAULT) retval = -ENOMEM; else if (retval == -ENOMEM) retval = -EAGAIN; return retval; } static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; start = untagged_addr(start); if (!can_do_mlock()) return -EPERM; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; locked += current->mm->locked_vm; if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { /* * It is possible that the regions requested intersect with * previously mlocked areas, that part area in "mm->locked_vm" * should not be counted to new mlock increment count. So check * and adjust locked count if necessary. */ locked -= count_mm_mlocked_page_nr(current->mm, start, len); } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); mmap_write_unlock(current->mm); if (error) return error; error = __mm_populate(start, len, 0); if (error) return __mlock_posix_error_return(error); return 0; } SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { return do_mlock(start, len, VM_LOCKED); } SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { vm_flags_t vm_flags = VM_LOCKED; if (flags & ~MLOCK_ONFAULT) return -EINVAL; if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT; return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; start = untagged_addr(start); len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); mmap_write_unlock(current->mm); return ret; } /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the * flags for all current VMAs. * * There are a couple of subtleties with this. If mlockall() is called multiple * times with different flags, the values do not necessarily stack. If mlockall * is called once including the MCL_FUTURE flag and then a second time without * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. */ static int apply_mlockall_flags(int flags) { VMA_ITERATOR(vmi, current->mm, 0); struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; if (flags & MCL_ONFAULT) current->mm->def_flags |= VM_LOCKONFAULT; if (!(flags & MCL_CURRENT)) goto out; } if (flags & MCL_CURRENT) { to_add |= VM_LOCKED; if (flags & MCL_ONFAULT) to_add |= VM_LOCKONFAULT; } for_each_vma(vmi, vma) { vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; /* Ignore errors */ mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, newflags); cond_resched(); } out: return 0; } SYSCALL_DEFINE1(mlockall, int, flags) { unsigned long lock_limit; int ret; if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) return -EPERM; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); mmap_write_unlock(current->mm); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); return ret; } SYSCALL_DEFINE0(munlockall) { int ret; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_mlockall_flags(0); mmap_write_unlock(current->mm); return ret; } /* * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB * shm segments) get accounted against the user_struct instead. */ static DEFINE_SPINLOCK(shmlock_user_lock); int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); if (lock_limit != RLIM_INFINITY) lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; } if (!get_ucounts(ucounts)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); allowed = 0; goto out; } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); put_ucounts(ucounts); } |
| 105 106 105 106 96 96 14 106 106 106 106 106 106 105 105 106 105 106 56 56 56 56 96 96 56 56 56 56 96 96 96 96 96 96 96 96 96 96 96 96 14 14 15 96 96 96 96 96 96 96 96 96 96 96 96 96 96 96 96 96 96 96 106 105 105 106 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. * Dave Platt : Interrupt stacking fix. * Richard Kooijman : Timestamp fixes. * Alan Cox : Changed buffer format. * Alan Cox : destructor hook for AF_UNIX etc. * Linus Torvalds : Better skb_clone. * Alan Cox : Added skb_copy. * Alan Cox : Added all the changed routines Linus * only put in the headers * Ray VanTassle : Fixed --skb->lock in free * Alan Cox : skb_copy copy arp field * Andi Kleen : slabified it. * Robert Olsson : Removed skb_head_pool * * NOTE: * The __skb_ routines should be called with interrupts * disabled, or you better be *real* sure that the operation is atomic * with respect to whatever list is being frobbed (e.g. via lock_sock() * or via disabling bottom half handlers, etc). */ /* * The functions in this file will not compile correctly with gcc 2.4.x */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/bitfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> #include <linux/iov_iter.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> #include <net/mctp.h> #include <net/page_pool/helpers.h> #include <net/dropreason.h> #include <linux/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> #include <linux/indirect_call_wrapper.h> #include <linux/textsearch.h> #include "dev.h" #include "sock_destructor.h" #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique * size, and we can differentiate heads from skb_small_head_cache * vs system slabs by looking at their size (skb_end_offset()). */ #define SKB_SMALL_HEAD_CACHE_SIZE \ (is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \ (SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \ SKB_SMALL_HEAD_SIZE) #define SKB_SMALL_HEAD_HEADROOM \ SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) /* kcm_write_msgs() relies on casting paged frags to bio_vec to use * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the * netmem is a page. */ static_assert(offsetof(struct bio_vec, bv_page) == offsetof(skb_frag_t, netmem)); static_assert(sizeof_field(struct bio_vec, bv_page) == sizeof_field(skb_frag_t, netmem)); static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len)); static_assert(sizeof_field(struct bio_vec, bv_len) == sizeof_field(skb_frag_t, len)); static_assert(offsetof(struct bio_vec, bv_offset) == offsetof(skb_frag_t, offset)); static_assert(sizeof_field(struct bio_vec, bv_offset) == sizeof_field(skb_frag_t, offset)); #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, static const char * const drop_reasons[] = { [SKB_CONSUMED] = "CONSUMED", DEFINE_DROP_REASON(FN, FN) }; static const struct drop_reason_list drop_reasons_core = { .reasons = drop_reasons, .n_reasons = ARRAY_SIZE(drop_reasons), }; const struct drop_reason_list __rcu * drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM] = { [SKB_DROP_REASON_SUBSYS_CORE] = RCU_INITIALIZER(&drop_reasons_core), }; EXPORT_SYMBOL(drop_reasons_by_subsys); /** * drop_reasons_register_subsys - register another drop reason subsystem * @subsys: the subsystem to register, must not be the core * @list: the list of drop reasons within the subsystem, must point to * a statically initialized list */ void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys, const struct drop_reason_list *list) { if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE || subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return; /* must point to statically allocated memory, so INIT is OK */ RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], list); } EXPORT_SYMBOL_GPL(drop_reasons_register_subsys); /** * drop_reasons_unregister_subsys - unregister a drop reason subsystem * @subsys: the subsystem to remove, must not be the core * * Note: This will synchronize_rcu() to ensure no users when it returns. */ void drop_reasons_unregister_subsys(enum skb_drop_reason_subsys subsys) { if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE || subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return; RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], NULL); synchronize_rcu(); } EXPORT_SYMBOL_GPL(drop_reasons_unregister_subsys); /** * skb_panic - private function for out-of-line support * @skb: buffer * @sz: size * @addr: address * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). * Keep out of line to prevent kernel bloat. * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, const char msg[]) { pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n", msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : "<NULL>"); BUG(); } static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } #define NAPI_SKB_CACHE_SIZE 64 #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) #if PAGE_SIZE == SZ_4K #define NAPI_HAS_SMALL_PAGE_FRAG 1 #define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) /* specialized page frag allocator using a single order 0 page * and slicing it into 1K sized fragment. Constrained to systems * with a very limited amount of 1K fragments fitting a single * page - to avoid excessive truesize underestimation */ struct page_frag_1k { void *va; u16 offset; bool pfmemalloc; }; static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) { struct page *page; int offset; offset = nc->offset - SZ_1K; if (likely(offset >= 0)) goto use_frag; page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); if (!page) return NULL; nc->va = page_address(page); nc->pfmemalloc = page_is_pfmemalloc(page); offset = PAGE_SIZE - SZ_1K; page_ref_add(page, offset / SZ_1K); use_frag: nc->offset = offset; return nc->va + offset; } #else /* the small page is actually unused in this build; add dummy helpers * to please the compiler and avoid later preprocessor's conditionals */ #define NAPI_HAS_SMALL_PAGE_FRAG 0 #define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false struct page_frag_1k { }; static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) { return NULL; } #endif struct napi_alloc_cache { struct page_frag_cache page; struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); /* Double check that napi_get_frags() allocates skbs with * skb->head being backed by slab, not a page fragment. * This is to make sure bug fixed in 3226b158e67c * ("net: avoid 32 x truesize under-estimation for tiny skbs") * does not accidentally come back. */ void napi_get_frags_check(struct napi_struct *napi) { struct sk_buff *skb; local_bh_disable(); skb = napi_get_frags(napi); WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); napi_free_frags(napi); local_bh_enable(); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); fragsz = SKB_DATA_ALIGN(fragsz); return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { struct napi_alloc_cache *nc; local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache); data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); local_bh_enable(); } return data; } EXPORT_SYMBOL(__netdev_alloc_frag_align); static struct sk_buff *napi_skb_cache_get(void) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; if (unlikely(!nc->skb_count)) { nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); if (unlikely(!nc->skb_count)) return NULL; } skb = nc->skb_cache[--nc->skb_count]; kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; } static inline void __finalize_skb_around(struct sk_buff *skb, void *data, unsigned int size) { struct skb_shared_info *shinfo; size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /* Assumes caller memset cleared SKB */ skb->truesize = SKB_TRUESIZE(size); refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb_set_end_offset(skb, size); skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; skb->alloc_cpu = raw_smp_processor_id(); /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); skb_set_kcov_handle(skb, kcov_common_handle()); } static inline void *__slab_build_skb(struct sk_buff *skb, void *data, unsigned int *size) { void *resized; /* Must find the allocation size (and grow it to match). */ *size = ksize(data); /* krealloc() will immediately return "data" when * "ksize(data)" is requested: it is the existing upper * bounds. As a result, GFP_ATOMIC will be ignored. Note * that this "new" pointer needs to be passed back to the * caller for use so the __alloc_size hinting will be * tracked correctly. */ resized = krealloc(data, *size, GFP_ATOMIC); WARN_ON_ONCE(resized != data); return resized; } /* build_skb() variant which can operate on slab buffers. * Note that this should be used sparingly as slab buffers * cannot be combined efficiently by GRO! */ struct sk_buff *slab_build_skb(void *data) { struct sk_buff *skb; unsigned int size; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); data = __slab_build_skb(skb, data, &size); __finalize_skb_around(skb, data, size); return skb; } EXPORT_SYMBOL(slab_build_skb); /* Caller must provide SKB that is memset cleared */ static void __build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { unsigned int size = frag_size; /* frag_size == 0 is considered deprecated now. Callers * using slab buffer should use slab_build_skb() instead. */ if (WARN_ONCE(size == 0, "Use slab_build_skb() instead")) data = __slab_build_skb(skb, data, &size); __finalize_skb_around(skb, data, size); } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data (must not be 0) * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated from the page * allocator or vmalloc(). (A @frag_size of 0 to indicate a kmalloc() * allocation is deprecated, and callers should use slab_build_skb() * instead.) * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : * Before IO, driver allocates only data buffer where NIC put incoming frame * Driver should add room at head (NET_SKB_PAD) and * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) * After IO, driver calls build_skb(), to allocate sk_buff and populate it * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); __build_skb_around(skb, data, frag_size); return skb; } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __build_skb(data, frag_size); if (likely(skb && frag_size)) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(build_skb); /** * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller * @frag_size: size of data */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { if (unlikely(!skb)) return NULL; __build_skb_around(skb, data, frag_size); if (frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(build_skb_around); /** * __napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __build_skb() that uses NAPI percpu caches to obtain * skbuff_head instead of inplace allocation. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = napi_skb_cache_get(); if (unlikely(!skb)) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); __build_skb_around(skb, data, frag_size); return skb; } /** * napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __napi_build_skb() that takes care of skb->head_frag * and skb->pfmemalloc when the data is a page or page fragment. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ struct sk_buff *napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __napi_build_skb(data, frag_size); if (likely(skb) && frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(napi_build_skb); /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells * the caller if emergency pfmemalloc reserves are being used. If it is and * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { bool ret_pfmemalloc = false; size_t obj_size; void *obj; obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); goto out; } obj_size = kmalloc_size_roundup(obj_size); /* The following cast might truncate high-order bits of obj_size, this * is harmless because kmalloc(obj_size >= 2^32) will fail anyway. */ *size = (unsigned int)obj_size; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; obj = kmalloc_node_track_caller(obj_size, flags, node); out: if (pfmemalloc) *pfmemalloc = ret_pfmemalloc; return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. * */ /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache * instead of head cache and allocate a cloned (child) skb. * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of at least size bytes. The object has a reference count * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { struct kmem_cache *cache; struct sk_buff *skb; bool pfmemalloc; u8 *data; cache = (flags & SKB_ALLOC_FCLONE) ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI && likely(node == NUMA_NO_NODE || node == numa_mem_id())) skb = napi_skb_cache_get(); else skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); if (unlikely(!skb)) return NULL; prefetchw(skb); /* We do our best to align skb_shared_info on a separate cache * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ prefetchw(data + SKB_WITH_OVERHEAD(size)); /* * Only clear those fields we need to clear, not those that we will * actually initialise below. Hence, don't put any more fields after * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); __build_skb_around(skb, data, size); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); skb->fclone = SKB_FCLONE_ORIG; refcount_set(&fclones->fclone_ref, 1); } return skb; nodata: kmem_cache_free(cache, skb); return NULL; } EXPORT_SYMBOL(__alloc_skb); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has NET_SKB_PAD headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, gfp_t gfp_mask) { struct page_frag_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; len += NET_SKB_PAD; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; } else { local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; local_bh_enable(); } if (unlikely(!data)) return NULL; skb = __build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); /** * napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used * only for NAPI Rx allocation. By doing this we can save several * CPU cycles by avoiding having to disable and re-enable IRQs. * * %NULL is returned if there is no free memory. */ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) { gfp_t gfp_mask = GFP_ATOMIC | __GFP_NOWARN; struct napi_alloc_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; DEBUG_NET_WARN_ON_ONCE(!in_softirq()); len += NET_SKB_PAD + NET_IP_ALIGN; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. * When the small frag allocator is available, prefer it over kmalloc * for small fragments */ if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } nc = this_cpu_ptr(&napi_alloc_cache); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { /* we are artificially inflating the allocation size, but * that is not as bad as it may look like, as: * - 'len' less than GRO_MAX_HEAD makes little sense * - On most systems, larger 'len' values lead to fragment * size above 512 bytes * - kmalloc would use the kmalloc-1k slab for such values * - Builds with smaller GRO_MAX_HEAD will very likely do * little networking, as that implies no WiFi and no * tunnels support, and 32 bits arches. */ len = SZ_1K; data = page_frag_alloc_1k(&nc->page_small, gfp_mask); pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); } else { len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; } if (unlikely(!data)) return NULL; skb = __napi_build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); skb->dev = napi->dev; skb_fail: return skb; } EXPORT_SYMBOL(napi_alloc_skb); void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize) { DEBUG_NET_WARN_ON_ONCE(size > truesize); skb_fill_netmem_desc(skb, i, netmem, off, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_add_rx_frag_netmem); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; DEBUG_NET_WARN_ON_ONCE(size > truesize); skb_frag_size_add(frag, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_coalesce_rx_frag); static void skb_drop_list(struct sk_buff **listp) { kfree_skb_list(*listp); *listp = NULL; } static inline void skb_drop_fraglist(struct sk_buff *skb) { skb_drop_list(&skb_shinfo(skb)->frag_list); } static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; skb_walk_frags(skb, list) skb_get(list); } static bool is_pp_page(struct page *page) { return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom) { #if IS_ENABLED(CONFIG_PAGE_POOL) u32 size, truesize, len, max_head_size, off; struct sk_buff *skb = *pskb, *nskb; int err, i, head_off; void *data; /* XDP does not support fraglist so we need to linearize * the skb. */ if (skb_has_frag_list(skb)) return -EOPNOTSUPP; max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) return -ENOMEM; size = min_t(u32, skb->len, max_head_size); truesize = SKB_HEAD_ALIGN(size) + headroom; data = page_pool_dev_alloc_va(pool, &truesize); if (!data) return -ENOMEM; nskb = napi_build_skb(data, truesize); if (!nskb) { page_pool_free_va(pool, data, true); return -ENOMEM; } skb_reserve(nskb, headroom); skb_copy_header(nskb, skb); skb_mark_for_recycle(nskb); err = skb_copy_bits(skb, 0, nskb->data, size); if (err) { consume_skb(nskb); return err; } skb_put(nskb, size); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); off = size; len = skb->len - off; for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { struct page *page; u32 page_off; size = min_t(u32, len, PAGE_SIZE); truesize = size; page = page_pool_dev_alloc(pool, &page_off, &truesize); if (!page) { consume_skb(nskb); return -ENOMEM; } skb_add_rx_frag(nskb, i, page, page_off, size, truesize); err = skb_copy_bits(skb, off, page_address(page) + page_off, size); if (err) { consume_skb(nskb); return err; } len -= size; off += size; } consume_skb(skb); *pskb = nskb; return 0; #else return -EOPNOTSUPP; #endif } EXPORT_SYMBOL(skb_pp_cow_data); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog) { if (!prog->aux->xdp_has_frags) return -EINVAL; return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM); } EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(struct page *page) { page = compound_head(page); /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation * in order to preserve any existing bits, such as bit 0 for the * head page of compound page and bit 1 for pfmemalloc page, so * mask those bits for freeing side when doing below checking, * and page_is_pfmemalloc() is checked in __page_pool_put_page() * to avoid recycling the pfmemalloc page. */ if (unlikely(!is_pp_page(page))) return false; page_pool_put_full_page(page->pp, page, false); return true; } EXPORT_SYMBOL(napi_pp_put_page); #endif static bool skb_pp_recycle(struct sk_buff *skb, void *data) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; return napi_pp_put_page(virt_to_page(data)); } /** * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb * @skb: page pool aware skb * * Increase the fragment reference count (pp_ref_count) of a skb. This is * intended to gain fragment references only for page pool aware skbs, * i.e. when skb->pp_recycle is true, and not for fragments in a * non-pp-recycling skb. It has a fallback to increase references on normal * pages, as page pool aware skbs may also have normal page fragments. */ static int skb_pp_frag_ref(struct sk_buff *skb) { struct skb_shared_info *shinfo; struct page *head_page; int i; if (!skb->pp_recycle) return -EINVAL; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { head_page = compound_head(skb_frag_page(&shinfo->frags[i])); if (likely(is_pp_page(head_page))) page_pool_ref_page(head_page); else page_ref_inc(head_page); } return 0; } static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) kmem_cache_free(net_hotdata.skb_small_head_cache, head); else kfree(head); } static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; if (skb->head_frag) { if (skb_pp_recycle(skb, head)) return; skb_free_frag(head); } else { skb_kfree_head(head, skb_end_offset(skb)); } } static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; if (!skb_data_unref(skb, shinfo)) goto exit; if (skb_zcopy(skb)) { bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS; skb_zcopy_clear(skb, true); if (skip_unref) goto free_head; } for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); free_head: if (shinfo->frag_list) kfree_skb_list_reason(shinfo->frag_list, reason); skb_free_head(skb); exit: /* When we clone an SKB we copy the reycling bit. The pp_recycle * bit is only set on the head though, so in order to avoid races * while trying to recycle fragments on __skb_frag_unref() we need * to make one SKB responsible for triggering the recycle path. * So disable the recycling bit if an SKB is cloned and we have * additional references to the fragmented part of the SKB. * Eventually the last SKB will have the recycling bit set and it's * dataref set to 0, which will trigger the recycling */ skb->pp_recycle = 0; } /* * Free an skbuff by memory without cleaning the state. */ static void kfree_skbmem(struct sk_buff *skb) { struct sk_buff_fclones *fclones; switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: fclones = container_of(skb, struct sk_buff_fclones, skb1); /* We usually free the clone (TX completion) before original skb * This test would have no chance to be true for the clone, * while here, branch prediction will be good. */ if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break; default: /* SKB_FCLONE_CLONE */ fclones = container_of(skb, struct sk_buff_fclones, skb2); break; } if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { DEBUG_NET_WARN_ON_ONCE(in_hardirq()); skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb_nfct(skb)); #endif skb_ext_put(skb); } /* Free everything but the sk_buff shell. */ static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_head_state(skb); if (likely(skb->head)) skb_release_data(skb, reason); } /** * __kfree_skb - private function * @skb: buffer * * Free an sk_buff. Release anything attached to the buffer. * Clean the state. This is an internal helper function. Users should * always call kfree_skb */ void __kfree_skb(struct sk_buff *skb) { skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); static __always_inline bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (unlikely(!skb_unref(skb))) return false; DEBUG_NET_WARN_ON_ONCE(reason == SKB_NOT_DROPPED_YET || u32_get_bits(reason, SKB_DROP_REASON_SUBSYS_MASK) >= SKB_DROP_REASON_SUBSYS_NUM); if (reason == SKB_CONSUMED) trace_consume_skb(skb, __builtin_return_address(0)); else trace_kfree_skb(skb, __builtin_return_address(0), reason); return true; } /** * kfree_skb_reason - free an sk_buff with special reason * @skb: buffer to free * @reason: reason why this skb is dropped * * Drop a reference to the buffer and free it if the usage count has * hit zero. Meanwhile, pass the drop reason to 'kfree_skb' * tracepoint. */ void __fix_address kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (__kfree_skb_reason(skb, reason)) __kfree_skb(skb); } EXPORT_SYMBOL(kfree_skb_reason); #define KFREE_SKB_BULK_SIZE 16 struct skb_free_array { unsigned int skb_count; void *skb_array[KFREE_SKB_BULK_SIZE]; }; static void kfree_skb_add_bulk(struct sk_buff *skb, struct skb_free_array *sa, enum skb_drop_reason reason) { /* if SKB is a clone, don't handle this case */ if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { __kfree_skb(skb); return; } skb_release_all(skb, reason); sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } } void __fix_address kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) { struct skb_free_array sa; sa.skb_count = 0; while (segs) { struct sk_buff *next = segs->next; if (__kfree_skb_reason(segs, reason)) { skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); } segs = next; } if (sa.skb_count) kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); /* Dump skb information and contents. * * Must only be called from net_ratelimit()-ed paths. * * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; struct sk_buff *list_skb; bool has_mac, has_trans; int headroom, tailroom; int i, len, seg_len; if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); headroom = skb_headroom(skb); tailroom = skb_tailroom(skb); has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n" "mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n" "priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n" "encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n", level, skb->len, headroom, skb_headlen(skb), tailroom, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->mac_len, skb->network_header, has_trans ? skb_network_header_len(skb) : -1, has_trans ? skb->transport_header : -1, sh->tx_flags, sh->nr_frags, sh->gso_size, sh->gso_type, sh->gso_segs, skb->csum, skb->csum_start, skb->csum_offset, skb->ip_summed, skb->csum_complete_sw, skb->csum_valid, skb->csum_level, skb->hash, skb->sw_hash, skb->l4_hash, ntohs(skb->protocol), skb->pkt_type, skb->skb_iif, skb->priority, skb->mark, skb->alloc_cpu, skb->vlan_all, skb->encapsulation, skb->inner_protocol, skb->inner_mac_header, skb->inner_network_header, skb->inner_transport_header); if (dev) printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", level, sk->sk_family, sk->sk_type, sk->sk_protocol); if (full_pkt && headroom) print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb->head, headroom, false); seg_len = min_t(int, skb_headlen(skb), len); if (seg_len) print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, seg_len, false); len -= seg_len; if (full_pkt && tailroom) print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb_tail_pointer(skb), tailroom, false); for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); vaddr = kmap_atomic(p); print_hex_dump(level, "skb frag: ", DUMP_PREFIX_OFFSET, 16, 1, vaddr + p_off, seg_len, false); kunmap_atomic(vaddr); len -= seg_len; if (!len) break; } } if (full_pkt && skb_has_frag_list(skb)) { printk("skb fraglist:\n"); skb_walk_frags(skb, list_skb) skb_dump(level, list_skb, true); } } EXPORT_SYMBOL(skb_dump); /** * skb_tx_error - report an sk_buff xmit error * @skb: buffer that triggered an error * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. */ void skb_tx_error(struct sk_buff *skb) { if (skb) { skb_zcopy_downgrade_managed(skb); skb_zcopy_clear(skb, true); } } EXPORT_SYMBOL(skb_tx_error); #ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free * * Drop a ref to the buffer and free it if the usage count has hit zero * Functions identically to kfree_skb, but kfree_skb assumes that the frame * is being dropped after a failure and notes that */ void consume_skb(struct sk_buff *skb) { if (!skb_unref(skb)) return; trace_consume_skb(skb, __builtin_return_address(0)); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); #endif /** * __consume_stateless_skb - free an skbuff, assuming it is stateless * @skb: buffer to free * * Alike consume_skb(), but this variant assumes that this is the last * skb reference and all the head states have been already dropped */ void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb, __builtin_return_address(0)); skb_release_data(skb, SKB_CONSUMED); kfree_skbmem(skb); } static void napi_skb_cache_put(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; if (!kasan_mempool_poison_object(skb)) return; nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], kmem_cache_size(net_hotdata.skbuff_cache)); kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } } void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_all(skb, reason); napi_skb_cache_put(skb); } void napi_skb_free_stolen_head(struct sk_buff *skb) { if (unlikely(skb->slow_gro)) { nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); skb_orphan(skb); skb->slow_gro = 0; } napi_skb_cache_put(skb); } void napi_consume_skb(struct sk_buff *skb, int budget) { /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) { dev_consume_skb_any(skb); return; } DEBUG_NET_WARN_ON_ONCE(!in_softirq()); if (!skb_unref(skb)) return; /* if reaching here SKB is ready to free */ trace_consume_skb(skb, __builtin_return_address(0)); /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } skb_release_all(skb, SKB_CONSUMED); napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); /* Make sure a field is contained by headers group */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) != \ offsetof(struct sk_buff, headers.field)); \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; /* We do not copy old->sk */ new->dev = old->dev; memcpy(new->cb, old->cb, sizeof(old->cb)); skb_dst_copy(new, old); __skb_ext_copy(new, old); __nf_copy(new, old, false); /* Note : this field could be in the headers group. * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; memcpy(&new->headers, &old->headers, sizeof(new->headers)); CHECK_SKB_FIELD(protocol); CHECK_SKB_FIELD(csum); CHECK_SKB_FIELD(hash); CHECK_SKB_FIELD(priority); CHECK_SKB_FIELD(skb_iif); CHECK_SKB_FIELD(vlan_proto); CHECK_SKB_FIELD(vlan_tci); CHECK_SKB_FIELD(transport_header); CHECK_SKB_FIELD(network_header); CHECK_SKB_FIELD(mac_header); CHECK_SKB_FIELD(inner_protocol); CHECK_SKB_FIELD(inner_transport_header); CHECK_SKB_FIELD(inner_network_header); CHECK_SKB_FIELD(inner_mac_header); CHECK_SKB_FIELD(mark); #ifdef CONFIG_NETWORK_SECMARK CHECK_SKB_FIELD(secmark); #endif #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif CHECK_SKB_FIELD(alloc_cpu); #ifdef CONFIG_XPS CHECK_SKB_FIELD(sender_cpu); #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #endif } /* * You should not add any new code to this function. Add it to * __copy_skb_header above instead. */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { #define C(x) n->x = skb->x n->next = n->prev = NULL; n->sk = NULL; __copy_skb_header(n, skb); C(len); C(data_len); C(mac_len); n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; n->peeked = 0; C(pfmemalloc); C(pp_recycle); n->destructor = NULL; C(tail); C(end); C(head); C(head_frag); C(data); C(truesize); refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); skb->cloned = 1; return n; #undef C } /** * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg * @first: first sk_buff of the msg */ struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) { struct sk_buff *n; n = alloc_skb(0, GFP_ATOMIC); if (!n) return NULL; n->len = first->len; n->data_len = first->len; n->truesize = first->truesize; skb_shinfo(n)->frag_list = first; __copy_skb_header(n, first); n->destructor = NULL; return n; } EXPORT_SYMBOL_GPL(alloc_skb_for_msg); /** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents * * This is identical to skb_clone except that the target skb is * supplied by the user. * * The target skb is returned upon exit. */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { skb_release_all(dst, SKB_CONSUMED); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg, rlim; struct user_struct *user; if (capable(CAP_IPC_LOCK) || !size) return 0; rlim = rlimit(RLIMIT_MEMLOCK); if (rlim == RLIM_INFINITY) return 0; num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ max_pg = rlim >> PAGE_SHIFT; user = mmp->user ? : current_user(); old_pg = atomic_long_read(&user->locked_vm); do { new_pg = old_pg + num_pg; if (new_pg > max_pg) return -ENOBUFS; } while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg)); if (!mmp->user) { mmp->user = get_uid(user); mmp->num_pg = num_pg; } else { mmp->num_pg += num_pg; } return 0; } EXPORT_SYMBOL_GPL(mm_account_pinned_pages); void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info_msgzc *uarg; struct sk_buff *skb; WARN_ON_ONCE(!in_task()); skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); uarg = (void *)skb->cb; uarg->mmp.user = NULL; if (mm_account_pinned_pages(&uarg->mmp, size)) { kfree_skb(skb); return NULL; } uarg->ubuf.ops = &msg_zerocopy_ubuf_ops; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; uarg->ubuf.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; refcount_set(&uarg->ubuf.refcnt, 1); sock_hold(sk); return &uarg->ubuf; } static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg) { if (uarg) { struct ubuf_info_msgzc *uarg_zc; const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; /* there might be non MSG_ZEROCOPY users */ if (uarg->ops != &msg_zerocopy_ubuf_ops) return NULL; /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ if (!sock_owned_by_user(sk)) { WARN_ON_ONCE(1); return NULL; } uarg_zc = uarg_to_msgzc(uarg); bytelen = uarg_zc->bytelen + size; if (uarg_zc->len == USHRT_MAX - 1 || bytelen > byte_limit) { /* TCP can create new skb to attach new uarg */ if (sk->sk_type == SOCK_STREAM) goto new_alloc; return NULL; } next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg_zc->id + uarg_zc->len) == next) { if (mm_account_pinned_pages(&uarg_zc->mmp, size)) return NULL; uarg_zc->len++; uarg_zc->bytelen = bytelen; atomic_set(&sk->sk_zckey, ++next); /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) net_zcopy_get(uarg); return uarg; } } new_alloc: return msg_zerocopy_alloc(sk, size); } EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 old_lo, old_hi; u64 sum_len; old_lo = serr->ee.ee_info; old_hi = serr->ee.ee_data; sum_len = old_hi - old_lo + 1ULL + len; if (sum_len >= (1ULL << 32)) return false; if (lo != old_hi + 1) return false; serr->ee.ee_data += len; return true; } static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; bool is_zerocopy; u32 lo, hi; u16 len; mm_unaccount_pinned_pages(&uarg->mmp); /* if !len, there was only 1 call, and it was aborted * so do not queue a completion notification */ if (!uarg->len || sock_flag(sk, SOCK_DEAD)) goto release; len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = 0; serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; spin_lock_irqsave(&q->lock, flags); tail = skb_peek_tail(q); if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY || !skb_zerocopy_notify_extend(tail, lo, len)) { __skb_queue_tail(q, skb); skb = NULL; } spin_unlock_irqrestore(&q->lock, flags); sk_error_report(sk); release: consume_skb(skb); sock_put(sk); } static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg, bool success) { struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg); uarg_zc->zerocopy = uarg_zc->zerocopy & success; if (refcount_dec_and_test(&uarg->refcnt)) __msg_zerocopy_callback(uarg_zc); } void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { struct sock *sk = skb_from_uarg(uarg_to_msgzc(uarg))->sk; atomic_dec(&sk->sk_zckey); uarg_to_msgzc(uarg)->len--; if (have_uref) msg_zerocopy_complete(NULL, uarg, true); } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); const struct ubuf_info_ops msg_zerocopy_ubuf_ops = { .complete = msg_zerocopy_complete, }; EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) { struct ubuf_info *orig_uarg = skb_zcopy(skb); int err, orig_len = skb->len; if (uarg->ops->link_skb) { err = uarg->ops->link_skb(skb, uarg); if (err) return err; } else { /* An skb can only point to one uarg. This edge case happens * when TCP appends to an skb, but zerocopy_realloc triggered * a new alloc. */ if (orig_uarg && uarg != orig_uarg) return -EEXIST; } err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; /* Streams do not free skb on error. Reset to prev state. */ iov_iter_revert(&msg->msg_iter, skb->len - orig_len); skb->sk = sk; ___pskb_trim(skb, orig_len); skb->sk = save_sk; return err; } if (!uarg->ops->link_skb) skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); void __skb_zcopy_downgrade_managed(struct sk_buff *skb) { int i; skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); } EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed); static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { if (skb_zcopy(orig)) { if (skb_zcopy(nskb)) { /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ if (!gfp_mask) { WARN_ON_ONCE(1); return -ENOMEM; } if (skb_uarg(nskb) == skb_uarg(orig)) return 0; if (skb_copy_ubufs(nskb, GFP_ATOMIC)) return -EIO; } skb_zcopy_set(nskb, skb_uarg(orig), NULL); } return 0; } /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. * * Returns 0 on success or a negative error code on failure * to allocate kernel memory to copy to. */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, order, psize, new_frags; u32 d_off; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; if (!num_frags) goto release; /* We might have to allocate high order pages, so compute what minimum * page order is needed. */ order = 0; while ((PAGE_SIZE << order) * MAX_SKB_FRAGS < __skb_pagelen(skb)) order++; psize = (PAGE_SIZE << order); new_frags = (__skb_pagelen(skb) + psize - 1) >> (PAGE_SHIFT + order); for (i = 0; i < new_frags; i++) { page = alloc_pages(gfp_mask | __GFP_COMP, order); if (!page) { while (head) { struct page *next = (struct page *)page_private(head); put_page(head); head = next; } return -ENOMEM; } set_page_private(page, (unsigned long)head); head = page; } page = head; d_off = 0; for (i = 0; i < num_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); while (done < p_len) { if (d_off == psize) { d_off = 0; page = (struct page *)page_private(page); } copy = min_t(u32, psize - d_off, p_len - done); memcpy(page_address(page) + d_off, vaddr + p_off + done, copy); done += copy; d_off += copy; } kunmap_atomic(vaddr); } } /* skb frags release userspace buffers */ for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { __skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize); head = (struct page *)page_private(head); } __skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; release: skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority * * Duplicate an &sk_buff. The new one is not owned by a socket. Both * copies share the same packet data but not structure. The new * buffer has a reference count of 1. If the allocation fails the * function returns %NULL otherwise the new buffer is returned. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. */ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff_fclones *fclones = container_of(skb, struct sk_buff_fclones, skb1); struct sk_buff *n; if (skb_orphan_frags(skb, gfp_mask)) return NULL; if (skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) == 1) { n = &fclones->skb2; refcount_set(&fclones->fclone_ref, 2); n->fclone = SKB_FCLONE_CLONE; } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; n->fclone = SKB_FCLONE_UNAVAILABLE; } return __skb_clone(n, skb); } EXPORT_SYMBOL(skb_clone); void skb_headers_offset_update(struct sk_buff *skb, int off) { /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += off; /* {transport,network,mac}_header and tail are relative to skb->head */ skb->transport_header += off; skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; skb->inner_transport_header += off; skb->inner_network_header += off; skb->inner_mac_header += off; } EXPORT_SYMBOL(skb_headers_offset_update); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { if (skb_pfmemalloc(skb)) return SKB_ALLOC_RX; return 0; } /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data. This is used when the * caller wishes to modify the data and needs a private copy of the * data to alter. Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * As by-product this function converts non-linear &sk_buff to linear * one, so that &sk_buff becomes completely private and caller is allowed * to modify all the data of returned buffer. This means that this * function is not recommended for use in circumstances when only * header is going to be modified. Use pskb_copy() instead. */ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; unsigned int size; int headerlen; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; headerlen = skb_headroom(skb); size = skb_end_offset(skb) + skb->data_len; n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; /* Set the data pointer */ skb_reserve(n, headerlen); /* Set the tail pointer and length */ skb_put(n, skb->len); BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); /** * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy * @headroom: headroom of new skb * @gfp_mask: allocation priority * @fclone: if true allocate the copy of the skb from the fclone * cache instead of the head cache; it is recommended to set this * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when * the caller wishes to modify only header of &sk_buff and needs * private copy of the header to alter. Returns %NULL on failure * or the pointer to the buffer on success. * The returned buffer has a reference count of 1. */ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone) { unsigned int size = skb_headlen(skb) + headroom; int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ skb_copy_from_linear_data(skb, n->data, n->len); n->truesize += skb->data_len; n->data_len = skb->data_len; n->len = skb->len; if (skb_shinfo(skb)->nr_frags) { int i; if (skb_orphan_frags(skb, gfp_mask) || skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; } if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } skb_copy_header(n, skb); out: return n; } EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @nhead: room to add at head * @ntail: room to add at tail * @gfp_mask: allocation priority * * Expands (or creates identical copy, if @nhead and @ntail are zero) * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { unsigned int osize = skb_end_offset(skb); unsigned int size = osize + nhead + ntail; long off; u8 *data; int i; BUG_ON(nhead < 0); BUG_ON(skb_shared(skb)); skb_zcopy_downgrade_managed(skb); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. */ memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); /* * if shinfo is shared we must drop the old head gracefully, but if it * is not we can just drop the old head and let the existing refcount * be since all we did is relocate the values */ if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; if (skb_zcopy(skb)) refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb, SKB_CONSUMED); } else { skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; skb->head_frag = 0; skb->data += off; skb_set_end_offset(skb, size); #ifdef NET_SKBUFF_DATA_USES_OFFSET off = nhead; #endif skb->tail += off; skb_headers_offset_update(skb, nhead); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); skb_metadata_clear(skb); /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). */ if (!skb->sk || skb->destructor == sock_edemux) skb->truesize += size - osize; return 0; nofrags: skb_kfree_head(data, size); nodata: return -ENOMEM; } EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) { struct sk_buff *skb2; int delta = headroom - skb_headroom(skb); if (delta <= 0) skb2 = pskb_copy(skb, GFP_ATOMIC); else { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { kfree_skb(skb2); skb2 = NULL; } } return skb2; } EXPORT_SYMBOL(skb_realloc_headroom); /* Note: We plan to rework this in linux-6.4 */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { unsigned int saved_end_offset, saved_truesize; struct skb_shared_info *shinfo; int res; saved_end_offset = skb_end_offset(skb); saved_truesize = skb->truesize; res = pskb_expand_head(skb, 0, 0, pri); if (res) return res; skb->truesize = saved_truesize; if (likely(skb_end_offset(skb) == saved_end_offset)) return 0; /* We can not change skb->end if the original or new value * is SKB_SMALL_HEAD_HEADROOM, as it might break skb_kfree_head(). */ if (saved_end_offset == SKB_SMALL_HEAD_HEADROOM || skb_end_offset(skb) == SKB_SMALL_HEAD_HEADROOM) { /* We think this path should not be taken. * Add a temporary trace to warn us just in case. */ pr_err_once("__skb_unclone_keeptruesize() skb_end_offset() %u -> %u\n", saved_end_offset, skb_end_offset(skb)); WARN_ON_ONCE(1); return 0; } shinfo = skb_shinfo(skb); /* We are about to change back skb->end, * we need to move skb_shinfo() to its new location. */ memmove(skb->head + saved_end_offset, shinfo, offsetof(struct skb_shared_info, frags[shinfo->nr_frags])); skb_set_end_offset(skb, saved_end_offset); return 0; } /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @headroom: needed headroom * * Unlike skb_realloc_headroom, this one does not allocate a new skb * if possible; copies skb->sk to new skb as needed * and frees original skb in case of failures. * * It expect increased headroom and generates warning otherwise. */ struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); int osize = skb_end_offset(skb); struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; delta = SKB_DATA_ALIGN(delta); /* pskb_expand_head() might crash, if skb is shared. */ if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) goto fail; if (sk) skb_set_owner_w(nskb, sk); consume_skb(skb); skb = nskb; } if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) goto fail; if (sk && is_skb_wmem(skb)) { delta = skb_end_offset(skb) - osize; refcount_add(delta, &sk->sk_wmem_alloc); skb->truesize += delta; } return skb; fail: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_expand_head); /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head * @newtailroom: new free bytes at tail * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data and while doing so * allocate additional space. * * This is used when the caller wishes to modify the data and needs a * private copy of the data to alter as well as more space for new fields. * Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask) { /* * Allocate the copy buffer */ int head_copy_len, head_copy_off; struct sk_buff *n; int oldheadroom; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; oldheadroom = skb_headroom(skb); n = __alloc_skb(newheadroom + skb->len + newtailroom, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; skb_reserve(n, newheadroom); /* Set the tail pointer and length */ skb_put(n, skb->len); head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; else head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); return n; } EXPORT_SYMBOL(skb_copy_expand); /** * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error * if @free_on_error is true. */ int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { int err; int ntail; /* If the skbuff is non linear tailroom is always zero.. */ if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); return 0; } ntail = skb->data_len + pad - (skb->end - skb->tail); if (likely(skb_cloned(skb) || ntail > 0)) { err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); if (unlikely(err)) goto free_skb; } /* FIXME: The use of this function with non-linear skb's really needs * to be audited. */ err = skb_linearize(skb); if (unlikely(err)) goto free_skb; memset(skb->data + skb->len, 0, pad); return 0; free_skb: if (free_on_error) kfree_skb(skb); return err; } EXPORT_SYMBOL(__skb_pad); /** * pskb_put - add data to the tail of a potentially fragmented buffer * @skb: start of the buffer to use * @tail: tail fragment of the buffer to use * @len: amount of data to add * * This function extends the used data area of the potentially * fragmented buffer. @tail must be the last fragment of @skb -- or * @skb itself. If this would exceed the total buffer size the kernel * will panic. A pointer to the first byte of the extra data is * returned. */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { if (tail != skb) { skb->data_len += len; skb->len += len; } return skb_put(tail, len); } EXPORT_SYMBOL_GPL(pskb_put); /** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer. If this would * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ void *skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; if (unlikely(skb->tail > skb->end)) skb_over_panic(skb, len, __builtin_return_address(0)); return tmp; } EXPORT_SYMBOL(skb_put); /** * skb_push - add data to the start of a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer at the buffer * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; if (unlikely(skb->data < skb->head)) skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data; } EXPORT_SYMBOL(skb_push); /** * skb_pull - remove data from the start of a buffer * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the next data in the buffer * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ void *skb_pull(struct sk_buff *skb, unsigned int len) { return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); /** * skb_pull_data - remove data from the start of a buffer returning its * original position. * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the original data in the buffer * is returned after checking if there is enough data to pull. Once the * data has been pulled future pushes will overwrite the old data. */ void *skb_pull_data(struct sk_buff *skb, size_t len) { void *data = skb->data; if (skb->len < len) return NULL; skb_pull(skb, len); return data; } EXPORT_SYMBOL(skb_pull_data); /** * skb_trim - remove end from a buffer * @skb: buffer to alter * @len: new length * * Cut the length of a buffer down by removing data from the tail. If * the buffer is already under the length specified it is not modified. * The skb must be linear. */ void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) __skb_trim(skb, len); } EXPORT_SYMBOL(skb_trim); /* Trims skb to length len. It can change skb pointers. */ int ___pskb_trim(struct sk_buff *skb, unsigned int len) { struct sk_buff **fragp; struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; int err; if (skb_cloned(skb) && unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) return err; i = 0; if (offset >= len) goto drop_pages; for (; i < nfrags; i++) { int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); goto done; } for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); fragp = &frag->next) { int end = offset + frag->len; if (skb_shared(frag)) { struct sk_buff *nfrag; nfrag = skb_clone(frag, GFP_ATOMIC); if (unlikely(!nfrag)) return -ENOMEM; nfrag->next = frag->next; consume_skb(frag); frag = nfrag; *fragp = frag; } if (end < len) { offset = end; continue; } if (end > len && unlikely((err = pskb_trim(frag, len - offset)))) return err; if (frag->next) skb_drop_list(&frag->next); break; } done: if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { skb->len = len; skb->data_len = 0; skb_set_tail_pointer(skb, len); } if (!skb->sk || skb->destructor == sock_edemux) skb_condense(skb); return 0; } EXPORT_SYMBOL(___pskb_trim); /* Note : use pskb_trim_rcsum() instead of calling this directly */ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len; skb->csum = csum_block_sub(skb->csum, skb_checksum(skb, len, delta, 0), len); } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len; int offset = skb_checksum_start_offset(skb) + skb->csum_offset; if (offset + sizeof(__sum16) > hdlen) return -EINVAL; } return __pskb_trim(skb, len); } EXPORT_SYMBOL(pskb_trim_rcsum_slow); /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate * @delta: number of bytes to advance tail * * The function makes a sense only on a fragmented &sk_buff, * it expands header moving its tail forward and copying necessary * data from fragmented part. * * &sk_buff MUST have reference count of 1. * * Returns %NULL (and &sk_buff does not change) if pull failed * or value of new tail of skb in the case of success. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ /* Moves tail of skb head forward, copying data from fragmented part, * when it is necessary. * 1. It may fail due to malloc failure. * 2. It may change skb pointers. * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ void *__pskb_pull_tail(struct sk_buff *skb, int delta) { /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough * room at tail, reallocate without expansion only if skb is cloned. */ int i, k, eat = (skb->tail + delta) - skb->end; if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) return NULL; } BUG_ON(skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size >= eat) goto pull_pages; eat -= size; } /* If we need update frag list, we are in troubles. * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. * Pure masohism, indeed. 8)8) */ if (eat) { struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_is_gso(skb) && !list->head_frag && skb_headlen(list)) skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ clone = skb_clone(list, GFP_ATOMIC); if (!clone) return NULL; insp = list->next; list = clone; } else { /* This may be pulled without * problems. */ insp = list; } if (!pskb_pull(list, eat)) { kfree_skb(clone); return NULL; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; skb_shinfo(skb)->frag_list = clone; } } /* Success! Now we may commit changes to skb data. */ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; *frag = skb_shinfo(skb)->frags[i]; if (eat) { skb_frag_off_add(frag, eat); skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; } k++; } } skb_shinfo(skb)->nr_frags = k; end: skb->tail += delta; skb->data_len -= delta; if (!skb->data_len) skb_zcopy_clear(skb, false); return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); /** * skb_copy_bits - copy bits from skb to kernel buffer * @skb: source skb * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source skb to the * destination buffer. * * CAUTION ! : * If its prototype is ever changed, * check arch/{*}/net/{*}.S files, * since it is called from BPF assembly code. */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; /* Copy header. */ if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; to += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(f, skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_copy_bits(frag_iter, offset - start, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_copy_bits); /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { put_page(spd->pages[i]); } static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) return NULL; *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); memcpy(page_address(pfrag->page) + pfrag->offset, page_address(page) + *offset, *len); *offset = pfrag->offset; pfrag->offset += *len; return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, struct page *page, unsigned int offset) { return spd->nr_pages && spd->pages[spd->nr_pages - 1] == page && (spd->partial[spd->nr_pages - 1].offset + spd->partial[spd->nr_pages - 1].len == offset); } /* * Fill page/offset/length into spd, if it can hold more pages. */ static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { page = linear_to_page(page, len, &offset, sk); if (!page) return true; } if (spd_can_coalesce(spd, page, offset)) { spd->partial[spd->nr_pages - 1].len += *len; return false; } get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; return false; } static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) { if (!*len) return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; return false; } /* ignore any bits we already processed */ poff += *off; plen -= *off; *off = 0; do { unsigned int flen = min(*len, plen); if (spd_fill_page(spd, pipe, page, &flen, poff, linear, sk)) return true; poff += flen; plen -= flen; *len -= flen; } while (*len && plen); return false; } /* * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsigned int *offset, unsigned int *len, struct splice_pipe_desc *spd, struct sock *sk) { int seg; struct sk_buff *iter; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a * fragment, and if the head is not shared with any clones then * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; /* * then map the fragments */ for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) return true; } skb_walk_frags(skb, iter) { if (*offset >= iter->len) { *offset -= iter->len; continue; } /* __skb_splice_bits() only fails if the output has no room * left, so no point in going over the frag_list for the error * case. */ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) return true; } return false; } /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; int ret = 0; __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); if (spd.nr_pages) ret = splice_to_pipe(pipe, &spd); return ret; } EXPORT_SYMBOL_GPL(skb_splice_bits); static int sendmsg_locked(struct sock *sk, struct msghdr *msg) { struct socket *sock = sk->sk_socket; size_t size = msg_data_left(msg); if (!sock) return -EINVAL; if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); return sock->ops->sendmsg_locked(sk, msg, size); } static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg) { struct socket *sock = sk->sk_socket; if (!sock) return -EINVAL; return sock_sendmsg(sock, msg); } typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg); static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len, sendmsg_func sendmsg) { unsigned int orig_len = len; struct sk_buff *head = skb; unsigned short fragidx; int slen, ret; do_frag_list: /* Deal with head data */ while (offset < skb_headlen(skb) && len) { struct kvec kv; struct msghdr msg; slen = min_t(int, len, skb_headlen(skb) - offset); kv.iov_base = skb->data + offset; kv.iov_len = slen; memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT; iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen); ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked, sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error; offset += ret; len -= ret; } /* All the data was skb head? */ if (!len) goto out; /* Make offset relative to start of frags */ offset -= skb_headlen(skb); /* Find where we are in frag list */ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; if (offset < skb_frag_size(frag)) break; offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { struct bio_vec bvec; struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT, }; bvec_set_page(&bvec, skb_frag_page(frag), slen, skb_frag_off(frag) + offset); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, slen); ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked, sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error; len -= ret; offset += ret; slen -= ret; } offset = 0; } if (len) { /* Process any frag lists */ if (skb == head) { if (skb_has_frag_list(skb)) { skb = skb_shinfo(skb)->frag_list; goto do_frag_list; } } else if (skb->next) { skb = skb->next; goto do_frag_list; } } out: return orig_len - len; error: return orig_len == len ? ret : orig_len - len; } /* Send skb data on a socket. Socket must be locked. */ int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_locked); } EXPORT_SYMBOL_GPL(skb_send_sock_locked); /* Send skb data on a socket. Socket must be unlocked. */ int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked); } /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer * @offset: offset in destination * @from: source buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source buffer to the * destination skb. This function handles all the messy bits of * traversing fragment lists and such. */ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; from += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_store_bits(frag_iter, offset - start, from, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum, const struct skb_checksum_ops *ops) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ if (copy > 0) { if (copy > len) copy = len; csum = INDIRECT_CALL_1(ops->update, csum_partial_ext, skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; pos = copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = INDIRECT_CALL_1(ops->update, csum_partial_ext, vaddr + p_off, p_len, 0); kunmap_atomic(vaddr); csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, csum, csum2, pos, p_len); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { __wsum csum2; if (copy > len) copy = len; csum2 = __skb_checksum(frag_iter, offset - start, copy, 0, ops); csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, csum, csum2, pos, copy); if ((len -= copy) == 0) return csum; offset += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(__skb_checksum); __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { const struct skb_checksum_ops ops = { .update = csum_partial_ext, .combine = csum_block_add_ext, }; return __skb_checksum(skb, offset, len, csum, &ops); } EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; __wsum csum = 0; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial_copy_nocheck(skb->data + offset, to, copy); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos = copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, to + copied, p_len); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { __wsum csum2; int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; csum2 = skb_copy_and_csum_bits(frag_iter, offset - start, to, copy); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_copy_and_csum_bits); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { __sum16 sum; sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) skb->csum_valid = !sum; return sum; } EXPORT_SYMBOL(__skb_checksum_complete_head); /* This function assumes skb->csum already holds pseudo header's checksum, * which has been changed from the hardware checksum, for example, by * __skb_checksum_validate_complete(). And, the original skb->csum must * have been validated unsuccessfully for CHECKSUM_COMPLETE case. * * It returns non-zero if the recomputed checksum is still invalid, otherwise * zero. The new checksum is stored back into skb->csum unless the skb is * shared. */ __sum16 __skb_checksum_complete(struct sk_buff *skb) { __wsum csum; __sum16 sum; csum = skb_checksum(skb, 0, skb->len, 0); sum = csum_fold(csum_add(skb->csum, csum)); /* This check is inverted, because we already knew the hardware * checksum is invalid before calling this function. So, if the * re-computed checksum is valid instead, then we have a mismatch * between the original skb->csum and skb_checksum(). This means either * the original hardware checksum is incorrect or we screw up skb->csum * when moving skb->data around. */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) { /* Save full packet checksum */ skb->csum = csum; skb->ip_summed = CHECKSUM_COMPLETE; skb->csum_complete_sw = 1; skb->csum_valid = !sum; } return sum; } EXPORT_SYMBOL(__skb_checksum_complete); static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum) { net_warn_ratelimited( "%s: attempt to compute crc32c without libcrc32c.ko\n", __func__); return 0; } static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2, int offset, int len) { net_warn_ratelimited( "%s: attempt to compute crc32c without libcrc32c.ko\n", __func__); return 0; } static const struct skb_checksum_ops default_crc32c_ops = { .update = warn_crc32c_csum_update, .combine = warn_crc32c_csum_combine, }; const struct skb_checksum_ops *crc32c_csum_stub __read_mostly = &default_crc32c_ops; EXPORT_SYMBOL(crc32c_csum_stub); /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer * * Calculates the amount of linear headroom needed in the 'to' skb passed * into skb_zerocopy(). */ unsigned int skb_zerocopy_headlen(const struct sk_buff *from) { unsigned int hlen = 0; if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); if (!hlen) hlen = from->len; } if (skb_has_frag_list(from)) hlen = from->len; return hlen; } EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); /** * skb_zerocopy - Zero copy skb to skb * @to: destination buffer * @from: source buffer * @len: number of bytes to copy from source buffer * @hlen: size of linear headroom in destination buffer * * Copies up to `len` bytes from `from` to `to` by creating references * to the frags in the source buffer. * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. * * Return value: * 0: everything is OK * -ENOMEM: couldn't orphan frags of @from due to lack of memory * -EFAULT: skb_copy_bits() found some problem with skb geometry */ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); /* dont bother with small payloads */ if (len <= skb_tailroom(to)) return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); if (unlikely(ret)) return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); __skb_fill_netmem_desc(to, 0, page_to_netmem(page), offset, plen); get_page(page); j = 1; len -= plen; } } skb_len_add(to, len + plen); if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { skb_tx_error(from); return -ENOMEM; } skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { int size; if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), len); skb_frag_size_set(&skb_shinfo(to)->frags[j], size); len -= size; skb_frag_ref(to, j); j++; } skb_shinfo(to)->nr_frags = j; return 0; } EXPORT_SYMBOL_GPL(skb_zerocopy); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart); if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum_offset; *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The head item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. The list lock is taken so the function * may be used safely with other locking list functions. The tail item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue_tail(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff_head tmp; unsigned long flags; if (skb_queue_empty_lockless(list)) return; __skb_queue_head_init(&tmp); spin_lock_irqsave(&list->lock, flags); skb_queue_splice_init(list, &tmp); spin_unlock_irqrestore(&list->lock, flags); __skb_queue_purge_reason(&tmp, reason); } EXPORT_SYMBOL(skb_queue_purge_reason); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); sum += skb->truesize; kfree_skb(skb); } return sum; } void skb_errqueue_purge(struct sk_buff_head *list) { struct sk_buff *skb, *next; struct sk_buff_head kill; unsigned long flags; __skb_queue_head_init(&kill); spin_lock_irqsave(&list->lock, flags); skb_queue_walk_safe(list, skb, next) { if (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) continue; __skb_unlink(skb, list); __skb_queue_tail(&kill, skb); } spin_unlock_irqrestore(&list->lock, flags); __skb_queue_purge(&kill); } EXPORT_SYMBOL(skb_errqueue_purge); /** * skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the tail of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * @list: list to use * * Remove a packet from a list. The list locks are taken and this * function is atomic with respect to other list locked calls * * You must know what list the SKB is on. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * @list: list to use * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls. * A buffer cannot be placed on two lists at the same time. */ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_append); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { int i; skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, int pos) { int i, k = 0; const int nfrags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->len = skb1->data_len = skb->len - len; skb->len = len; skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < len) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; } else skb_shinfo(skb)->nr_frags++; pos += size; } skb_shinfo(skb1)->nr_frags = k; } /** * skb_split - Split fragmented skb to two parts at length len. * @skb: the buffer to split * @skb1: the buffer to receive the second part * @len: new length for skb */ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; skb_zcopy_downgrade_managed(skb); skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } EXPORT_SYMBOL(skb_split); /* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here! */ static int skb_prepare_for_shift(struct sk_buff *skb) { return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** * skb_shift - Shifts paged data partially from skb to another * @tgt: buffer into which tail data gets added * @skb: buffer from which the paged data comes from * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. * * Skb cannot include anything else but paged data while tgt is allowed * to have non-paged data as well. * * TODO: full sized shift could be optimized but that would need * specialized skb free'er to handle frags without up-to-date nr_frags. */ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); if (skb_headlen(skb)) return 0; if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0; todo = shiftlen; from = 0; to = skb_shinfo(tgt)->nr_frags; fragfrom = &skb_shinfo(skb)->frags[from]; /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ if (!to || !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; /* All previous frag pointers might be stale! */ fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } from++; } /* Skip full, not-fitting skb to avoid expensive operations */ if ((shiftlen == skb->len) && (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) return 0; if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { if (to == MAX_SKB_FRAGS) return 0; fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; todo -= skb_frag_size(fragfrom); from++; to++; } else { __skb_frag_ref(fragfrom); skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; to++; break; } } /* Ready to "commit" this state change to tgt */ skb_shinfo(tgt)->nr_frags = to; if (merge >= 0) { fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ to = 0; while (from < skb_shinfo(skb)->nr_frags) skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; skb_shinfo(skb)->nr_frags = to; BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); onlymerged: /* Most likely the tgt won't ever need its checksum anymore, skb on * the other hand might need it if it needs to be resent */ tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; skb_len_add(skb, -shiftlen); skb_len_add(tgt, shiftlen); return shiftlen; } /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read * @from: lower offset of data to be read * @to: upper offset of data to be read * @st: state variable * * Initializes the specified state variable. Must be called before * invoking skb_seq_read() for the first time. */ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st) { st->lower_offset = from; st->upper_offset = to; st->root_skb = st->cur_skb = skb; st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; st->frag_off = 0; } EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data * @consumed: number of bytes consumed by the caller so far * @data: destination pointer for data to be returned * @st: state variable * * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st) { unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; if (unlikely(abs_offset >= st->upper_offset)) { if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } return 0; } next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; if (abs_offset < block_limit && !st->frag_data) { *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { unsigned int pg_idx, pg_off, pg_sz; frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; pg_idx = 0; pg_off = skb_frag_off(frag); pg_sz = skb_frag_size(frag); if (skb_frag_must_loop(skb_frag_page(frag))) { pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT; pg_off = offset_in_page(pg_off + st->frag_off); pg_sz = min_t(unsigned int, pg_sz - st->frag_off, PAGE_SIZE - pg_off); } block_limit = pg_sz + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx); *data = (u8 *)st->frag_data + pg_off + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->stepped_offset += pg_sz; st->frag_off += pg_sz; if (st->frag_off == skb_frag_size(frag)) { st->frag_off = 0; st->frag_idx++; } } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; } else if (st->cur_skb->next) { st->cur_skb = st->cur_skb->next; st->frag_idx = 0; goto next_skb; } return 0; } EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data * @st: state variable * * Must be called if skb_seq_read() was not called until it * returned 0. */ void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, struct ts_config *conf, struct ts_state *state) { return skb_seq_read(offset, text, TS_SKB_CB(state)); } static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) { skb_abort_seq_read(TS_SKB_CB(state)); } /** * skb_find_text - Find a text pattern in skb data * @skb: the buffer to look in * @from: search offset * @to: search limit * @config: textsearch configuration * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve * subsequent occurrences of the pattern. Returns the offset * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { unsigned int patlen = config->ops->get_pattern_len(config); struct ts_state state; unsigned int ret; BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb)); config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); return (ret + patlen <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags) { int i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < max_frags) { skb_zcopy_downgrade_managed(skb); get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, size); } else { return -EMSGSIZE; } return 0; } EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_pull on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_pull unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { unsigned char *data = skb->data; BUG_ON(len > skb->len); __skb_pull(skb, len); skb_postpull_rcsum(skb, data, len); return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) { skb_frag_t head_frag; struct page *page; page = virt_to_head_page(frag_skb->head); skb_frag_fill_page_desc(&head_frag, page, frag_skb->data - (unsigned char *)page_address(page), skb_headlen(frag_skb)); return head_frag; } struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset) { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_truesize = 0; unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int len_diff, err; skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ err = skb_unclone(skb, GFP_ATOMIC); if (err) goto err_linearize; skb_shinfo(skb)->frag_list = NULL; while (list_skb) { nskb = list_skb; list_skb = list_skb->next; err = 0; delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { consume_skb(nskb); nskb = tmp; err = skb_unclone(nskb, GFP_ATOMIC); } else { err = -ENOMEM; } } if (!tail) skb->next = nskb; else tail->next = nskb; if (unlikely(err)) { nskb->next = list_skb; goto err_linearize; } tail = nskb; delta_len += nskb->len; skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; skb_gso_reset(skb); skb->prev = tail; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto err_linearize; skb_get(skb); return skb; err_linearize: kfree_skb_list(skb->next); skb->next = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(skb_segment_list); /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ struct sk_buff *skb_segment(struct sk_buff *head_skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; struct sk_buff *frag_skb; skb_frag_t *frag; __be16 proto; bool csum, sg; int err = -ENOMEM; int i = 0; int nfrags, pos; if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { struct sk_buff *check_skb; for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { if (skb_headlen(check_skb) && !check_skb->head_frag) { /* gso_size is untrusted, and we have a frag_list with * a linear non head_frag item. * * If head_skb's headlen does not fit requested gso_size, * it means that the frag_list members do NOT terminate * on exact gso_size boundaries. Hence we cannot perform * skb_frag_t page sharing. Therefore we must fallback to * copying the frag_list skbs; we do so by disabling SG. */ features &= ~NETIF_F_SG; break; } } } __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL); sg = !!(features & NETIF_F_SG); csum = !!can_checksum_protocol(features, proto); if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; /* If we get here then all the required * GSO features except frag_list are supported. * Try to split the SKB to multiple GSO SKBs * with no frag_list. * Currently we can do that only when the buffers don't * have a linear part and all the buffers except * the last are of the same length. */ frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { if (frag_len != iter->len && iter->next) goto normal; if (skb_headlen(iter) && !iter->head_frag) goto normal; len -= iter->len; } if (len != frag_len) goto normal; } /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. * Cap len to not accidentally hit GSO_BY_FRAGS. */ partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1) mss *= partial_segs; else partial_segs = 0; } normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); if (skb_orphan_frags(head_skb, GFP_ATOMIC)) return ERR_PTR(-ENOMEM); nfrags = skb_shinfo(head_skb)->nr_frags; frag = skb_shinfo(head_skb)->frags; frag_skb = head_skb; do { struct sk_buff *nskb; skb_frag_t *nskb_frag; int hsize; int size; if (unlikely(mss == GSO_BY_FRAGS)) { len = list_skb->len; } else { len = head_skb->len - offset; if (len > mss) len = mss; } hsize = skb_headlen(head_skb) - offset; if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); nskb = skb_clone(list_skb, GFP_ATOMIC); if (unlikely(!nskb)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; frag++; } list_skb = list_skb->next; if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; } hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) goto err; skb_reserve(nskb, headroom); __skb_put(nskb, doffset); } if (segs) tail->next = nskb; else segs = nskb; tail = nskb; __copy_skb_header(nskb, head_skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { if (!csum) { if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) goto err; } continue; } nskb_frag = skb_shinfo(nskb)->frags; skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & SKBFL_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { if (skb_orphan_frags(list_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, list_skb, GFP_ATOMIC)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { BUG_ON(!list_skb->head_frag); /* to make room for head_frag. */ i--; frag--; } list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS)) { net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); err = -EINVAL; goto err; } *nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag; __skb_frag_ref(nskb_frag); size = skb_frag_size(nskb_frag); if (pos < offset) { skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; frag++; pos += size; } else { skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } nskb_frag++; } skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; perform_csum_check: if (!csum) { if (skb_has_shared_frag(nskb) && __skb_linearize(nskb)) goto err; if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); /* Some callers want to get the end of the list. * Put it in segs->prev to avoid walking the list. * (see validate_xmit_skb_list() for example) */ segs->prev = tail; if (partial_segs) { struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; unsigned short gso_size = skb_shinfo(head_skb)->gso_size; /* Update type to add partial and then remove dodgy if set */ type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL; type &= ~SKB_GSO_DODGY; /* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols. */ for (iter = segs; iter; iter = iter->next) { skb_shinfo(iter)->gso_size = gso_size; skb_shinfo(iter)->gso_segs = partial_segs; skb_shinfo(iter)->gso_type = type; SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset; } if (tail->len - doffset <= gso_size) skb_shinfo(tail)->gso_size = 0; else if (tail != segs) skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size); } /* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment. */ if (head_skb->destructor == sock_wfree) { swap(tail->truesize, head_skb->truesize); swap(tail->destructor, head_skb->destructor); swap(tail->sk, head_skb->sk); } return segs; err: kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info), #endif #ifdef CONFIG_XFRM [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path), #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) [SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow), #endif }; static __always_inline unsigned int skb_ext_total_length(void) { unsigned int l = SKB_EXT_CHUNKSIZEOF(struct skb_ext); int i; for (i = 0; i < ARRAY_SIZE(skb_ext_type_len); i++) l += skb_ext_type_len[i]; return l; } static void skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM >= 8); #if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL) BUILD_BUG_ON(skb_ext_total_length() > 255); #endif skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } #else static void skb_extensions_init(void) {} #endif /* The SKB kmem_cache slab is critical for network performance. Never * merge/alias the slab with similar sized objects. This avoids fragmentation * that hurts performance of kmem_cache_{alloc,free}_bulk APIs. */ #ifndef CONFIG_SLUB_TINY #define FLAG_SKB_NO_MERGE SLAB_NO_MERGE #else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */ #define FLAG_SKB_NO_MERGE 0 #endif void __init skb_init(void) { net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| FLAG_SKB_NO_MERGE, offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, 0, SKB_SMALL_HEAD_HEADROOM, NULL); skb_extensions_init(); } static int __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsigned int recursion_level) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0; if (unlikely(recursion_level >= 24)) return -EMSGSIZE; if (copy > 0) { if (copy > len) copy = len; sg_set_buf(sg, skb->data + offset, copy); elt++; if ((len -= copy) == 0) return elt; offset += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end, ret; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start, copy, recursion_level + 1); if (unlikely(ret < 0)) return ret; elt += ret; if ((len -= copy) == 0) return elt; offset += copy; } start = end; } BUG_ON(len); return elt; } /** * skb_to_sgvec - Fill a scatter-gather list from a socket buffer * @skb: Socket buffer containing the buffers to be mapped * @sg: The scatter-gather list to map into * @offset: The offset into the buffer's contents to start mapping * @len: Length of buffer space to be mapped * * Fill the specified scatter-gather list with mappings/pointers into a * region of the buffer space attached to a socket buffer. Returns either * the number of scatterlist items used, or -EMSGSIZE if the contents * could not fit. */ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len, 0); if (nsg <= 0) return nsg; sg_mark_end(&sg[nsg - 1]); return nsg; } EXPORT_SYMBOL_GPL(skb_to_sgvec); /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after * the first call without calling sg_unmark_end to expend sg list. * * Scenario to use skb_to_sgvec_nomark: * 1. sg_init_table * 2. skb_to_sgvec_nomark(payload1) * 3. skb_to_sgvec_nomark(payload2) * * This is equivalent to: * 1. sg_init_table * 2. skb_to_sgvec(payload1) * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * * When mapping mutilple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { return __skb_to_sgvec(skb, sg, offset, len, 0); } EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); /** * skb_cow_data - Check that a socket buffer's data buffers are writable * @skb: The socket buffer to check. * @tailbits: Amount of trailing space to be added * @trailer: Returned pointer to the skb where the @tailbits space begins * * Make sure that the data buffers attached to a socket buffer are * writable. If they are not, private copies are made of the data buffers * and the socket buffer is set to use these instead. * * If @tailbits is given, make sure that there is space to write @tailbits * bytes of data beyond current end of socket buffer. @trailer will be * set to point to the skb in which this space begins. * * The number of scatterlist elements required to completely map the * COW'd and extended socket buffer will be returned. */ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) { int copyflag; int elt; struct sk_buff *skb1, **skb_p; /* If skb is cloned or its head is paged, reallocate * head pulling out all the pages (pages are considered not writable * at the moment even if they are anonymous). */ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && !__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM; /* Easy case. Most of packets will go this way. */ if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more * space, 128 bytes is fair. */ if (skb_tailroom(skb) < tailbits && pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) return -ENOMEM; /* Voila! */ *trailer = skb; return 1; } /* Misery. We are in troubles, going to mincer fragments... */ elt = 1; skb_p = &skb_shinfo(skb)->frag_list; copyflag = 0; while ((skb1 = *skb_p) != NULL) { int ntail = 0; /* The fragment is partially pulled by someone, * this can happen on input. Copy it and everything * after it. */ if (skb_shared(skb1)) copyflag = 1; /* If the skb is the last, worry about trailer. */ if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } if (copyflag || skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ if (ntail == 0) skb2 = skb_copy(skb1, GFP_ATOMIC); else skb2 = skb_copy_expand(skb1, skb_headroom(skb1), ntail, GFP_ATOMIC); if (unlikely(skb2 == NULL)) return -ENOMEM; if (skb1->sk) skb_set_owner_w(skb2, skb1->sk); /* Looking around. Are we still alive? * OK, link new skb, drop old one */ skb2->next = skb1->next; *skb_p = skb2; kfree_skb(skb1); skb1 = skb2; } elt++; *trailer = skb1; skb_p = &skb1->next; } return elt; } EXPORT_SYMBOL_GPL(skb_cow_data); static void sock_rmem_free(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); } static void skb_set_err_queue(struct sk_buff *skb) { /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING. * So, it is safe to (mis)use it to mark skbs on the error queue. */ skb->pkt_type = PACKET_OUTGOING; BUILD_BUG_ON(PACKET_OUTGOING == 0); } /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); skb_set_err_queue(skb); /* before exiting rcu section, make sure dst is refcounted */ skb_dst_force(skb); skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); static bool is_icmp_err_skb(const struct sk_buff *skb) { return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6); } struct sk_buff *sock_dequeue_err_skb(struct sock *sk) { struct sk_buff_head *q = &sk->sk_error_queue; struct sk_buff *skb, *skb_next = NULL; bool icmp_next = false; unsigned long flags; if (skb_queue_empty_lockless(q)) return NULL; spin_lock_irqsave(&q->lock, flags); skb = __skb_dequeue(q); if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); if (is_icmp_err_skb(skb) && !icmp_next) sk->sk_err = 0; if (skb_next) sk_error_report(sk); return skb; } EXPORT_SYMBOL(sock_dequeue_err_skb); /** * skb_clone_sk - create clone of skb, and take reference to socket * @skb: the skb to clone * * This function creates a clone of a buffer that holds a reference on * sk_refcnt. Buffers created via this function are meant to be * returned using sock_queue_err_skb, or free via kfree_skb. * * When passing buffers allocated with this function to sock_queue_err_skb * it is necessary to wrap the call with sock_hold/sock_put in order to * prevent the socket from being released prior to being enqueued on * the sk_error_queue. */ struct sk_buff *skb_clone_sk(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sk_buff *clone; if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) { sock_put(sk); return NULL; } clone->sk = sk; clone->destructor = sock_efree; return clone; } EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, int tstype, bool opt_stats) { struct sock_exterr_skb *serr; int err; BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) serr->ee.ee_data -= atomic_read(&sk->sk_tskey); } err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); } static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); ret = sk->sk_socket && sk->sk_socket->file && file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW); read_unlock_bh(&sk->sk_callback_lock); return ret; } void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); return; } err: kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { struct sk_buff *skb; bool tsonly, opt_stats = false; u32 tsflags; if (!sk) return; tsflags = READ_ONCE(sk->sk_tsflags); if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk_is_tcp(sk)) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); opt_stats = true; } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { kfree_skb(skb); return; } } if (!skb) return; if (tsonly) { skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags & SKBTX_ANY_TSTAMP; skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; } if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; else __net_timestamp(skb); __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); #ifdef CONFIG_WIRELESS void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } if (err) kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); #endif /* CONFIG_WIRELESS */ /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set * @start: the number of bytes after skb->data to start checksumming. * @off: the offset from start to place the checksum. * * For untrusted partially-checksummed packets, we need to make sure the values * for skb->csum_start and skb->csum_offset are valid so we don't oops. * * This function checks and sets those values and skb->ip_summed: if this * returns false you should drop the packet. */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); u32 csum_start = skb_headroom(skb) + (u32)start; if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) { net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = csum_start; skb->csum_offset = off; skb->transport_header = csum_start; return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, unsigned int max) { if (skb_headlen(skb) >= len) return 0; /* If we need to pullup then pullup to the max, so we * won't need to do it again. */ if (max > skb->len) max = skb->len; if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) return -ENOMEM; if (skb_headlen(skb) < len) return -EPROTO; return 0; } #define MAX_TCP_HDR_LEN (15 * 4) static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { int err; switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; case IPPROTO_UDP: err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), off + sizeof(struct udphdr)); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct udphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &udp_hdr(skb)->check; } return ERR_PTR(-EPROTO); } /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; __sum16 *csum; int err; fragment = false; err = skb_maybe_pull_tail(skb, sizeof(struct iphdr), MAX_IP_HDR_LEN); if (err < 0) goto out; if (ip_is_fragment(ip_hdr(skb))) fragment = true; off = ip_hdrlen(skb); err = -EPROTO; if (fragment) goto out; csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - off, ip_hdr(skb)->protocol, 0); err = 0; out: return err; } /* This value should be large enough to cover a tagged ethernet header plus * an IPv6 header, all options, and a maximal TCP or UDP header. */ #define MAX_IPV6_HDR_LEN 256 #define OPT_HDR(type, skb, off) \ (type *)(skb_network_header(skb) + (off)) static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) { int err; u8 nexthdr; unsigned int off; unsigned int len; bool fragment; bool done; __sum16 *csum; fragment = false; done = false; off = sizeof(struct ipv6hdr); err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); if (err < 0) goto out; nexthdr = ipv6_hdr(skb)->nexthdr; len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { struct ipv6_opt_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ipv6_opt_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { struct ip_auth_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ip_auth_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ip_auth_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_authlen(hp); break; } case IPPROTO_FRAGMENT: { struct frag_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct frag_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct frag_hdr, skb, off); if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) fragment = true; nexthdr = hp->nexthdr; off += sizeof(struct frag_hdr); break; } default: done = true; break; } } err = -EPROTO; if (!done || fragment) goto out; csum = skb_checksum_setup_ip(skb, nexthdr, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - off, nexthdr, 0); err = 0; out: return err; } /** * skb_checksum_setup - set up partial checksum offset * @skb: the skb to set up * @recalculate: if true the pseudo-header checksum will be recalculated */ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) { int err; switch (skb->protocol) { case htons(ETH_P_IP): err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): err = skb_checksum_setup_ipv6(skb, recalculate); break; default: err = -EPROTO; break; } return err; } EXPORT_SYMBOL(skb_checksum_setup); /** * skb_checksum_maybe_trim - maybe trims the given skb * @skb: the skb to check * @transport_len: the data length beyond the network header * * Checks whether the given skb has data beyond the given transport length. * If so, returns a cloned skb trimmed to this transport length. * Otherwise returns the provided skb. Returns NULL in error cases * (e.g. transport_len exceeds skb length or out-of-memory). * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsigned int transport_len) { struct sk_buff *skb_chk; unsigned int len = skb_transport_offset(skb) + transport_len; int ret; if (skb->len < len) return NULL; else if (skb->len == len) return skb; skb_chk = skb_clone(skb, GFP_ATOMIC); if (!skb_chk) return NULL; ret = pskb_trim_rcsum(skb_chk, len); if (ret) { kfree_skb(skb_chk); return NULL; } return skb_chk; } /** * skb_checksum_trimmed - validate checksum of an skb * @skb: the skb to check * @transport_len: the data length beyond the network header * @skb_chkf: checksum function to use * * Applies the given checksum function skb_chkf to the provided skb. * Returns a checked and maybe trimmed skb. Returns NULL on error. * * If the skb has data beyond the given transport length, then a * trimmed & cloned skb is checked and returned. * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)) { struct sk_buff *skb_chk; unsigned int offset = skb_transport_offset(skb); __sum16 ret; skb_chk = skb_checksum_maybe_trim(skb, transport_len); if (!skb_chk) goto err; if (!pskb_may_pull(skb_chk, offset)) goto err; skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); skb_push_rcsum(skb_chk, offset); if (ret) goto err; return skb_chk; err: if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return NULL; } EXPORT_SYMBOL(skb_checksum_trimmed); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } } EXPORT_SYMBOL(kfree_skb_partial); /** * skb_try_coalesce - try to merge skb to prior one * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; if (skb_cloned(to)) return false; /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. In theory we could take full * references if @from is cloned and !@to->pp_recycle but its * tricky (due to potential race with the clone disappearing) and * rare, so not worth dealing with. */ if (to->pp_recycle != from->pp_recycle) return false; if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; return true; } to_shinfo = skb_shinfo(to); from_shinfo = skb_shinfo(from); if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; if (skb_headlen(from) != 0) { struct page *page; unsigned int offset; if (to_shinfo->nr_frags + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) return false; delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { if (to_shinfo->nr_frags + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); } WARN_ON_ONCE(delta < len); memcpy(to_shinfo->frags + to_shinfo->nr_frags, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ if (skb_pp_frag_ref(from)) { for (i = 0; i < from_shinfo->nr_frags; i++) __skb_frag_ref(&from_shinfo->frags[i]); } to->truesize += delta; to->len += len; to->data_len += len; *delta_truesize = delta; return true; } EXPORT_SYMBOL(skb_try_coalesce); /** * skb_scrub_packet - scrub an skb * * @skb: buffer to clean * @xnet: packet is crossing netns * * skb_scrub_packet can be used after encapsulating or decapsulting a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in * another namespace (@xnet == true). We have to clear all information in the * skb that could impact namespace isolation. */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif if (!xnet) return; ipvs_reset(skb); skb->mark = 0; skb_clear_tstamp(skb); } EXPORT_SYMBOL_GPL(skb_scrub_packet); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { int mac_len, meta_len; void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } mac_len = skb->data - skb_mac_header(skb); if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) { memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } meta_len = skb_metadata_len(skb); if (meta_len) { meta = skb_metadata_end(skb) - meta_len; memmove(meta + VLAN_HLEN, meta, meta_len); } skb->mac_header += VLAN_HLEN; return skb; } struct sk_buff *skb_vlan_untag(struct sk_buff *skb) { struct vlan_hdr *vhdr; u16 vlan_tci; if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; vlan_tci = ntohs(vhdr->h_vlan_TCI); __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb = skb_reorder_vlan_header(skb); if (unlikely(!skb)) goto err_free; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); return skb; err_free: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_vlan_untag); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) { if (!pskb_may_pull(skb, write_len)) return -ENOMEM; if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; return pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev) { int needed_headroom = dev->needed_headroom; int needed_tailroom = dev->needed_tailroom; /* For tail taggers, we need to pad short frames ourselves, to ensure * that the tail tag does not fail at its role of being at the end of * the packet, once the conduit interface pads the frame. Account for * that pad length here, and pad later. */ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) needed_tailroom += ETH_ZLEN - skb->len; /* skb_headroom() returns unsigned int... */ needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) /* No reallocation needed, yay! */ return 0; return pskb_expand_head(skb, needed_headroom, needed_tailroom, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable_head_tail); /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = skb_ensure_writable(skb, VLAN_ETH_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); vlan_remove_tag(skb, vlan_tci); skb->mac_header += VLAN_HLEN; if (skb_network_offset(skb) < ETH_HLEN) skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return err; } EXPORT_SYMBOL(__skb_vlan_pop); /* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header. */ int skb_vlan_pop(struct sk_buff *skb) { u16 vlan_tci; __be16 vlan_proto; int err; if (likely(skb_vlan_tag_present(skb))) { __vlan_hwaccel_clear_tag(skb); } else { if (unlikely(!eth_type_vlan(skb->protocol))) return 0; err = __skb_vlan_pop(skb, &vlan_tci); if (err) return err; } /* move next vlan tag to hw accel tag */ if (likely(!eth_type_vlan(skb->protocol))) return 0; vlan_proto = skb->protocol; err = __skb_vlan_pop(skb, &vlan_tci); if (unlikely(err)) return err; __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_pop); /* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present). * Expects skb->data at mac header. */ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { if (skb_vlan_tag_present(skb)) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "skb_vlan_push got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; skb->mac_len += VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_push); /** * skb_eth_pop() - Drop the Ethernet header at the head of a packet * * @skb: Socket buffer to modify * * Drop the Ethernet header of @skb. * * Expects that skb->data points to the mac header and that no VLAN tags are * present. * * Returns 0 on success, -errno otherwise. */ int skb_eth_pop(struct sk_buff *skb) { if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || skb_network_offset(skb) < ETH_HLEN) return -EPROTO; skb_pull_rcsum(skb, ETH_HLEN); skb_reset_mac_header(skb); skb_reset_mac_len(skb); return 0; } EXPORT_SYMBOL(skb_eth_pop); /** * skb_eth_push() - Add a new Ethernet header at the head of a packet * * @skb: Socket buffer to modify * @dst: Destination MAC address of the new header * @src: Source MAC address of the new header * * Prepend @skb with a new Ethernet header. * * Expects that skb->data points to the mac header, which must be empty. * * Returns 0 on success, -errno otherwise. */ int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src) { struct ethhdr *eth; int err; if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) return -EPROTO; err = skb_cow_head(skb, sizeof(*eth)); if (err < 0) return err; skb_push(skb, sizeof(*eth)); skb_reset_mac_header(skb); skb_reset_mac_len(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_dest, dst); ether_addr_copy(eth->h_source, src); eth->h_proto = skb->protocol; skb_postpush_rcsum(skb, eth, sizeof(*eth)); return 0; } EXPORT_SYMBOL(skb_eth_push); /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { if (skb->ip_summed == CHECKSUM_COMPLETE) { __be16 diff[] = { ~hdr->h_proto, ethertype }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } hdr->h_proto = ethertype; } /** * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is * ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; if (unlikely(!eth_p_mpls(mpls_proto))) return -EINVAL; /* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) return -EINVAL; err = skb_cow_head(skb, MPLS_HLEN); if (unlikely(err)) return err; if (!skb->inner_protocol) { skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_push); /** * skb_mpls_pop() - pop the outermost MPLS header * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return 0; err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN); skb_mod_eth_type(skb, hdr, next_proto); } skb->protocol = next_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); /** * skb_mpls_update_lse() - modify outermost MPLS header and update csum * * @skb: buffer * @mpls_lse: new MPLS label stack entry to update to * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } mpls_hdr(skb)->label_stack_entry = mpls_lse; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_update_lse); /** * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header * * @skb: buffer * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_dec_ttl(struct sk_buff *skb) { u32 lse; u8 ttl; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) return -ENOMEM; lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) return -EINVAL; lse &= ~MPLS_LS_TTL_MASK; lse |= ttl << MPLS_LS_TTL_SHIFT; return skb_mpls_update_lse(skb, cpu_to_be32(lse)); } EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl); /** * alloc_skb_with_frags - allocate skb with page frags * * @header_len: size of linear part * @data_len: needed length in frags * @order: max page order desired. * @errcode: pointer to error code if any * @gfp_mask: allocation mask * * This can be used to allocate a paged skb, given a maximal order for frags. */ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int order, int *errcode, gfp_t gfp_mask) { unsigned long chunk; struct sk_buff *skb; struct page *page; int nr_frags = 0; *errcode = -EMSGSIZE; if (unlikely(data_len > MAX_SKB_FRAGS * (PAGE_SIZE << order))) return NULL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; while (data_len) { if (nr_frags == MAX_SKB_FRAGS - 1) goto failure; while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order)) order--; if (order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN, order); if (!page) { order--; continue; } } else { page = alloc_page(gfp_mask); if (!page) goto failure; } chunk = min_t(unsigned long, data_len, PAGE_SIZE << order); skb_fill_page_desc(skb, nr_frags, page, 0, chunk); nr_frags++; skb->truesize += (PAGE_SIZE << order); data_len -= chunk; } return skb; failure: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(alloc_skb_with_frags); /* carve out the first off bytes from skb when off < headlen */ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { int i; unsigned int size = skb_end_offset(skb); int new_hlen = headlen - off; u8 *data; if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); /* Copy real data, and all frags */ skb_copy_from_linear_data_offset(skb, off, data, new_hlen); skb->len -= off; memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { skb_kfree_head(data, size); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb, SKB_CONSUMED); } else { /* we can reuse existing recount- all we did was * relocate values */ skb_free_head(skb); } skb->head = data; skb->data = data; skb->head_frag = 0; skb_set_end_offset(skb, size); skb_set_tail_pointer(skb, skb_headlen(skb)); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp); /* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve() */ static int pskb_carve_frag_list(struct sk_buff *skb, struct skb_shared_info *shinfo, int eat, gfp_t gfp_mask) { struct sk_buff *list = shinfo->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (!list) { pr_err("Not enough bytes to eat. Want %d\n", eat); return -EFAULT; } if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_shared(list)) { clone = skb_clone(list, gfp_mask); if (!clone) return -ENOMEM; insp = list->next; list = clone; } else { /* This may be pulled without problems. */ insp = list; } if (pskb_carve(list, eat, gfp_mask) < 0) { kfree_skb(clone); return -ENOMEM; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; shinfo->frag_list = clone; } return 0; } /* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb */ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { int i, k = 0; unsigned int size = skb_end_offset(skb); u8 *data; const int nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo; if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { skb_kfree_head(data, size); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); for (i = 0; i < nfrags; i++) { int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + fsize > off) { shinfo->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < off) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); k++; } pos += fsize; } shinfo->nr_frags = k; if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); /* split line is in frag list */ if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); skb_kfree_head(data, size); return -ENOMEM; } skb_release_data(skb, SKB_CONSUMED); skb->head = data; skb->head_frag = 0; skb->data = data; skb_set_end_offset(skb, size); skb_reset_tail_pointer(skb); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; skb->len -= off; skb->data_len = skb->len; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } /* remove len bytes from the beginning of the skb */ static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp) { int headlen = skb_headlen(skb); if (len < headlen) return pskb_carve_inside_header(skb, len, headlen, gfp); else return pskb_carve_inside_nonlinear(skb, len, headlen, gfp); } /* Extract to_copy bytes starting at off from skb, and return this in * a new skb */ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp) { struct sk_buff *clone = skb_clone(skb, gfp); if (!clone) return NULL; if (pskb_carve(clone, off, gfp) < 0 || pskb_trim(clone, to_copy)) { kfree_skb(clone); return NULL; } return clone; } EXPORT_SYMBOL(pskb_extract); /** * skb_condense - try to get rid of fragments/frag_list if possible * @skb: buffer * * Can be used to save memory before skb is added to a busy queue. * If packet has bytes in frags and enough tail room in skb->head, * pull all of them, so that we can free the frags right now and adjust * truesize. * Notes: * We do not reallocate skb->head thus can not fail. * Caller must re-evaluate skb->truesize if needed. */ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || skb_cloned(skb)) return; /* Nice, we can free page frag(s) right now */ __pskb_pull_tail(skb, skb->data_len); } /* At this point, skb->truesize might be over estimated, * because skb had a fragment, and fragments do not tell * their truesize. * When we pulled its content into skb->head, fragment * was freed, but __pskb_pull_tail() could not possibly * adjust skb->truesize, not knowing the frag truesize. */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) { return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } /** * __skb_ext_alloc - allocate a new skb extensions storage * * @flags: See kmalloc(). * * Returns the newly allocated pointer. The pointer can later attached to a * skb via __skb_ext_set(). * Note: caller must handle the skb_ext as an opaque data. */ struct skb_ext *__skb_ext_alloc(gfp_t flags) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags); if (new) { memset(new->offset, 0, sizeof(new->offset)); refcount_set(&new->refcnt, 1); } return new; } static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, unsigned int old_active) { struct skb_ext *new; if (refcount_read(&old->refcnt) == 1) return old; new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); if (!new) return NULL; memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE); refcount_set(&new->refcnt, 1); #ifdef CONFIG_XFRM if (old_active & (1 << SKB_EXT_SEC_PATH)) { struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH); unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } #endif #ifdef CONFIG_MCTP_FLOWS if (old_active & (1 << SKB_EXT_MCTP)) { struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP); if (flow->key) refcount_inc(&flow->key->refs); } #endif __skb_ext_put(old); return new; } /** * __skb_ext_set - attach the specified extension storage to this skb * @skb: buffer * @id: extension id * @ext: extension storage previously allocated via __skb_ext_alloc() * * Existing extensions, if any, are cleared. * * Returns the pointer to the extension. */ void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext) { unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); skb_ext_put(skb); newlen = newoff + skb_ext_type_len[id]; ext->chunks = newlen; ext->offset[id] = newoff; skb->extensions = ext; skb->active_extensions = 1 << id; return skb_ext_get_ptr(ext, id); } /** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for * * Allocates enough space for the given extension. * If the extension is already present, a pointer to that extension * is returned. * * If the skb was cloned, COW applies and the returned memory can be * modified without changing the extension space of clones buffers. * * Returns pointer to the extension or NULL on allocation failure. */ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *new, *old = NULL; unsigned int newlen, newoff; if (skb->active_extensions) { old = skb->extensions; new = skb_ext_maybe_cow(old, skb->active_extensions); if (!new) return NULL; if (__skb_ext_exist(new, id)) goto set_active; newoff = new->chunks; } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); new = __skb_ext_alloc(GFP_ATOMIC); if (!new) return NULL; } newlen = newoff + skb_ext_type_len[id]; new->chunks = newlen; new->offset[id] = newoff; set_active: skb->slow_gro = 1; skb->extensions = new; skb->active_extensions |= 1 << id; return skb_ext_get_ptr(new, id); } EXPORT_SYMBOL(skb_ext_add); #ifdef CONFIG_XFRM static void skb_ext_put_sp(struct sec_path *sp) { unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_put(sp->xvec[i]); } #endif #ifdef CONFIG_MCTP_FLOWS static void skb_ext_put_mctp(struct mctp_flow *flow) { if (flow->key) mctp_key_unref(flow->key); } #endif void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *ext = skb->extensions; skb->active_extensions &= ~(1 << id); if (skb->active_extensions == 0) { skb->extensions = NULL; __skb_ext_put(ext); #ifdef CONFIG_XFRM } else if (id == SKB_EXT_SEC_PATH && refcount_read(&ext->refcnt) == 1) { struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH); skb_ext_put_sp(sp); sp->len = 0; #endif } } EXPORT_SYMBOL(__skb_ext_del); void __skb_ext_put(struct skb_ext *ext) { /* If this is last clone, nothing can increment * it after check passes. Avoids one atomic op. */ if (refcount_read(&ext->refcnt) == 1) goto free_now; if (!refcount_dec_and_test(&ext->refcnt)) return; free_now: #ifdef CONFIG_XFRM if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH)) skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif #ifdef CONFIG_MCTP_FLOWS if (__skb_ext_exist(ext, SKB_EXT_MCTP)) skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP)); #endif kmem_cache_free(skbuff_ext_cache, ext); } EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ static void kfree_skb_napi_cache(struct sk_buff *skb) { /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } local_bh_disable(); __napi_kfree_skb(skb, SKB_CONSUMED); local_bh_enable(); } /** * skb_attempt_defer_free - queue skb for remote freeing * @skb: buffer * * Put @skb in a per-cpu list, using the cpu which * allocated the skb/pages to reduce false sharing * and memory zone spinlock contention. */ void skb_attempt_defer_free(struct sk_buff *skb) { int cpu = skb->alloc_cpu; struct softnet_data *sd; unsigned int defer_max; bool kick; if (cpu == raw_smp_processor_id() || WARN_ON_ONCE(cpu >= nr_cpu_ids) || !cpu_online(cpu)) { nodefer: kfree_skb_napi_cache(skb); return; } DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); DEBUG_NET_WARN_ON_ONCE(skb->destructor); sd = &per_cpu(softnet_data, cpu); defer_max = READ_ONCE(net_hotdata.sysctl_skb_defer_max); if (READ_ONCE(sd->defer_count) >= defer_max) goto nodefer; spin_lock_bh(&sd->defer_lock); /* Send an IPI every time queue reaches half capacity. */ kick = sd->defer_count == (defer_max >> 1); /* Paired with the READ_ONCE() few lines above */ WRITE_ONCE(sd->defer_count, sd->defer_count + 1); skb->next = sd->defer_list; /* Paired with READ_ONCE() in skb_defer_free_flush() */ WRITE_ONCE(sd->defer_list, skb); spin_unlock_bh(&sd->defer_lock); /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU * if we are unlucky enough (this seems very unlikely). */ if (unlikely(kick)) kick_defer_list_purge(sd, cpu); } static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, size_t offset, size_t len) { const char *kaddr; __wsum csum; kaddr = kmap_local_page(page); csum = csum_partial(kaddr + offset, len, 0); kunmap_local(kaddr); skb->csum = csum_block_add(skb->csum, csum, skb->len); } /** * skb_splice_from_iter - Splice (or copy) pages to skbuff * @skb: The buffer to add pages to * @iter: Iterator representing the pages to be added * @maxsize: Maximum amount of pages to be added * @gfp: Allocation flags * * This is a common helper function for supporting MSG_SPLICE_PAGES. It * extracts pages from an iterator and adds them to the socket buffer if * possible, copying them to fragments if not possible (such as if they're slab * pages). * * Returns the amount of data spliced/copied or -EMSGSIZE if there's * insufficient space in the buffer to transfer anything. */ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp) { size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags); struct page *pages[8], **ppages = pages; ssize_t spliced = 0, ret = 0; unsigned int i; while (iter->count > 0) { ssize_t space, nr, len; size_t off; ret = -EMSGSIZE; space = frag_limit - skb_shinfo(skb)->nr_frags; if (space < 0) break; /* We might be able to coalesce without increasing nr_frags */ nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages)); len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off); if (len <= 0) { ret = len ?: -EIO; break; } i = 0; do { struct page *page = pages[i++]; size_t part = min_t(size_t, PAGE_SIZE - off, len); ret = -EIO; if (WARN_ON_ONCE(!sendpage_ok(page))) goto out; ret = skb_append_pagefrags(skb, page, off, part, frag_limit); if (ret < 0) { iov_iter_revert(iter, len); goto out; } if (skb->ip_summed == CHECKSUM_NONE) skb_splice_csum_page(skb, page, off, part); off = 0; spliced += part; maxsize -= part; len -= part; } while (len > 0); if (maxsize <= 0) break; } out: skb_len_add(skb, spliced); return spliced ?: ret; } EXPORT_SYMBOL(skb_splice_from_iter); static __always_inline size_t memcpy_from_iter_csum(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { __wsum *csum = priv2; __wsum next = csum_partial_copy_nocheck(iter_from, to + progress, len); *csum = csum_block_add(*csum, next, progress); return 0; } static __always_inline size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { __wsum next, *csum = priv2; next = csum_and_copy_from_user(iter_from, to + progress, len); *csum = csum_block_add(*csum, next, progress); return next ? 0 : len; } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { size_t copied; if (WARN_ON_ONCE(!i->data_source)) return false; copied = iterate_and_advance2(i, bytes, addr, csum, copy_from_user_iter_csum, memcpy_from_iter_csum); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | // SPDX-License-Identifier: GPL-2.0 /* * hrtimers - High-resolution kernel timers * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes * * Started by: Thomas Gleixner and Ingo Molnar */ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> #include <linux/hrtimer_types.h> #include <linux/init.h> #include <linux/list.h> #include <linux/percpu-defs.h> #include <linux/rbtree.h> #include <linux/timer.h> /* * Mode arguments of xxx_hrtimer functions: * * HRTIMER_MODE_ABS - Time value is absolute * HRTIMER_MODE_REL - Time value is relative to now * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered * when starting the timer) * HRTIMER_MODE_SOFT - Timer callback function will be executed in * soft irq context * HRTIMER_MODE_HARD - Timer callback function will be executed in * hard irq context even on PREEMPT_RT. */ enum hrtimer_mode { HRTIMER_MODE_ABS = 0x00, HRTIMER_MODE_REL = 0x01, HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, HRTIMER_MODE_HARD = 0x08, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, }; /* * Values to track state of the timer * * Possible states: * * 0x00 inactive * 0x01 enqueued into rbtree * * The callback state is not part of the timer->state because clearing it would * mean touching the timer after the callback, this makes it impossible to free * the timer from the callback function. * * Therefore we track the callback state in: * * timer->base->cpu_base->running == timer * * On SMP it is possible to have a "callback function running and enqueued" * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 /** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up * * task is set to NULL, when the timer expires. */ struct hrtimer_sleeper { struct hrtimer timer; struct task_struct *task; }; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { timer->node.expires = tv64; timer->_softexpires = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { return timer->node.expires; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) { return ktime_to_ns(timer->node.expires); } static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { return ktime_sub(timer->node.expires, timer->base->get_time()); } static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) { return timer->base->get_time(); } static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? timer->base->cpu_base->hres_active : 0; } #ifdef CONFIG_HIGH_RES_TIMERS struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); extern unsigned int hrtimer_resolution; #else #define hrtimer_resolution (unsigned int)LOW_RES_NSEC #endif static inline ktime_t __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) { ktime_t rem = ktime_sub(timer->node.expires, now); /* * Adjust relative timers for the extra we added in * hrtimer_start_range_ns() to prevent short timeouts. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) rem -= hrtimer_resolution; return rem; } static inline ktime_t hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) { return __hrtimer_expires_remaining_adjusted(timer, timer->base->get_time()); } #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); extern void timerfd_resume(void); #else static inline void timerfd_clock_was_set(void) { } static inline void timerfd_resume(void) { } #endif DECLARE_PER_CPU(struct tick_device, tick_cpu_device); #ifdef CONFIG_PREEMPT_RT void hrtimer_cancel_wait_running(const struct hrtimer *timer); #else static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) { cpu_relax(); } #endif /* Exported timer functions: */ /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else static inline void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode) { hrtimer_init(timer, which_clock, mode); } static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { hrtimer_init_sleeper(sl, clock_id, mode); } static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { hrtimer_start_range_ns(timer, tim, 0, mode); } extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); hrtimer_start_range_ns(timer, soft, delta, mode); } void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode); static inline void hrtimer_restart(struct hrtimer *timer) { hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read */ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { return __hrtimer_get_remaining(timer, false); } extern u64 hrtimer_get_next_event(void); extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); /** * hrtimer_is_queued - check, whether the timer is on one of the queues * @timer: Timer to check * * Returns: True if the timer is queued, false otherwise * * The function can be used lockless, but it gives only a current snapshot. */ static inline bool hrtimer_is_queued(struct hrtimer *timer) { /* The READ_ONCE pairs with the update functions of timer->state */ return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* * Helper function to check, whether the timer is running the callback * function */ static inline int hrtimer_callback_running(struct hrtimer *timer) { return timer->base->running == timer; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /** * hrtimer_forward_now() - forward the timer expiry so it expires after now * @timer: hrtimer to forward * @interval: the interval to forward * * It is a variant of hrtimer_forward(). The timer will expire after the current * time of the hrtimer clock base. See hrtimer_forward() for details. */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { return hrtimer_forward(timer, timer->base->get_time(), interval); } /* Precise sleep: */ extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); /* Show pending timers: */ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else #define hrtimers_cpu_dying NULL #endif #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 | #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H #include <linux/types.h> struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; struct __una_u64 { u64 x; } __packed; static inline u16 __get_unaligned_cpu16(const void *p) { const struct __una_u16 *ptr = (const struct __una_u16 *)p; return ptr->x; } static inline u32 __get_unaligned_cpu32(const void *p) { const struct __una_u32 *ptr = (const struct __una_u32 *)p; return ptr->x; } static inline u64 __get_unaligned_cpu64(const void *p) { const struct __una_u64 *ptr = (const struct __una_u64 *)p; return ptr->x; } static inline void __put_unaligned_cpu16(u16 val, void *p) { struct __una_u16 *ptr = (struct __una_u16 *)p; ptr->x = val; } static inline void __put_unaligned_cpu32(u32 val, void *p) { struct __una_u32 *ptr = (struct __una_u32 *)p; ptr->x = val; } static inline void __put_unaligned_cpu64(u64 val, void *p) { struct __una_u64 *ptr = (struct __una_u64 *)p; ptr->x = val; } #endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */ |
| 64 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_KVM_MAIN_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KVM_MAIN_H #include <linux/tracepoint.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm #define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x } #define kvm_trace_exit_reason \ ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL), \ ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN), \ ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \ ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\ ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL), \ ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\ ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI), \ ERSN(HYPERV), ERSN(ARM_NISV), ERSN(X86_RDMSR), ERSN(X86_WRMSR) TRACE_EVENT(kvm_userspace_exit, TP_PROTO(__u32 reason, int errno), TP_ARGS(reason, errno), TP_STRUCT__entry( __field( __u32, reason ) __field( int, errno ) ), TP_fast_assign( __entry->reason = reason; __entry->errno = errno; ), TP_printk("reason %s (%d)", __entry->errno < 0 ? (__entry->errno == -EINTR ? "restart" : "error") : __print_symbolic(__entry->reason, kvm_trace_exit_reason), __entry->errno < 0 ? -__entry->errno : __entry->reason) ); TRACE_EVENT(kvm_vcpu_wakeup, TP_PROTO(__u64 ns, bool waited, bool valid), TP_ARGS(ns, waited, valid), TP_STRUCT__entry( __field( __u64, ns ) __field( bool, waited ) __field( bool, valid ) ), TP_fast_assign( __entry->ns = ns; __entry->waited = waited; __entry->valid = valid; ), TP_printk("%s time %lld ns, polling %s", __entry->waited ? "wait" : "poll", __entry->ns, __entry->valid ? "valid" : "invalid") ); #if defined(CONFIG_HAVE_KVM_IRQCHIP) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), TP_ARGS(gsi, level, irq_source_id), TP_STRUCT__entry( __field( unsigned int, gsi ) __field( int, level ) __field( int, irq_source_id ) ), TP_fast_assign( __entry->gsi = gsi; __entry->level = level; __entry->irq_source_id = irq_source_id; ), TP_printk("gsi %u level %d source %d", __entry->gsi, __entry->level, __entry->irq_source_id) ); #endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ #if defined(__KVM_HAVE_IOAPIC) #define kvm_deliver_mode \ {0x0, "Fixed"}, \ {0x1, "LowPrio"}, \ {0x2, "SMI"}, \ {0x3, "Res3"}, \ {0x4, "NMI"}, \ {0x5, "INIT"}, \ {0x6, "SIPI"}, \ {0x7, "ExtINT"} TRACE_EVENT(kvm_ioapic_set_irq, TP_PROTO(__u64 e, int pin, bool coalesced), TP_ARGS(e, pin, coalesced), TP_STRUCT__entry( __field( __u64, e ) __field( int, pin ) __field( bool, coalesced ) ), TP_fast_assign( __entry->e = e; __entry->pin = pin; __entry->coalesced = coalesced; ), TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s", __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e, __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), (__entry->e & (1<<11)) ? "logical" : "physical", (__entry->e & (1<<15)) ? "level" : "edge", (__entry->e & (1<<16)) ? "|masked" : "", __entry->coalesced ? " (coalesced)" : "") ); TRACE_EVENT(kvm_ioapic_delayed_eoi_inj, TP_PROTO(__u64 e), TP_ARGS(e), TP_STRUCT__entry( __field( __u64, e ) ), TP_fast_assign( __entry->e = e; ), TP_printk("dst %x vec %u (%s|%s|%s%s)", (u8)(__entry->e >> 56), (u8)__entry->e, __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), (__entry->e & (1<<11)) ? "logical" : "physical", (__entry->e & (1<<15)) ? "level" : "edge", (__entry->e & (1<<16)) ? "|masked" : "") ); TRACE_EVENT(kvm_msi_set_irq, TP_PROTO(__u64 address, __u64 data), TP_ARGS(address, data), TP_STRUCT__entry( __field( __u64, address ) __field( __u64, data ) ), TP_fast_assign( __entry->address = address; __entry->data = data; ), TP_printk("dst %llx vec %u (%s|%s|%s%s)", (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00), (u8)__entry->data, __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode), (__entry->address & (1<<2)) ? "logical" : "physical", (__entry->data & (1<<15)) ? "level" : "edge", (__entry->address & (1<<3)) ? "|rh" : "") ); #define kvm_irqchips \ {KVM_IRQCHIP_PIC_MASTER, "PIC master"}, \ {KVM_IRQCHIP_PIC_SLAVE, "PIC slave"}, \ {KVM_IRQCHIP_IOAPIC, "IOAPIC"} #endif /* defined(__KVM_HAVE_IOAPIC) */ #if defined(CONFIG_HAVE_KVM_IRQCHIP) #ifdef kvm_irqchips #define kvm_ack_irq_string "irqchip %s pin %u" #define kvm_ack_irq_parm __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin #else #define kvm_ack_irq_string "irqchip %d pin %u" #define kvm_ack_irq_parm __entry->irqchip, __entry->pin #endif TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), TP_ARGS(irqchip, pin), TP_STRUCT__entry( __field( unsigned int, irqchip ) __field( unsigned int, pin ) ), TP_fast_assign( __entry->irqchip = irqchip; __entry->pin = pin; ), TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm) ); #endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ #define KVM_TRACE_MMIO_READ_UNSATISFIED 0 #define KVM_TRACE_MMIO_READ 1 #define KVM_TRACE_MMIO_WRITE 2 #define kvm_trace_symbol_mmio \ { KVM_TRACE_MMIO_READ_UNSATISFIED, "unsatisfied-read" }, \ { KVM_TRACE_MMIO_READ, "read" }, \ { KVM_TRACE_MMIO_WRITE, "write" } TRACE_EVENT(kvm_mmio, TP_PROTO(int type, int len, u64 gpa, void *val), TP_ARGS(type, len, gpa, val), TP_STRUCT__entry( __field( u32, type ) __field( u32, len ) __field( u64, gpa ) __field( u64, val ) ), TP_fast_assign( __entry->type = type; __entry->len = len; __entry->gpa = gpa; __entry->val = 0; if (val) memcpy(&__entry->val, val, min_t(u32, sizeof(__entry->val), len)); ), TP_printk("mmio %s len %u gpa 0x%llx val 0x%llx", __print_symbolic(__entry->type, kvm_trace_symbol_mmio), __entry->len, __entry->gpa, __entry->val) ); #define kvm_fpu_load_symbol \ {0, "unload"}, \ {1, "load"} TRACE_EVENT(kvm_fpu, TP_PROTO(int load), TP_ARGS(load), TP_STRUCT__entry( __field( u32, load ) ), TP_fast_assign( __entry->load = load; ), TP_printk("%s", __print_symbolic(__entry->load, kvm_fpu_load_symbol)) ); #ifdef CONFIG_KVM_ASYNC_PF DECLARE_EVENT_CLASS(kvm_async_get_page_class, TP_PROTO(u64 gva, u64 gfn), TP_ARGS(gva, gfn), TP_STRUCT__entry( __field(__u64, gva) __field(u64, gfn) ), TP_fast_assign( __entry->gva = gva; __entry->gfn = gfn; ), TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) ); DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page, TP_PROTO(u64 gva, u64 gfn), TP_ARGS(gva, gfn) ); DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_repeated_fault, TP_PROTO(u64 gva, u64 gfn), TP_ARGS(gva, gfn) ); DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready, TP_PROTO(u64 token, u64 gva), TP_ARGS(token, gva), TP_STRUCT__entry( __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( __entry->token = token; __entry->gva = gva; ), TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva) ); DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present, TP_PROTO(u64 token, u64 gva), TP_ARGS(token, gva) ); DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready, TP_PROTO(u64 token, u64 gva), TP_ARGS(token, gva) ); TRACE_EVENT( kvm_async_pf_completed, TP_PROTO(unsigned long address, u64 gva), TP_ARGS(address, gva), TP_STRUCT__entry( __field(unsigned long, address) __field(u64, gva) ), TP_fast_assign( __entry->address = address; __entry->gva = gva; ), TP_printk("gva %#llx address %#lx", __entry->gva, __entry->address) ); #endif TRACE_EVENT(kvm_halt_poll_ns, TP_PROTO(bool grow, unsigned int vcpu_id, unsigned int new, unsigned int old), TP_ARGS(grow, vcpu_id, new, old), TP_STRUCT__entry( __field(bool, grow) __field(unsigned int, vcpu_id) __field(unsigned int, new) __field(unsigned int, old) ), TP_fast_assign( __entry->grow = grow; __entry->vcpu_id = vcpu_id; __entry->new = new; __entry->old = old; ), TP_printk("vcpu %u: halt_poll_ns %u (%s %u)", __entry->vcpu_id, __entry->new, __entry->grow ? "grow" : "shrink", __entry->old) ); #define trace_kvm_halt_poll_ns_grow(vcpu_id, new, old) \ trace_kvm_halt_poll_ns(true, vcpu_id, new, old) #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \ trace_kvm_halt_poll_ns(false, vcpu_id, new, old) TRACE_EVENT(kvm_dirty_ring_push, TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset), TP_ARGS(ring, slot, offset), TP_STRUCT__entry( __field(int, index) __field(u32, dirty_index) __field(u32, reset_index) __field(u32, slot) __field(u64, offset) ), TP_fast_assign( __entry->index = ring->index; __entry->dirty_index = ring->dirty_index; __entry->reset_index = ring->reset_index; __entry->slot = slot; __entry->offset = offset; ), TP_printk("ring %d: dirty 0x%x reset 0x%x " "slot %u offset 0x%llx (used %u)", __entry->index, __entry->dirty_index, __entry->reset_index, __entry->slot, __entry->offset, __entry->dirty_index - __entry->reset_index) ); TRACE_EVENT(kvm_dirty_ring_reset, TP_PROTO(struct kvm_dirty_ring *ring), TP_ARGS(ring), TP_STRUCT__entry( __field(int, index) __field(u32, dirty_index) __field(u32, reset_index) ), TP_fast_assign( __entry->index = ring->index; __entry->dirty_index = ring->dirty_index; __entry->reset_index = ring->reset_index; ), TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)", __entry->index, __entry->dirty_index, __entry->reset_index, __entry->dirty_index - __entry->reset_index) ); TRACE_EVENT(kvm_dirty_ring_exit, TP_PROTO(struct kvm_vcpu *vcpu), TP_ARGS(vcpu), TP_STRUCT__entry( __field(int, vcpu_id) ), TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; ), TP_printk("vcpu %d", __entry->vcpu_id) ); TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), TP_STRUCT__entry( __field( unsigned long, start ) __field( unsigned long, end ) ), TP_fast_assign( __entry->start = start; __entry->end = end; ), TP_printk("mmu notifier unmap range: %#016lx -- %#016lx", __entry->start, __entry->end) ); TRACE_EVENT(kvm_age_hva, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), TP_STRUCT__entry( __field( unsigned long, start ) __field( unsigned long, end ) ), TP_fast_assign( __entry->start = start; __entry->end = end; ), TP_printk("mmu notifier age hva: %#016lx -- %#016lx", __entry->start, __entry->end) ); TRACE_EVENT(kvm_test_age_hva, TP_PROTO(unsigned long hva), TP_ARGS(hva), TP_STRUCT__entry( __field( unsigned long, hva ) ), TP_fast_assign( __entry->hva = hva; ), TP_printk("mmu notifier test age hva: %#016lx", __entry->hva) ); #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 48 41 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be * applied to the leaves of pgtables. */ #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { /* pages reclaimed outside of LRU-based reclaim */ unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; /* * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based * reclaim * @pages: number of pages reclaimed * * If the current process is undergoing a reclaim operation, increment the * number of reclaimed pages by @pages. */ static inline void mm_account_reclaimed_pages(unsigned long pages) { if (current->reclaim_state) current->reclaim_state->reclaimed += pages; } #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The data field stores next cluster if the cluster is free or cluster usage * counter otherwise. The flags field determines if a cluster is free. This is * protected by swap_info_struct.lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * and swap_info_struct->swap_map * elements correspond to the swap * cluster */ unsigned int data:24; unsigned int flags:8; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as * a sentinel to indicate next is not valid in percpu_cluster. */ #define SWAP_NEXT_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) #else #define SWAP_NR_ORDERS 1 #endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; struct swap_cluster_list { struct swap_cluster_info head; struct swap_cluster_info tail; }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct swap_cluster_list free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct swap_cluster_list discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; static inline swp_entry_t page_swap_entry(struct page *page) { struct folio *folio = page_folio(page); swp_entry_t entry = folio->swap; entry.val += folio_page_idx(folio, page); return entry; } /* linux/mm/workingset.c */ bool workingset_test_recent(void *shadow, bool file, bool *workingset); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated); void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } void free_swap_cache(struct folio *folio); void free_page_and_swap_cache(struct page *); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) { } static inline void free_swap_cache(struct folio *folio) { } static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline int swapcache_prepare(swp_entry_t swp) { return 0; } static inline void swap_free(swp_entry_t swp) { } static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); } #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return READ_ONCE(vm_swappiness); return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return READ_ONCE(vm_swappiness); } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; __folio_throttle_swaprate(folio, gfp); } #else static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { } #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 - Google LLC * Author: Quentin Perret <qperret@google.com> */ #include <linux/init.h> #include <linux/kmemleak.h> #include <linux/kvm_host.h> #include <linux/memblock.h> #include <linux/mutex.h> #include <linux/sort.h> #include <asm/kvm_pkvm.h> #include "hyp_constants.h" DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); static struct memblock_region *hyp_memory = kvm_nvhe_sym(hyp_memory); static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr); phys_addr_t hyp_mem_base; phys_addr_t hyp_mem_size; static int cmp_hyp_memblock(const void *p1, const void *p2) { const struct memblock_region *r1 = p1; const struct memblock_region *r2 = p2; return r1->base < r2->base ? -1 : (r1->base > r2->base); } static void __init sort_memblock_regions(void) { sort(hyp_memory, *hyp_memblock_nr_ptr, sizeof(struct memblock_region), cmp_hyp_memblock, NULL); } static int __init register_memblock_regions(void) { struct memblock_region *reg; for_each_mem_region(reg) { if (*hyp_memblock_nr_ptr >= HYP_MEMBLOCK_REGIONS) return -ENOMEM; hyp_memory[*hyp_memblock_nr_ptr] = *reg; (*hyp_memblock_nr_ptr)++; } sort_memblock_regions(); return 0; } void __init kvm_hyp_reserve(void) { u64 hyp_mem_pages = 0; int ret; if (!is_hyp_mode_available() || is_kernel_in_hyp_mode()) return; if (kvm_get_mode() != KVM_MODE_PROTECTED) return; ret = register_memblock_regions(); if (ret) { *hyp_memblock_nr_ptr = 0; kvm_err("Failed to register hyp memblocks: %d\n", ret); return; } hyp_mem_pages += hyp_s1_pgtable_pages(); hyp_mem_pages += host_s2_pgtable_pages(); hyp_mem_pages += hyp_vm_table_pages(); hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE); hyp_mem_pages += hyp_ffa_proxy_pages(); /* * Try to allocate a PMD-aligned region to reduce TLB pressure once * this is unmapped from the host stage-2, and fallback to PAGE_SIZE. */ hyp_mem_size = hyp_mem_pages << PAGE_SHIFT; hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE), PMD_SIZE); if (!hyp_mem_base) hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE); else hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE); if (!hyp_mem_base) { kvm_err("Failed to reserve hyp memory\n"); return; } kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20, hyp_mem_base); } static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) { if (host_kvm->arch.pkvm.handle) { WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, host_kvm->arch.pkvm.handle)); } host_kvm->arch.pkvm.handle = 0; free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); } /* * Allocates and donates memory for hypervisor VM structs at EL2. * * Allocates space for the VM state, which includes the hyp vm as well as * the hyp vcpus. * * Stores an opaque handler in the kvm struct for future reference. * * Return 0 on success, negative error code on failure. */ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) { size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz; struct kvm_vcpu *host_vcpu; pkvm_handle_t handle; void *pgd, *hyp_vm; unsigned long idx; int ret; if (host_kvm->created_vcpus < 1) return -EINVAL; pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.mmu.vtcr); /* * The PGD pages will be reclaimed using a hyp_memcache which implies * page granularity. So, use alloc_pages_exact() to get individual * refcounts. */ pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT); if (!pgd) return -ENOMEM; /* Allocate memory to donate to hyp for vm and vcpu pointers. */ hyp_vm_sz = PAGE_ALIGN(size_add(PKVM_HYP_VM_SIZE, size_mul(sizeof(void *), host_kvm->created_vcpus))); hyp_vm = alloc_pages_exact(hyp_vm_sz, GFP_KERNEL_ACCOUNT); if (!hyp_vm) { ret = -ENOMEM; goto free_pgd; } /* Donate the VM memory to hyp and let hyp initialize it. */ ret = kvm_call_hyp_nvhe(__pkvm_init_vm, host_kvm, hyp_vm, pgd); if (ret < 0) goto free_vm; handle = ret; host_kvm->arch.pkvm.handle = handle; /* Donate memory for the vcpus at hyp and initialize it. */ hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE); kvm_for_each_vcpu(idx, host_vcpu, host_kvm) { void *hyp_vcpu; /* Indexing of the vcpus to be sequential starting at 0. */ if (WARN_ON(host_vcpu->vcpu_idx != idx)) { ret = -EINVAL; goto destroy_vm; } hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT); if (!hyp_vcpu) { ret = -ENOMEM; goto destroy_vm; } ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu, hyp_vcpu); if (ret) { free_pages_exact(hyp_vcpu, hyp_vcpu_sz); goto destroy_vm; } } return 0; destroy_vm: __pkvm_destroy_hyp_vm(host_kvm); return ret; free_vm: free_pages_exact(hyp_vm, hyp_vm_sz); free_pgd: free_pages_exact(pgd, pgd_sz); return ret; } int pkvm_create_hyp_vm(struct kvm *host_kvm) { int ret = 0; mutex_lock(&host_kvm->arch.config_lock); if (!host_kvm->arch.pkvm.handle) ret = __pkvm_create_hyp_vm(host_kvm); mutex_unlock(&host_kvm->arch.config_lock); return ret; } void pkvm_destroy_hyp_vm(struct kvm *host_kvm) { mutex_lock(&host_kvm->arch.config_lock); __pkvm_destroy_hyp_vm(host_kvm); mutex_unlock(&host_kvm->arch.config_lock); } int pkvm_init_host_vm(struct kvm *host_kvm) { return 0; } static void __init _kvm_host_prot_finalize(void *arg) { int *err = arg; if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize))) WRITE_ONCE(*err, -EINVAL); } static int __init pkvm_drop_host_privileges(void) { int ret = 0; /* * Flip the static key upfront as that may no longer be possible * once the host stage 2 is installed. */ static_branch_enable(&kvm_protected_mode_initialized); on_each_cpu(_kvm_host_prot_finalize, &ret, 1); return ret; } static int __init finalize_pkvm(void) { int ret; if (!is_protected_kvm_enabled() || !is_kvm_arm_initialised()) return 0; /* * Exclude HYP sections from kmemleak so that they don't get peeked * at, which would end badly once inaccessible. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start); kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size); ret = pkvm_drop_host_privileges(); if (ret) pr_err("Failed to finalize Hyp protection: %d\n", ret); return ret; } device_initcall_sync(finalize_pkvm); |
| 69 68 69 17 19 128 19 19 128 126 19 4 126 19 126 126 126 125 134 136 136 135 136 136 135 135 136 136 136 8 81 82 27 46 62 46 46 62 122 121 122 122 75 74 74 75 122 121 121 122 121 122 75 75 75 121 121 5 5 3 5 5 5 5 121 5 8 8 8 5 5 8 1 8 8 8 8 9 7 8 8 8 8 60 7 7 60 54 6 6 54 27 27 19 10 10 7 4 19 4 4 19 18 10 17 17 17 85 7 32 32 47 85 86 85 3 86 86 86 85 86 86 83 2 83 55 40 84 86 84 47 47 46 46 7 18 17 4 3 17 17 1 43 43 42 40 51 26 24 28 74 40 40 40 28 74 69 31 49 89 10 10 8 8 81 43 43 42 84 90 50 10 69 10 10 10 10 69 69 10 10 10 10 74 49 57 56 56 55 57 57 36 36 36 86 86 48 51 63 57 36 85 84 84 84 86 26 26 57 57 89 90 9 8 8 8 10 10 10 10 7 6 9 9 9 9 9 9 9 8 3 8 8 8 8 8 9 10 10 108 126 126 121 126 126 126 127 115 128 128 122 122 122 3 121 120 116 99 121 121 121 121 121 121 121 121 121 116 98 121 126 126 116 116 125 100 126 126 126 7 126 126 126 125 126 126 126 126 126 125 126 126 33 125 125 93 125 126 126 126 93 126 2 2 1 2 3 126 134 134 134 133 22 3 134 74 49 74 73 74 74 12 12 74 74 60 7 74 6 49 6 69 2 8 68 68 39 28 5 28 28 27 27 27 39 23 20 61 61 62 62 62 62 5 61 69 69 69 43 18 54 18 68 69 11 11 11 11 11 95 96 96 94 3 96 96 96 78 79 78 16 130 2 130 19 129 123 98 98 98 98 98 98 98 98 98 98 98 98 98 98 98 2 98 98 98 98 98 98 98 98 98 98 98 98 97 97 97 97 97 97 97 97 97 97 97 97 97 97 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> #include <linux/mmdebug.h> #include <linux/perf_event.h> #include <linux/audit.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/notifier.h> #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #define CREATE_TRACE_POINTS #include <trace/events/mmap.h> #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; int mmap_rnd_bits_max __ro_after_init = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked); static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, mapping); i_mmap_unlock_write(mapping); } } /* * Close a vm structure and free it. */ static void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); if (unreachable) __vm_area_free(vma); else vm_area_free(vma); } static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev(&vmi->mas, min); } /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. * @addr: The address to check * @len: The size of increase. * * Return: 0 on success. */ static int check_brk_limits(unsigned long addr, unsigned long len) { unsigned long mapped_addr; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; return mlock_future_ok(current->mm, current->mm->def_flags, len) ? 0 : -EAGAIN; } static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma, unsigned long addr, unsigned long request, unsigned long flags); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *brkvma, *next = NULL; unsigned long min_brk; bool populate = false; LIST_HEAD(uf); struct vma_iterator vmi; if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* Always allow shrinking brk. */ if (brk <= mm->brk) { /* Search one past newbrk */ vma_iter_init(&vmi, mm, newbrk); brkvma = vma_find(&vmi, oldbrk); if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. * do_vma_munmap() will drop the lock on success, so update it * before calling do_vma_munmap(). */ mm->brk = brk; if (do_vma_munmap(&vmi, brkvma, newbrk, oldbrk, &uf, true)) goto out; goto success_unlocked; } if (check_brk_limits(oldbrk, newbrk - oldbrk)) goto out; /* * Only check if the next VMA is within the stack_guard_gap of the * expansion area */ vma_iter_init(&vmi, mm, oldbrk); next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; brkvma = vma_prev_limit(&vmi, mm->start_brk); /* Ok, looks good - let it rip. */ if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, 0) < 0) goto out; mm->brk = brk; if (mm->def_flags & VM_LOCKED) populate = true; success: mmap_write_unlock(mm); success_unlocked: userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: mm->brk = origbrk; mmap_write_unlock(mm); return origbrk; } #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mt_validate(&mm->mm_mt); for_each_vma(vmi, vma) { #ifdef CONFIG_DEBUG_VM_RB struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; #endif unsigned long vmi_start, vmi_end; bool warn = 0; vmi_start = vma_iter_addr(&vmi); vmi_end = vma_iter_end(&vmi); if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) warn = 1; if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) warn = 1; if (warn) { pr_emerg("issue in %s\n", current->comm); dump_stack(); dump_vma(vma); pr_emerg("tree range: %px start %lx end %lx\n", vma, vmi_start, vmi_end - 1); vma_iter_dump_tree(&vmi); } #ifdef CONFIG_DEBUG_VM_RB if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } #endif i++; } if (i != mm->map_count) { pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #else /* !CONFIG_DEBUG_VM_MAPLE_TREE */ #define validate_mm(mm) do { } while (0) #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static inline void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static inline void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { VMA_ITERATOR(vmi, mm, addr); struct vm_area_struct *vma; unsigned long nr_pages = 0; for_each_vma_range(vmi, vma, end) { unsigned long vm_start = max(addr, vma->vm_start); unsigned long vm_end = min(end, vma->vm_end); nr_pages += PHYS_PFN(vm_end - vm_start); } return nr_pages; } static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } static void vma_link_file(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct address_space *mapping; if (file) { mapping = file->f_mapping; i_mmap_lock_write(mapping); __vma_link_file(vma, mapping); i_mmap_unlock_write(mapping); } } static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { VMA_ITERATOR(vmi, mm, 0); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; vma_start_write(vma); vma_iter_store(&vmi, vma); vma_link_file(vma); mm->map_count++; validate_mm(mm); return 0; } /* * init_multi_vma_prep() - Initializer for struct vma_prepare * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked * @next: The next vma if it is to be adjusted * @remove: The first vma to be removed * @remove2: The second vma to be removed */ static inline void init_multi_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma, struct vm_area_struct *next, struct vm_area_struct *remove, struct vm_area_struct *remove2) { memset(vp, 0, sizeof(struct vma_prepare)); vp->vma = vma; vp->anon_vma = vma->anon_vma; vp->remove = remove; vp->remove2 = remove2; vp->adj_next = next; if (!vp->anon_vma && next) vp->anon_vma = next->anon_vma; vp->file = vma->vm_file; if (vp->file) vp->mapping = vma->vm_file->f_mapping; } /* * init_vma_prep() - Initializer wrapper for vma_prepare struct * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked */ static inline void init_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma) { init_multi_vma_prep(vp, vma, NULL, NULL, NULL); } /* * vma_prepare() - Helper function for handling locking VMAs prior to altering * @vp: The initialized vma_prepare struct */ static inline void vma_prepare(struct vma_prepare *vp) { if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); if (vp->adj_next) uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, vp->adj_next->vm_end); i_mmap_lock_write(vp->mapping); if (vp->insert && vp->insert->vm_file) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(vp->insert, vp->insert->vm_file->f_mapping); } } if (vp->anon_vma) { anon_vma_lock_write(vp->anon_vma); anon_vma_interval_tree_pre_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_pre_update_vma(vp->adj_next); } if (vp->file) { flush_dcache_mmap_lock(vp->mapping); vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); if (vp->adj_next) vma_interval_tree_remove(vp->adj_next, &vp->mapping->i_mmap); } } /* * vma_complete- Helper function for handling the unlocking after altering VMAs, * or for inserting a VMA. * * @vp: The vma_prepare struct * @vmi: The vma iterator * @mm: The mm_struct */ static inline void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, struct mm_struct *mm) { if (vp->file) { if (vp->adj_next) vma_interval_tree_insert(vp->adj_next, &vp->mapping->i_mmap); vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); flush_dcache_mmap_unlock(vp->mapping); } if (vp->remove && vp->file) { __remove_shared_vm_struct(vp->remove, vp->mapping); if (vp->remove2) __remove_shared_vm_struct(vp->remove2, vp->mapping); } else if (vp->insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ vma_iter_store(vmi, vp->insert); mm->map_count++; } if (vp->anon_vma) { anon_vma_interval_tree_post_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_post_update_vma(vp->adj_next); anon_vma_unlock_write(vp->anon_vma); } if (vp->file) { i_mmap_unlock_write(vp->mapping); uprobe_mmap(vp->vma); if (vp->adj_next) uprobe_mmap(vp->adj_next); } if (vp->remove) { again: vma_mark_detached(vp->remove, true); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); fput(vp->file); } if (vp->remove->anon_vma) anon_vma_merge(vp->vma, vp->remove); mm->map_count--; mpol_put(vma_policy(vp->remove)); if (!vp->remove2) WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); vm_area_free(vp->remove); /* * In mprotect's case 6 (see comments on vma_merge), * we are removing both mid and next vmas */ if (vp->remove2) { vp->remove = vp->remove2; vp->remove2 = NULL; goto again; } } if (vp->insert && vp->file) uprobe_mmap(vp->insert); validate_mm(mm); } /* * dup_anon_vma() - Helper function to duplicate anon_vma * @dst: The destination VMA * @src: The source VMA * @dup: Pointer to the destination VMA when successful. * * Returns: 0 on success. */ static inline int dup_anon_vma(struct vm_area_struct *dst, struct vm_area_struct *src, struct vm_area_struct **dup) { /* * Easily overlooked: when mprotect shifts the boundary, make sure the * expanding vma has anon_vma set if the shrinking vma had, to cover any * anon pages imported. */ if (src->anon_vma && !dst->anon_vma) { int ret; vma_assert_write_locked(dst); dst->anon_vma = src->anon_vma; ret = anon_vma_clone(dst, src); if (ret) return ret; *dup = dst; } return 0; } /* * vma_expand - Expand an existing VMA * * @vmi: The vma iterator * @vma: The vma to expand * @start: The start of the vma * @end: The exclusive end of the vma * @pgoff: The page offset of vma * @next: The current of next vma. * * Expand @vma to @start and @end. Can expand off the start and end. Will * expand over @next if it's different from @vma and @end == @next->vm_end. * Checking if the @vma can expand and merge with @next needs to be handled by * the caller. * * Returns: 0 on success */ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *next) { struct vm_area_struct *anon_dup = NULL; bool remove_next = false; struct vma_prepare vp; vma_start_write(vma); if (next && (vma != next) && (end == next->vm_end)) { int ret; remove_next = true; vma_start_write(next); ret = dup_anon_vma(vma, next, &anon_dup); if (ret) return ret; } init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON(next && !vp.remove && next != vma && end > next->vm_start); /* Only handles expanding */ VM_WARN_ON(vma->vm_start < start || vma->vm_end > end); /* Note: vma iterator must be pointing to 'start' */ vma_iter_config(vmi, start, end); if (vma_iter_prealloc(vmi, vma)) goto nomem; vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); vma_set_range(vma, start, end, pgoff); vma_iter_store(vmi, vma); vma_complete(&vp, vmi, vma->vm_mm); return 0; nomem: if (anon_dup) unlink_anon_vmas(anon_dup); return -ENOMEM; } /* * vma_shrink() - Reduce an existing VMAs memory area * @vmi: The vma iterator * @vma: The VMA to modify * @start: The new start * @end: The new end * * Returns: 0 on success, -ENOMEM otherwise */ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { struct vma_prepare vp; WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); if (vma->vm_start < start) vma_iter_config(vmi, vma->vm_start, start); else vma_iter_config(vmi, end, vma->vm_end); if (vma_iter_prealloc(vmi, NULL)) return -ENOMEM; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); vma_iter_clear(vmi); vma_set_range(vma, start, end, pgoff); vma_complete(&vp, vmi, vma->vm_mm); return 0; } /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those if the caller indicates * the current vma may be removed as part of the merge. */ static inline bool is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name, bool may_remove_vma) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return false; if (vma->vm_file != file) return false; if (may_remove_vma && vma->vm_ops && vma->vm_ops->close) return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return false; if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) return false; return true; } static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return true; return anon_vma1 == anon_vma2; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. * * We assume the vma may be removed as part of the merge. */ static bool can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return true; } return false; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We assume that vma is not removed as part of the merge. */ static bool can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, false) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return true; } return false; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), * figure out whether that can be merged with its predecessor or its * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when * called for mprotect, it is certain to be already mapped (either at * an offset within prev, or at the start of next), and the flags of * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * * The following mprotect cases have to be considered, where **** is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPP is the previous vma, CCCC is a concurrent vma that starts * at the same address as **** and is of the same or larger span, and * NNNN the next vma after ****: * * **** **** **** * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPCCCCCC * cannot merge might become might become * PPNNNNNNNNNN PPPPPPPPPPCC * mmap, brk or case 4 below case 5 below * mremap move: * **** **** * PPPP NNNN PPPPCCCCNNNN * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or * PPPPPPPPNNNN 2 or PPPPPPPPNNNN 7 or * PPPPNNNNNNNN 3 PPPPNNNNNNNN 8 * * It is important for case 8 that the vma CCCC overlapping the * region **** is never going to extended over NNNN. Instead NNNN must * be extended in region **** and CCCC must be removed. This way in * all cases where vma_merge succeeds, the moment vma_merge drops the * rmap_locks, the properties of the merged vma will be already * correct for the whole merged range. Some of those properties like * vm_page_prot/vm_flags may be accessed by rmap_walks and they must * be correct for the whole merged range immediately after the * rmap_locks are released. Otherwise if NNNN would be removed and * CCCC would be extended over the NNNN range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of CCCC * instead of the right permissions of NNNN. * * In the code below: * PPPP is represented by *prev * CCCC is represented by *curr or not represented at all (NULL) * NNNN is represented by *next or not represented at all (NULL) * **** is not represented - it will be merged and the vma containing the * area is returned, or the function will return NULL */ static struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *src, unsigned long addr, unsigned long end, unsigned long vm_flags, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { struct mm_struct *mm = src->vm_mm; struct anon_vma *anon_vma = src->anon_vma; struct file *file = src->vm_file; struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; struct vm_area_struct *anon_dup = NULL; struct vma_prepare vp; pgoff_t vma_pgoff; int err = 0; bool merge_prev = false; bool merge_next = false; bool vma_expanded = false; unsigned long vma_start = addr; unsigned long vma_end = end; pgoff_t pglen = (end - addr) >> PAGE_SHIFT; long adj_start = 0; /* * We later require that vma->vm_flags == vm_flags, * so this tests vma->vm_flags & VM_SPECIAL, too. */ if (vm_flags & VM_SPECIAL) return NULL; /* Does the input range span an existing VMA? (cases 5 - 8) */ curr = find_vma_intersection(mm, prev ? prev->vm_end : 0, end); if (!curr || /* cases 1 - 4 */ end == curr->vm_end) /* cases 6 - 8, adjacent VMA */ next = vma_lookup(mm, end); else next = NULL; /* case 5 */ if (prev) { vma_start = prev->vm_start; vma_pgoff = prev->vm_pgoff; /* Can we merge the predecessor? */ if (addr == prev->vm_end && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, vm_userfaultfd_ctx, anon_name)) { merge_prev = true; vma_prev(vmi); } } /* Can we merge the successor? */ if (next && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx, anon_name)) { merge_next = true; } /* Verify some invariant that must be enforced by the caller. */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); VM_WARN_ON(addr >= end); if (!merge_prev && !merge_next) return NULL; /* Not mergeable. */ if (merge_prev) vma_start_write(prev); res = vma = prev; remove = remove2 = adjust = NULL; /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { vma_start_write(next); remove = next; /* case 1 */ vma_end = next->vm_end; err = dup_anon_vma(prev, next, &anon_dup); if (curr) { /* case 6 */ vma_start_write(curr); remove = curr; remove2 = next; /* * Note that the dup_anon_vma below cannot overwrite err * since the first caller would do nothing unless next * has an anon_vma. */ if (!next->anon_vma) err = dup_anon_vma(prev, curr, &anon_dup); } } else if (merge_prev) { /* case 2 */ if (curr) { vma_start_write(curr); if (end == curr->vm_end) { /* case 7 */ /* * can_vma_merge_after() assumed we would not be * removing prev vma, so it skipped the check * for vm_ops->close, but we are removing curr */ if (curr->vm_ops && curr->vm_ops->close) err = -EINVAL; remove = curr; } else { /* case 5 */ adjust = curr; adj_start = (end - curr->vm_start); } if (!err) err = dup_anon_vma(prev, curr, &anon_dup); } } else { /* merge_next */ vma_start_write(next); res = next; if (prev && addr < prev->vm_end) { /* case 4 */ vma_start_write(prev); vma_end = addr; adjust = next; adj_start = -(prev->vm_end - addr); err = dup_anon_vma(next, prev, &anon_dup); } else { /* * Note that cases 3 and 8 are the ONLY ones where prev * is permitted to be (but is not necessarily) NULL. */ vma = next; /* case 3 */ vma_start = addr; vma_end = next->vm_end; vma_pgoff = next->vm_pgoff - pglen; if (curr) { /* case 8 */ vma_pgoff = curr->vm_pgoff; vma_start_write(curr); remove = curr; err = dup_anon_vma(next, curr, &anon_dup); } } } /* Error in anon_vma clone. */ if (err) goto anon_vma_fail; if (vma_start < vma->vm_start || vma_end > vma->vm_end) vma_expanded = true; if (vma_expanded) { vma_iter_config(vmi, vma_start, vma_end); } else { vma_iter_config(vmi, adjust->vm_start + adj_start, adjust->vm_end); } if (vma_iter_prealloc(vmi, vma)) goto prealloc_fail; init_multi_vma_prep(&vp, vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && vp.anon_vma != adjust->anon_vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); vma_set_range(vma, vma_start, vma_end, vma_pgoff); if (vma_expanded) vma_iter_store(vmi, vma); if (adj_start) { adjust->vm_start += adj_start; adjust->vm_pgoff += adj_start >> PAGE_SHIFT; if (adj_start < 0) { WARN_ON(vma_expanded); vma_iter_store(vmi, next); } } vma_complete(&vp, vmi, mm); khugepaged_enter_vma(res, vm_flags); return res; prealloc_fail: if (anon_dup) unlink_anon_vmas(anon_dup); anon_vma_fail: vma_iter_set(vmi, addr); vma_iter_load(vmi); return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); /* Try next first. */ next = vma_iter_load(&vmi); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } prev = vma_prev(&vmi); VM_BUG_ON_VMA(prev != vma, vma); prev = vma_prev(&vmi); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes) { unsigned long locked_pages, limit_pages; if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) return true; locked_pages = bytes >> PAGE_SHIFT; locked_pages += mm->locked_vm; limit_pages = rlimit(RLIMIT_MEMLOCK); limit_pages >>= PAGE_SHIFT; return locked_pages <= limit_pages; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_mode & FMODE_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /* * The caller must write-lock current->mm->mmap_lock. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; int pkey = 0; *populate = 0; if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we don't add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* * addr is returned from get_unmapped_area, * There are two cases: * 1> MAP_FIXED == false * unallocated memory, no need to check sealing. * 1> MAP_FIXED == true * sealing is checked inside mmap_region when * do_vmi_munmap is called. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (!mlock_future_ok(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK; if (file->f_op->fop_flags & FOP_MMAP_SYNC) flags_mask |= MAP_SYNC; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!file->f_op->mmap) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) { return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); } static bool vma_is_shared_writable(struct vm_area_struct *vma) { return (vma->vm_flags & (VM_WRITE | VM_SHARED)) == (VM_WRITE | VM_SHARED); } static bool vma_fs_can_writeback(struct vm_area_struct *vma) { /* No managed pages to writeback. */ if (vma->vm_flags & VM_PFNMAP) return false; return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * Does this VMA require the underlying folios to have their dirty state * tracked? */ bool vma_needs_dirty_tracking(struct vm_area_struct *vma) { /* Only shared, writable VMAs require dirty tracking. */ if (!vma_is_shared_writable(vma)) return false; /* Does the filesystem need to be notified? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* * Even if the filesystem doesn't indicate a need for writenotify, if it * can writeback, dirty tracking is still required. */ return vma_fs_can_writeback(vma); } /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { /* If it was private or non-writable, the write bit is already clear */ if (!vma_is_shared_writable(vma)) return false; /* The backer wishes to know when pages are first written to? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) return false; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return true; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) return true; /* Can the mapping track the dirty pages? */ return vma_fs_can_writeback(vma); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static inline bool accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return false; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } /** * unmapped_area() - Find an area between the low_limit and the high_limit with * the correct alignment and offset, all from @info. Note: current->mm is used * for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { unsigned long length, gap; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) return -ENOMEM; /* * Adjust for the gap first so it doesn't interfere with the * later alignment. The first step is the minimum needed to * fulill the start gap, the next steps is the minimum to align * that. It is the minimum needed to fulill both. */ gap = vma_iter_addr(&vmi) + info->start_gap; gap += (info->align_offset - gap) & info->align_mask; tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap + length - 1) { low_limit = tmp->vm_end; vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { low_limit = vm_end_gap(tmp); vma_iter_reset(&vmi); goto retry; } } return gap; } /** * unmapped_area_topdown() - Find an area between the low_limit and the * high_limit with the correct alignment and offset at the highest available * address, all from @info. Note: current->mm is used for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { unsigned long length, gap, gap_end; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) return -ENOMEM; gap = vma_iter_end(&vmi) - info->length; gap -= (gap - info->align_offset) & info->align_mask; gap_end = vma_iter_end(&vmi); tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap_end) { high_limit = vm_start_gap(tmp); vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { high_limit = tmp->vm_start; vma_iter_reset(&vmi); goto retry; } } return gap; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; return vm_unmapped_area(&info); } #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_get_unmapped_area(filp, addr, len, pgoff, flags); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } #endif #ifndef HAVE_ARCH_UNMAPPED_AREA_VMFLAGS unsigned long arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area(filp, addr, len, pgoff, flags); } unsigned long arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } #endif unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, vm_flags); return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, vm_flags); } unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. */ get_area = shmem_get_unmapped_area; } /* Always treat pgoff as zero for anonymous memory. */ if (!file) pgoff = 0; if (get_area) { addr = get_area(file, addr, len, pgoff, flags); } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); } else { addr = mm_get_unmapped_area_vmflags(current->mm, file, addr, len, pgoff, flags, vm_flags); } if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags); return arch_get_unmapped_area(file, addr, len, pgoff, flags); } EXPORT_SYMBOL(mm_get_unmapped_area); /** * find_vma_intersection() - Look up the first VMA which intersects the interval * @mm: The process address space. * @start_addr: The inclusive start user address. * @end_addr: The exclusive end user address. * * Returns: The first VMA within the provided range, %NULL otherwise. Assumes * start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { unsigned long index = start_addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, end_addr - 1); } EXPORT_SYMBOL(find_vma_intersection); /** * find_vma() - Find the VMA for a given address, or the next VMA. * @mm: The mm_struct to check * @addr: The address * * Returns: The VMA associated with addr, or the next VMA. * May return %NULL in the case of no VMA at addr or above. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { unsigned long index = addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, ULONG_MAX); } EXPORT_SYMBOL(find_vma); /** * find_vma_prev() - Find the VMA for a given address, or the next vma and * set %pprev to the previous VMA, if any. * @mm: The mm_struct to check * @addr: The address * @pprev: The pointer to set to the previous VMA * * Note that RCU lock is missing here since the external mmap_lock() is used * instead. * * Returns: The VMA associated with @addr, or the next vma. * May return %NULL in the case of no vma at addr or above. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, addr); vma = vma_iter_load(&vmi); *pprev = vma_prev(&vmi); if (!vma) vma = vma_next(&vmi); return vma; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT)) return -ENOMEM; /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #if defined(CONFIG_STACK_GROWSUP) /* * PA-RISC uses this for its stack. * vma is the last one with address > vma->vm_end. Have to extend vma. */ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } if (next) vma_iter_prev_range_limit(&vmi, address); vma_iter_config(&vmi, vma->vm_start, address); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * We only hold a shared mmap_lock lock here, so * we need to protect against concurrent vma * expansions. anon_vma_lock_write() doesn't * help here, as we don't guarantee that all * growable vmas in a mm share the same root * anon vma. So, we reuse mm->page_table_lock * to guard against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. * mmap_lock held for writing. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSDOWN)) return -EFAULT; address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; /* Enforce stack_guard_gap */ prev = vma_prev(&vmi); /* Check that both stack segments have the same anon_vma? */ if (prev) { if (!(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev) && (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; } if (prev) vma_iter_next_range_limit(&vmi, vma->vm_start); vma_iter_config(&vmi, address, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * We only hold a shared mmap_lock lock here, so * we need to protect against concurrent vma * expansions. anon_vma_lock_write() doesn't * help here, as we don't guarantee that all * growable vmas in a mm share the same root * anon vma. So, we reuse mm->page_table_lock * to guard against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; static int __init cmdline_parse_stack_guard_gap(char *p) { unsigned long val; char *endptr; val = simple_strtoul(p, &endptr, 10); if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); #ifdef CONFIG_STACK_GROWSUP int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; if (!prev) return NULL; if (expand_stack_locked(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm, addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; start = vma->vm_start; if (expand_stack_locked(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif #if defined(CONFIG_STACK_GROWSUP) #define vma_expand_up(vma,addr) expand_upwards(vma, addr) #define vma_expand_down(vma, addr) (-EFAULT) #else #define vma_expand_up(vma,addr) (-EFAULT) #define vma_expand_down(vma, addr) expand_downwards(vma, addr) #endif /* * expand_stack(): legacy interface for page faulting. Don't use unless * you have to. * * This is called with the mm locked for reading, drops the lock, takes * the lock for writing, tries to look up a vma again, expands it if * necessary, and downgrades the lock to reading again. * * If no vma is found or it can't be expanded, it returns NULL and has * dropped the lock. */ struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; mmap_read_unlock(mm); if (mmap_write_lock_killable(mm)) return NULL; vma = find_vma_prev(mm, addr, &prev); if (vma && vma->vm_start <= addr) goto success; if (prev && !vma_expand_up(prev, addr)) { vma = prev; goto success; } if (vma && !vma_expand_down(vma, addr)) goto success; mmap_write_unlock(mm); return NULL; success: mmap_write_downgrade(mm); return vma; } /* * Ok - we have the memory areas we should free on a maple tree so release them, * and do the vma updates. * * Called with the mm semaphore held. */ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas) { unsigned long nr_accounted = 0; struct vm_area_struct *vma; /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); mas_for_each(mas, vma, ULONG_MAX) { long nrpages = vma_pages(vma); if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; vm_stat_account(mm, vma->vm_flags, -nrpages); remove_vma(vma, false); } vm_unacct_memory(nr_accounted); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ static void unmap_region(struct mm_struct *mm, struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked) { struct mmu_gather tlb; unsigned long mt_start = mas->index; lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); unmap_vmas(&tlb, mas, vma, start, end, tree_end, mm_wr_locked); mas_set(mas, mt_start); free_pgtables(&tlb, mas, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING, mm_wr_locked); tlb_finish_mmu(&tlb); } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the end VMA. */ static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; int err; WARN_ON(vma->vm_start >= addr); WARN_ON(vma->vm_end <= addr); if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) { new->vm_end = addr; } else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = -ENOMEM; vma_iter_config(vmi, new->vm_start, new->vm_end); if (vma_iter_prealloc(vmi, new)) goto out_free_vma; err = vma_dup_policy(vma, new); if (err) goto out_free_vmi; err = anon_vma_clone(new, vma); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); vma_start_write(vma); vma_start_write(new); init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); if (new_below) { vma->vm_start = addr; vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT; } else { vma->vm_end = addr; } /* vma_complete stores the new vma */ vma_complete(&vp, vmi, vma->vm_mm); /* Success. */ if (new_below) vma_next(vmi); return 0; out_free_mpol: mpol_put(vma_policy(new)); out_free_vmi: vma_iter_free(vmi); out_free_vma: vm_area_free(new); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (vma->vm_mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(vmi, vma, addr, new_below); } /* * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd * context and anonymous VMA name within the range [start, end). * * As a result, we might be able to merge the newly modified VMA range with an * adjacent VMA with identical properties. * * If no merge is possible and the range does not span the entirety of the VMA, * we then need to split the VMA to accommodate the change. * * The function returns either the merged VMA, the original VMA if a split was * required instead, or an error if the split failed. */ struct vm_area_struct *vma_modify(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long vm_flags, struct mempolicy *policy, struct vm_userfaultfd_ctx uffd_ctx, struct anon_vma_name *anon_name) { pgoff_t pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); struct vm_area_struct *merged; merged = vma_merge(vmi, prev, vma, start, end, vm_flags, pgoff, policy, uffd_ctx, anon_name); if (merged) return merged; if (vma->vm_start < start) { int err = split_vma(vmi, vma, start, 1); if (err) return ERR_PTR(err); } if (vma->vm_end > end) { int err = split_vma(vmi, vma, end, 0); if (err) return ERR_PTR(err); } return vma; } /* * Attempt to merge a newly mapped VMA with those adjacent to it. The caller * must ensure that [start, end) does not overlap any existing VMA. */ static struct vm_area_struct *vma_merge_new_vma(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { return vma_merge(vmi, prev, vma, start, end, vma->vm_flags, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); } /* * Expand vma by delta bytes, potentially merging with an immediately adjacent * VMA with identical properties. */ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta) { pgoff_t pgoff = vma->vm_pgoff + vma_pages(vma); /* vma is specified as prev, so case 1 or 2 will apply. */ return vma_merge(vmi, vma, vma, vma->vm_end, vma->vm_end + delta, vma->vm_flags, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); } /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct * @mm: The mm_struct * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head * @unlock: Set to true to drop the mmap_lock. unlocking only happens on * success. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ static int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { struct vm_area_struct *prev, *next = NULL; struct maple_tree mt_detach; int count = 0; int error = -ENOMEM; unsigned long locked_vm = 0; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(mt_detach); /* * If we need to split any vma, do it now to save pain later. * * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially * unmapped vm_area_struct will remain in use: so lower split_vma * places tmp vma above, and higher split_vma places tmp vma below. */ /* Does it split the first one? */ if (start > vma->vm_start) { /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) goto map_count_exceeded; error = __split_vma(vmi, vma, start, 1); if (error) goto start_split_failed; } /* * Detach a range of VMAs from the mm. Using next as a temp variable as * it is always overwritten. */ next = vma; do { /* Does it split the end? */ if (next->vm_end > end) { error = __split_vma(vmi, next, end, 0); if (error) goto end_split_failed; } vma_start_write(next); mas_set(&mas_detach, count); error = mas_store_gfp(&mas_detach, next, GFP_KERNEL); if (error) goto munmap_gather_failed; vma_mark_detached(next, true); if (next->vm_flags & VM_LOCKED) locked_vm += vma_pages(next); count++; if (unlikely(uf)) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain split, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ error = userfaultfd_unmap_prep(next, start, end, uf); if (error) goto userfaultfd_error; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE BUG_ON(next->vm_start < start); BUG_ON(next->vm_start > end); #endif } for_each_vma_range(*vmi, next, end); #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) /* Make sure no VMAs are about to be lost. */ { MA_STATE(test, &mt_detach, 0, 0); struct vm_area_struct *vma_mas, *vma_test; int test_count = 0; vma_iter_set(vmi, start); rcu_read_lock(); vma_test = mas_find(&test, count - 1); for_each_vma_range(*vmi, vma_mas, end) { BUG_ON(vma_mas != vma_test); test_count++; vma_test = mas_next(&test, count - 1); } rcu_read_unlock(); BUG_ON(count != test_count); } #endif while (vma_iter_addr(vmi) > start) vma_iter_prev_range(vmi); error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL); if (error) goto clear_tree_failed; /* Point of no return */ mm->locked_vm -= locked_vm; mm->map_count -= count; if (unlock) mmap_write_downgrade(mm); prev = vma_iter_prev_range(vmi); next = vma_next(vmi); if (next) vma_iter_prev_range(vmi); /* * We can free page tables without write-locking mmap_lock because VMAs * were isolated before we downgraded mmap_lock. */ mas_set(&mas_detach, 1); unmap_region(mm, &mas_detach, vma, prev, next, start, end, count, !unlock); /* Statistics and freeing VMAs */ mas_set(&mas_detach, 0); remove_mt(mm, &mas_detach); validate_mm(mm); if (unlock) mmap_read_unlock(mm); __mt_destroy(&mt_detach); return 0; clear_tree_failed: userfaultfd_error: munmap_gather_failed: end_split_failed: mas_set(&mas_detach, 0); mas_for_each(&mas_detach, next, end) vma_mark_detached(next, false); __mt_destroy(&mt_detach); start_split_failed: map_count_exceeded: validate_mm(mm); return error; } /* * do_vmi_munmap() - munmap a given range. * @vmi: The vma iterator * @mm: The mm_struct * @start: The start address to munmap * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @unlock: set to true if the user wants to drop the mmap_lock on success * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be * aligned and any arch_unmap work will be preformed. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock) { unsigned long end; struct vm_area_struct *vma; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; end = start + PAGE_ALIGN(len); if (end == start) return -EINVAL; /* * Check if memory is sealed before arch_unmap. * Prevent unmapping a sealed VMA. * can_modify_mm assumes we have acquired the lock on MM. */ if (unlikely(!can_modify_mm(mm, start, end))) return -EPERM; /* arch_unmap() might do unmaps itself. */ arch_unmap(mm, start, end); /* Find the first overlapping VMA */ vma = vma_find(vmi, end); if (!vma) { if (unlock) mmap_write_unlock(mm); return 0; } return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } /* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls. * @mm: The mm_struct * @start: The start address to munmap * @len: The length to be munmapped. * @uf: The userfaultfd list_head * * Return: 0 on success, error otherwise. */ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { VMA_ITERATOR(vmi, mm, start); return do_vmi_munmap(&vmi, mm, start, len, uf, false); } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct vm_area_struct *next, *prev, *merge; pgoff_t pglen = len >> PAGE_SHIFT; unsigned long charged = 0; unsigned long end = addr + len; unsigned long merge_start = addr, merge_end = end; bool writable_file_mapping = false; pgoff_t vm_pgoff; int error; VMA_ITERATOR(vmi, mm, addr); /* Check against address space limit. */ if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* * MAP_FIXED may remove pages of mappings that intersects with * requested mapping. Account for the pages it would unmap. */ nr_pages = count_vma_pages_range(mm, addr, end); if (!may_expand_vm(mm, vm_flags, (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } /* Unmap any existing mapping in the area */ error = do_vmi_munmap(&vmi, mm, addr, len, uf, false); if (error == -EPERM) return error; else if (error) return -ENOMEM; /* * Private writable mapping: check memory availability */ if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; } next = vma_next(&vmi); prev = vma_prev(&vmi); if (vm_flags & VM_SPECIAL) { if (prev) vma_iter_next_range(&vmi); goto cannot_expand; } /* Attempt to expand an old mapping */ /* Check next */ if (next && next->vm_start == end && !vma_policy(next) && can_vma_merge_before(next, vm_flags, NULL, file, pgoff+pglen, NULL_VM_UFFD_CTX, NULL)) { merge_end = next->vm_end; vma = next; vm_pgoff = next->vm_pgoff - pglen; } /* Check prev */ if (prev && prev->vm_end == addr && !vma_policy(prev) && (vma ? can_vma_merge_after(prev, vm_flags, vma->anon_vma, file, pgoff, vma->vm_userfaultfd_ctx, NULL) : can_vma_merge_after(prev, vm_flags, NULL, file, pgoff, NULL_VM_UFFD_CTX, NULL))) { merge_start = prev->vm_start; vma = prev; vm_pgoff = prev->vm_pgoff; } else if (prev) { vma_iter_next_range(&vmi); } /* Actually expand, if possible */ if (vma && !vma_expand(&vmi, vma, merge_start, merge_end, vm_pgoff, next)) { khugepaged_enter_vma(vma, vm_flags); goto expanded; } if (vma == prev) vma_iter_set(&vmi, addr); cannot_expand: /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } vma_iter_config(&vmi, addr, end); vma_set_range(vma, addr, end, pgoff); vm_flags_init(vma, vm_flags); vma->vm_page_prot = vm_get_page_prot(vm_flags); if (file) { vma->vm_file = get_file(file); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; if (vma_is_shared_maywrite(vma)) { error = mapping_map_writable(file->f_mapping); if (error) goto close_and_free_vma; writable_file_mapping = true; } /* * Expansion is handled above, merging is handled below. * Drivers should not alter the address of the VMA. */ error = -EINVAL; if (WARN_ON((addr != vma->vm_start))) goto close_and_free_vma; vma_iter_config(&vmi, addr, end); /* * If vm_flags changed after call_mmap(), we should try merge * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge_new_vma(&vmi, prev, vma, vma->vm_start, vma->vm_end, vma->vm_pgoff); if (merge) { /* * ->mmap() can change vma->vm_file and fput * the original file. So fput the vma->vm_file * here or we would add an extra fput for file * and cause general protection fault * ultimately. */ fput(vma->vm_file); vm_area_free(vma); vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } else { vma_set_anonymous(vma); } if (map_deny_write_exec(vma, vma->vm_flags)) { error = -EACCES; goto close_and_free_vma; } /* Allow architectures to sanity-check the vm_flags */ error = -EINVAL; if (!arch_validate_flags(vma->vm_flags)) goto close_and_free_vma; error = -ENOMEM; if (vma_iter_prealloc(&vmi, vma)) goto close_and_free_vma; /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); vma_iter_store(&vmi, vma); mm->map_count++; vma_link_file(vma); /* * vma_merge() calls khugepaged_enter_vma() either, the below * call covers the non-merge case. */ khugepaged_enter_vma(vma, vma->vm_flags); /* Once vma denies write, undo our temporary denial count */ unmap_writable: if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); file = vma->vm_file; ksm_add_vma(vma); expanded: perf_event_mmap(vma); vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) vm_flags_clear(vma, VM_LOCKED_MASK); else mm->locked_vm += (len >> PAGE_SHIFT); } if (file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vm_flags_set(vma, VM_SOFTDIRTY); vma_set_page_prot(vma); validate_mm(mm); return addr; close_and_free_vma: if (file && vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (file || vma->vm_file) { unmap_and_free_vma: fput(vma->vm_file); vma->vm_file = NULL; vma_iter_set(&vmi, vma->vm_end); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, vma->vm_end, vma->vm_end, true); } if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); free_vma: vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); validate_mm(mm); return error; } static int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, start); if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock); if (ret || !unlock) mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); return ret; } int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); return __vm_munmap(addr, len, true); } /* * Emulation of deprecated remap_file_pages() syscall. */ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_write_lock_killable(mm)) return -EINTR; vma = vma_lookup(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; if (start + size > vma->vm_end) { VMA_ITERATOR(vmi, mm, vma->vm_end); struct vm_area_struct *next, *prev = vma; for_each_vma_range(vmi, next, start + size) { /* hole between vmas ? */ if (next->vm_start != prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; prev = next; } if (!next) goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; file = get_file(vma->vm_file); ret = do_mmap(vma->vm_file, start, size, prot, flags, 0, pgoff, &populate, NULL); fput(file); out: mmap_write_unlock(mm); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } /* * do_vma_munmap() - Unmap a full or partial vma. * @vmi: The vma iterator pointing at the vma * @vma: The first vma to be munmapped * @start: the start of the address to unmap * @end: The end of the address to unmap * @uf: The userfaultfd list_head * @unlock: Drop the lock on success * * unmaps a VMA mapping when the vma iterator is already in position. * Does not handle alignment. * * Return: 0 on success drops the lock of so directed, error on failure and will * still hold the lock. */ int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { struct mm_struct *mm = vma->vm_mm; /* * Check if memory is sealed before arch_unmap. * Prevent unmapping a sealed VMA. * can_modify_mm assumes we have acquired the lock on MM. */ if (unlikely(!can_modify_mm(mm, start, end))) return -EPERM; arch_unmap(mm, start, end); return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } /* * do_brk_flags() - Increase the brk vma if the flags match. * @vmi: The vma iterator * @addr: The start address * @len: The length of the increase * @vma: The vma, * @flags: The VMA Flags * * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags * do not match then create a new anonymous VMA. Eventually we may be able to * do some brk-specific accounting here. */ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, unsigned long len, unsigned long flags) { struct mm_struct *mm = current->mm; struct vma_prepare vp; /* * Check against address space limits by the changed size * Note: This happens *after* clearing old mappings in some code paths. */ flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ if (vma && vma->vm_end == addr && !vma_policy(vma) && can_vma_merge_after(vma, flags, NULL, NULL, addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) { vma_iter_config(vmi, vma->vm_start, addr + len); if (vma_iter_prealloc(vmi, vma)) goto unacct_fail; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); vma->vm_end = addr + len; vm_flags_set(vma, VM_SOFTDIRTY); vma_iter_store(vmi, vma); vma_complete(&vp, vmi, mm); khugepaged_enter_vma(vma, flags); goto out; } if (vma) vma_iter_next_range(vmi); /* create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) goto unacct_fail; vma_set_anonymous(vma); vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT); vm_flags_init(vma, flags); vma->vm_page_prot = vm_get_page_prot(flags); vma_start_write(vma); if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) goto mas_store_fail; mm->map_count++; validate_mm(mm); ksm_add_vma(vma); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vm_flags_set(vma, VM_SOFTDIRTY); return 0; mas_store_fail: vm_area_free(vma); unacct_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; unsigned long len; int ret; bool populate; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, addr); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; if (mmap_write_lock_killable(mm)) return -EINTR; ret = check_brk_limits(addr, len); if (ret) goto limits_failed; ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0); if (ret) goto munmap_failed; vma = vma_prev(&vmi); ret = do_brk_flags(&vmi, vma, addr, len, flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; munmap_failed: limits_failed: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(vm_brk_flags); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; VMA_ITERATOR(vmi, mm, 0); int count = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); mmap_read_lock(mm); arch_exit_mmap(mm); vma = vma_next(&vmi); if (!vma || unlikely(xa_is_zero(vma))) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); mmap_write_lock(mm); goto destroy; } lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, &vmi.mas, vma, 0, ULONG_MAX, ULONG_MAX, false); mmap_read_unlock(mm); /* * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper * because the memory has been already freed. */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mt_clear_in_rcu(&mm->mm_mt); vma_iter_set(&vmi, vma->vm_end); free_pgtables(&tlb, &vmi.mas, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING, true); tlb_finish_mmu(&tlb); /* * Walk the list again, actually closing and freeing it, with preemption * enabled, without holding any MM locks besides the unreachable * mmap_write_lock. */ vma_iter_set(&vmi, vma->vm_end); do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); remove_vma(vma, true); count++; cond_resched(); vma = vma_next(&vmi); } while (vma && likely(!xa_is_zero(vma))); BUG_ON(count != mm->map_count); trace_exit_mmap(mm); destroy: __mt_destroy(&mm->mm_mt); mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { unsigned long charged = vma_pages(vma); if (find_vma_intersection(mm, vma->vm_start, vma->vm_end)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap and in do_brk_flags. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } if (vma_link(mm, vma)) { if (vma->vm_flags & VM_ACCOUNT) vm_unacct_memory(charged); return -ENOMEM; } return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; bool faulted_in_anon_vma = true; VMA_ITERATOR(vmi, mm, addr); /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } new_vma = find_vma_prev(mm, addr, &prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ new_vma = vma_merge_new_vma(&vmi, prev, vma, addr, addr + len, pgoff); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; vma_set_range(new_vma, addr, addr + len, pgoff); if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; } return new_vma; out_vma_link: if (new_vma->vm_ops && new_vma->vm_ops->close) new_vma->vm_ops->close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr) { /* * Forbid splitting special mappings - kernel has expectations over * the number of pages in mapping. Together with VM_DONTEXPAND * the size of vma should stay the same over the special mapping's * lifetime. */ return -EINVAL; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, .may_split = special_mapping_split, }; static const struct vm_operations_struct legacy_special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; if (vma->vm_ops == &legacy_special_mapping_vmops) { pages = vma->vm_private_data; } else { struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; } for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma_set_range(vma, addr, addr + len, 0); vm_flags_init(vma, (vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); return vma; out: vm_area_free(vma); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && (vma->vm_ops == &special_mapping_vmops || vma->vm_ops == &legacy_special_mapping_vmops); } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { struct vm_area_struct *vma = __install_special_mapping( mm, addr, len, vm_flags, (void *)pages, &legacy_special_mapping_vmops); return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); /* * vma_start_write() does not have a complement in mm_drop_all_locks() * because vma_start_write() is always asymmetrical; it marks a VMA as * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * initialise the percpu counter for VM */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (tmp > 0 && tmp < SZ_128K) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (tmp > 0 && tmp < SZ_8K) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static int __meminit init_reserve_notifier(void) { if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier); |
| 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned int nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { struct folio *folio; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false); if (folio) clear_user_highpage(&folio->page, vaddr); return folio; } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) { } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_highmem(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } static inline void unmap_and_put_page(struct page *page, void *addr) { folio_release_kmap(page_folio(page), addr); } #endif /* _LINUX_HIGHMEM_H */ |
| 337 2 48 337 336 337 338 337 274 110 233 234 175 234 180 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/cpumask.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU // Bits for ->trc_reader_special.b.need_qs field. #define TRC_NEED_QS 0x1 // Task needs a quiescent state. #define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); void rcu_tasks_trace_qs_blkd(struct task_struct *t); # define rcu_tasks_trace_qs(t) \ do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs(t); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, local) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)); \ }) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as is * the case in the context of the RCU callback that is freeing up the data, * or after a synchronize_rcu() returns. This can be useful when tearing * down multi-linked structures after a grace period has elapsed. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also * wait for regions of code with preemption disabled, including regions of * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which * define synchronize_sched(), only code enclosed within rcu_read_lock() * and rcu_read_unlock() are guaranteed to be waited for. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. * In recent kernels that have consolidated synchronize_sched() and * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity * also extends to the scheduler's runqueue and priority-inheritance * spinlocks, courtesy of the quiescent-state deferral that is carried * out when rcu_read_unlock() is invoked with interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * The object to be freed can be allocated either by kmalloc() or * kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, do { rcu_read_lock(); /* * sparse doesn't call the cleanup function, * so just release immediately and don't track * the context. We don't need to anyway, since * the whole point of the guard is to not need * the explicit unlock. */ __release(RCU); } while (0), rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ |
| 2 33 128 128 127 128 41 40 130 134 63 10 11 7 2 2 2 2 5 5 132 62 132 132 132 132 132 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/tracepoint-defs.h> struct folio_batch; /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */ #define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */ #define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (flags & FPB_IGNORE_DIRTY) pte = pte_mkclean(pte); if (likely(flags & FPB_IGNORE_SOFT_DIRTY)) pte = pte_clear_soft_dirty(pte); return pte_wrprotect(pte_mkold(pte)); } /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @addr: The user virtual address the first page is mapped at. * @start_ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. * @any_dirty: Optional pointer to indicate whether any entry except the * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY). * * start_ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; if (any_dirty) *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; while (ptep < end_ptep) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); if (any_dirty) dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) break; /* * Stop immediately once we reached the end of the folio. In * corner cases the next PFN might fall into a different * folio. */ if (pte_pfn(pte) >= folio_end_pfn) break; if (any_writable) *any_writable |= writable; if (any_young) *any_young |= young; if (any_dirty) *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); ptep += nr; } return min(ptep - start_ptep, max_nr); } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + 1))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; pte_t *ptep = start_ptep + 1; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte))); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t vmf_anon_prepare(struct vm_fault *vmf); vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool isolate_lru_page(struct page *page); bool folio_isolate_lru(struct folio *folio); void putback_lru_page(struct page *page); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef CONFIG_64BIT folio->_folio_nr_pages = 1U << order; #endif } void folio_undo_large_rmappable(struct folio *folio); static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; void free_unref_page(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end, int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area (including shadow stacks) * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ struct anon_vma *folio_anon_vma(struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif /* * mm/memory-failure.c */ void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags pagetype_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int page_nid, int *flags); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_page(struct page *page); /* * mm/gup.c */ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); int __must_check try_grab_page(struct page *page, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); /* * mm/mmap.c */ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta); enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; extern bool memblock_has_mirror(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline void vma_iter_config(struct vma_iterator *vmi, unsigned long index, unsigned long last) { __mas_set_range(&vmi->mas, index, last - 1); } static inline void vma_iter_reset(struct vma_iterator *vmi) { mas_reset(&vmi->mas); } static inline struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev_range(&vmi->mas, min); } static inline struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) { return mas_next_range(&vmi->mas, max); } static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area(&vmi->mas, min, max - 1, size); } static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area_rev(&vmi->mas, min, max - 1, size); } /* * VMA Iterator functions shared between nommu and mmap */ static inline int vma_iter_prealloc(struct vma_iterator *vmi, struct vm_area_struct *vma) { return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); } static inline void vma_iter_clear(struct vma_iterator *vmi) { mas_store_prealloc(&vmi->mas, NULL); } static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) { return mas_walk(&vmi->mas); } /* Store a VMA with preallocated memory */ static inline void vma_iter_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.index > vma->vm_start)) { pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", vmi->mas.index, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.last < vma->vm_start)) { pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } #endif if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_prealloc(&vmi->mas, vma); } static inline int vma_iter_store_gfp(struct vma_iterator *vmi, struct vm_area_struct *vma, gfp_t gfp) { if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_gfp(&vmi->mas, vma, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } /* * VMA lock generalization */ struct vma_prepare { struct vm_area_struct *vma; struct vm_area_struct *adj_next; struct file *file; struct address_space *mapping; struct anon_vma *anon_vma; struct vm_area_struct *insert; struct vm_area_struct *remove; struct vm_area_struct *remove2; }; void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { if (flags) return -EINVAL; return 0; } bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end); bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior); #else static inline int can_do_mseal(unsigned long flags) { return -EPERM; } static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) { return true; } static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior) { return true; } #endif #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; #endif /* __MM_INTERNAL_H */ |
| 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TASK_WORK_H #define _LINUX_TASK_WORK_H #include <linux/list.h> #include <linux/sched.h> typedef void (*task_work_func_t)(struct callback_head *); static inline void init_task_work(struct callback_head *twork, task_work_func_t func) { twork->func = func; } enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) { return READ_ONCE(task->task_works); } int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) { task_work_run(); } #endif /* _LINUX_TASK_WORK_H */ |
| 14 14 5 5 21 27 23 52 36 124 1 120 120 41 41 171 66 13 46 55 55 36 35 5 5 36 36 36 36 11 46 9 36 6 23 5 114 97 23 32 50 3 214 7 214 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* FMODE_* bits 7 to 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* File is huge (eg. /dev/mem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* FMODE_* bit 24 */ /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the * iocb completion can be passed back to the owner for execution from a safe * context rather than needing to be punted through a workqueue. If this * flag is set, the bio completion handling may set iocb->dio_complete to a * handler function and iocb->private to context information for that handler. * The issuer should call the handler with that context information from task * context to complete the processing of the iocb. Note that while this * provides a task context for the dio_complete() callback, it should only be * used on the completion side for non-IO generating completions. It's fine to * call blocking functions from this callback, but they should not wait for * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ union { /* * Only used for async buffered reads, where it denotes the * page waitqueue associated with completing the read. Valid * IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; /* * Can be used for O_DIRECT IO, where the completion handling * is punted back to the issuer of the IO. May only be set * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer * must then check for presence of this handler when ki_complete * is invoked. The data passed in to this handler must be * assigned to ->private when dio_complete is assigned. */ ssize_t (*dio_complete)(void *data); }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. * @i_private_list: For use by the owner of the address_space. * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; struct timespec64 __i_atime; struct timespec64 __i_mtime; struct timespec64 __i_ctime; /* use inode_*_ctime accessors! */ spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ unsigned long i_state; struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_inode_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned int mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /* * f_{lock,count,pos_lock} members can be highly contended and share * the same cacheline. f_{lock,mode} are very frequently used together * and so share the same cacheline as well. The read-mostly * f_{path,inode,op} are kept on a separate cacheline. */ struct file { union { /* fput() uses task work when closing and freeing file (default). */ struct callback_head f_task_work; /* fput() must use workqueue (most kernel threads). */ struct llist_node f_llist; unsigned int f_iocb_flags; }; /* * Protects f_ep, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; fmode_t f_mode; atomic_long_t f_count; struct mutex f_pos_lock; loff_t f_pos; unsigned int f_flags; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; u64 f_version; #ifdef CONFIG_SECURITY void *f_security; #endif /* needed for tty driver, and maybe others */ void *private_data; #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ struct hlist_head *f_ep; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { long prior = atomic_long_fetch_inc_relaxed(&f->f_count); WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif /* * q: why are s_id and s_sysfs_name not the same? both are human * readable strings that identify the filesystem * a: s_id is allowed to change at runtime; it's used in log messages, * and we want to when a device starts out as single device (s_id is dev * name) but then a device is hot added and we have to switch to * identifying it by UUID * but s_sysfs_name is a handle for programmatic access, and can't * change at runtime */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->__i_atime.tv_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->__i_atime.tv_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { return inode->__i_atime; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->__i_atime = ts; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->__i_mtime.tv_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->__i_mtime.tv_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { return inode->__i_mtime; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->__i_mtime = ts; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->__i_ctime.tv_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->__i_ctime.tv_nsec; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { return inode->__i_ctime; } static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { inode->__i_ctime = ts; return ts; } /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /** * enum freeze_holder - holder of the freeze * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the * same holder aren't allowed. It is however allowed to hold a single * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at * the same time. This is relied upon by some filesystems during online * repair or similar. */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), }; struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *, enum freeze_holder who); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *, enum freeze_holder who); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); void (*shutdown)(struct super_block *sb); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) #define I_DIRTY_DATASYNC (1 << 1) #define I_DIRTY_PAGES (1 << 2) #define __I_NEW 3 #define I_NEW (1 << __I_NEW) #define I_WILL_FREE (1 << 4) #define I_FREEING (1 << 5) #define I_CLEAR (1 << 6) #define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) #define I_REFERENCED (1 << 8) #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode->i_state & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) #define fops_put(fops) \ do { if (fops) module_put((fops)->owner); } while(0) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); int freeze_super(struct super_block *super, enum freeze_holder who); int thaw_super(struct super_block *super, enum freeze_holder who); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regualr file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); /** * is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); #define no_llseek NULL extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif void inode_dio_wait(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) return !!sb->s_encoding; #else return false; #endif } int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; /* * Don't strictly need d_lock here? If the parent ino could change * then surely we'd have a deeper race in the caller? */ spin_lock(&dentry->d_lock); res = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return res; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); #endif /* _LINUX_FS_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/gfp_types.h> #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> #include <linux/sched.h> struct vm_area_struct; struct mempolicy; /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * gfp flag masking for nested internal allocations. * * For code that needs to do allocations inside the public allocation API (e.g. * memory allocation tracking code) the allocations need to obey the caller * allocation context constrains to prevent allocation context mismatches (e.g. * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock * situations. * * It is also assumed that these nested allocations are for internal kernel * object storage purposes only and are not going to be used for DMA, etc. Hence * we strip out all the zone information and leave just the context information * intact. * * Further, internal allocations must fail before the higher level allocation * can fail, so we must make them fail faster and fail silently. We also don't * want them to deplete emergency reserves. Hence nested allocations must be * prepared for these allocations to fail. */ static inline gfp_t gfp_nested_mask(gfp_t flags) { return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the case of non-NUMA systems the NODE_DATA() gets optimized to * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct list_head *page_list, struct page **page_array); #define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); #define alloc_pages_bulk_array_mempolicy(...) \ alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ #define alloc_pages_bulk_list(_gfp, _nr_pages, _list) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) #define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array) static inline unsigned long alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array); } #define alloc_pages_bulk_array_node(...) \ alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__)) static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) return; if (node_online(this_node)) return; pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); dump_stack(); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } #define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) static inline struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); return __folio_alloc_noprof(gfp, order, nid, NULL); } #define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node_noprof(nid, gfp_mask, order); } #define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) #ifdef CONFIG_NUMA struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return alloc_pages_noprof(gfp, order); } static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } #define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ folio_alloc_noprof(gfp, order) #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) #define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr, false); return &folio->page; } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); #define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); #define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); #define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) void free_pages_exact(void *virt, size_t size); __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define alloc_pages_exact_nid(...) \ alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; void page_frag_cache_drain(struct page_frag_cache *nc); extern void __page_frag_cache_drain(struct page *page, unsigned int count); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask); static inline void *page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); } static inline void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask) { return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); } extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); int decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); static inline bool gfp_has_io_fs(gfp_t gfp) { return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS); } /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); #define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); #endif /* __LINUX_GFP_H */ |
| 24 24 4 53 138 134 14 3 46 19 49 48 27 137 49 198 198 193 232 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } #ifdef INLINE_COPY_FROM_USER static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } #else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (check_copy_size(to, n, false)) n = _copy_from_user(to, from, n); return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (check_copy_size(from, n, true)) n = _copy_to_user(to, from, n); return n; } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifndef __get_kernel_nofault #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 299 300 299 298 300 300 300 299 296 299 299 299 300 24 24 24 24 24 24 24 24 24 24 24 24 24 24 3 300 299 299 300 297 298 300 300 299 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 | // SPDX-License-Identifier: GPL-2.0-only /* * FP/SIMD context switching and fault handling * * Copyright (C) 2012 ARM Ltd. * Author: Catalin Marinas <catalin.marinas@arm.com> */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bottom_half.h> #include <linux/bug.h> #include <linux/cache.h> #include <linux/compat.h> #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/linkage.h> #include <linux/irqflags.h> #include <linux/init.h> #include <linux/percpu.h> #include <linux/prctl.h> #include <linux/preempt.h> #include <linux/ptrace.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/signal.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/sysctl.h> #include <linux/swab.h> #include <asm/esr.h> #include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/neon.h> #include <asm/processor.h> #include <asm/simd.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> #include <asm/traps.h> #include <asm/virt.h> #define FPEXC_IOF (1 << 0) #define FPEXC_DZF (1 << 1) #define FPEXC_OFF (1 << 2) #define FPEXC_UFF (1 << 3) #define FPEXC_IXF (1 << 4) #define FPEXC_IDF (1 << 7) /* * (Note: in this discussion, statements about FPSIMD apply equally to SVE.) * * In order to reduce the number of times the FPSIMD state is needlessly saved * and restored, we need to keep track of two things: * (a) for each task, we need to remember which CPU was the last one to have * the task's FPSIMD state loaded into its FPSIMD registers; * (b) for each CPU, we need to remember which task's userland FPSIMD state has * been loaded into its FPSIMD registers most recently, or whether it has * been used to perform kernel mode NEON in the meantime. * * For (a), we add a fpsimd_cpu field to thread_struct, which gets updated to * the id of the current CPU every time the state is loaded onto a CPU. For (b), * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the * address of the userland FPSIMD state of the task that was loaded onto the CPU * the most recently, or NULL if kernel mode NEON has been performed after that. * * With this in place, we no longer have to restore the next FPSIMD state right * when switching between tasks. Instead, we can defer this check to userland * resume, at which time we verify whether the CPU's fpsimd_last_state and the * task's fpsimd_cpu are still mutually in sync. If this is the case, we * can omit the FPSIMD restore. * * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to * indicate whether or not the userland FPSIMD state of the current task is * present in the registers. The flag is set unless the FPSIMD registers of this * CPU currently contain the most recent userland FPSIMD state of the current * task. If the task is behaving as a VMM, then this is will be managed by * KVM which will clear it to indicate that the vcpu FPSIMD state is currently * loaded on the CPU, allowing the state to be saved if a FPSIMD-aware * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and * flag the register state as invalid. * * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be * called from softirq context, which will save the task's FPSIMD context back * to task_struct. To prevent this from racing with the manipulation of the * task's FPSIMD state from task context and thereby corrupting the state, it * is necessary to protect any manipulation of a task's fpsimd_state or * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend * softirq servicing entirely until put_cpu_fpsimd_context() is called. * * For a certain task, the sequence may look something like this: * - the task gets scheduled in; if both the task's fpsimd_cpu field * contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu * variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is * cleared, otherwise it is set; * * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's * userland FPSIMD state is copied from memory to the registers, the task's * fpsimd_cpu field is set to the id of the current CPU, the current * CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the * TIF_FOREIGN_FPSTATE flag is cleared; * * - the task executes an ordinary syscall; upon return to userland, the * TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is * restored; * * - the task executes a syscall which executes some NEON instructions; this is * preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD * register contents to memory, clears the fpsimd_last_state per-cpu variable * and sets the TIF_FOREIGN_FPSTATE flag; * * - the task gets preempted after kernel_neon_end() is called; as we have not * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so * whatever is in the FPSIMD registers is not saved to memory, but discarded. */ static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state); __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = { #ifdef CONFIG_ARM64_SVE [ARM64_VEC_SVE] = { .type = ARM64_VEC_SVE, .name = "SVE", .min_vl = SVE_VL_MIN, .max_vl = SVE_VL_MIN, .max_virtualisable_vl = SVE_VL_MIN, }, #endif #ifdef CONFIG_ARM64_SME [ARM64_VEC_SME] = { .type = ARM64_VEC_SME, .name = "SME", }, #endif }; static unsigned int vec_vl_inherit_flag(enum vec_type type) { switch (type) { case ARM64_VEC_SVE: return TIF_SVE_VL_INHERIT; case ARM64_VEC_SME: return TIF_SME_VL_INHERIT; default: WARN_ON_ONCE(1); return 0; } } struct vl_config { int __default_vl; /* Default VL for tasks */ }; static struct vl_config vl_config[ARM64_VEC_MAX]; static inline int get_default_vl(enum vec_type type) { return READ_ONCE(vl_config[type].__default_vl); } #ifdef CONFIG_ARM64_SVE static inline int get_sve_default_vl(void) { return get_default_vl(ARM64_VEC_SVE); } static inline void set_default_vl(enum vec_type type, int val) { WRITE_ONCE(vl_config[type].__default_vl, val); } static inline void set_sve_default_vl(int val) { set_default_vl(ARM64_VEC_SVE, val); } static void __percpu *efi_sve_state; #else /* ! CONFIG_ARM64_SVE */ /* Dummy declaration for code that will be optimised out: */ extern void __percpu *efi_sve_state; #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int get_sme_default_vl(void) { return get_default_vl(ARM64_VEC_SME); } static void set_sme_default_vl(int val) { set_default_vl(ARM64_VEC_SME, val); } static void sme_free(struct task_struct *); #else static inline void sme_free(struct task_struct *t) { } #endif static void fpsimd_bind_task_to_cpu(void); /* * Claim ownership of the CPU FPSIMD context for use by the calling context. * * The caller may freely manipulate the FPSIMD context metadata until * put_cpu_fpsimd_context() is called. * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom * half processing is always in thread context on RT kernels so it * implicitly prevents bottom half processing as well. */ static void get_cpu_fpsimd_context(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_disable(); else preempt_disable(); } /* * Release the CPU FPSIMD context. * * Must be called from a context in which get_cpu_fpsimd_context() was * previously called, with no call to put_cpu_fpsimd_context() in the * meantime. */ static void put_cpu_fpsimd_context(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } unsigned int task_get_vl(const struct task_struct *task, enum vec_type type) { return task->thread.vl[type]; } void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl) { task->thread.vl[type] = vl; } unsigned int task_get_vl_onexec(const struct task_struct *task, enum vec_type type) { return task->thread.vl_onexec[type]; } void task_set_vl_onexec(struct task_struct *task, enum vec_type type, unsigned long vl) { task->thread.vl_onexec[type] = vl; } /* * TIF_SME controls whether a task can use SME without trapping while * in userspace, when TIF_SME is set then we must have storage * allocated in sve_state and sme_state to store the contents of both ZA * and the SVE registers for both streaming and non-streaming modes. * * If both SVCR.ZA and SVCR.SM are disabled then at any point we * may disable TIF_SME and reenable traps. */ /* * TIF_SVE controls whether a task can use SVE without trapping while * in userspace, and also (together with TIF_SME) the way a task's * FPSIMD/SVE state is stored in thread_struct. * * The kernel uses this flag to track whether a user task is actively * using SVE, and therefore whether full SVE register state needs to * be tracked. If not, the cheaper FPSIMD context handling code can * be used instead of the more costly SVE equivalents. * * * TIF_SVE or SVCR.SM set: * * The task can execute SVE instructions while in userspace without * trapping to the kernel. * * During any syscall, the kernel may optionally clear TIF_SVE and * discard the vector state except for the FPSIMD subset. * * * TIF_SVE clear: * * An attempt by the user task to execute an SVE instruction causes * do_sve_acc() to be called, which does some preparation and then * sets TIF_SVE. * * During any syscall, the kernel may optionally clear TIF_SVE and * discard the vector state except for the FPSIMD subset. * * The data will be stored in one of two formats: * * * FPSIMD only - FP_STATE_FPSIMD: * * When the FPSIMD only state stored task->thread.fp_type is set to * FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in * task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are * logically zero but not stored anywhere; P0-P15 and FFR are not * stored and have unspecified values from userspace's point of * view. For hygiene purposes, the kernel zeroes them on next use, * but userspace is discouraged from relying on this. * * task->thread.sve_state does not need to be non-NULL, valid or any * particular size: it must not be dereferenced and any data stored * there should be considered stale and not referenced. * * * SVE state - FP_STATE_SVE: * * When the full SVE state is stored task->thread.fp_type is set to * FP_STATE_SVE and Z0-Z31 (incorporating Vn in bits[127:0] or the * corresponding Zn), P0-P15 and FFR are encoded in in * task->thread.sve_state, formatted appropriately for vector * length task->thread.sve_vl or, if SVCR.SM is set, * task->thread.sme_vl. The storage for the vector registers in * task->thread.uw.fpsimd_state should be ignored. * * task->thread.sve_state must point to a valid buffer at least * sve_state_size(task) bytes in size. The data stored in * task->thread.uw.fpsimd_state.vregs should be considered stale * and not referenced. * * * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state * irrespective of whether TIF_SVE is clear or set, since these are * not vector length dependent. */ /* * Update current's FPSIMD/SVE registers from thread_struct. * * This function should be called only when the FPSIMD/SVE state in * thread_struct is known to be up to date, when preparing to enter * userspace. */ static void task_fpsimd_load(void) { bool restore_sve_regs = false; bool restore_ffr; WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); if (system_supports_fpmr()) write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: /* Stop tracking SVE for this task until next use. */ if (test_and_clear_thread_flag(TIF_SVE)) sve_user_disable(); break; case FP_STATE_SVE: if (!thread_sm_enabled(¤t->thread) && !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE))) sve_user_enable(); if (test_thread_flag(TIF_SVE)) sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); restore_sve_regs = true; restore_ffr = true; break; default: /* * This indicates either a bug in * fpsimd_save_user_state() or memory corruption, we * should always record an explicit format * when we save. We always at least have the * memory allocated for FPSMID registers so * try that and hope for the best. */ WARN_ON_ONCE(1); clear_thread_flag(TIF_SVE); break; } } /* Restore SME, override SVE register configuration if needed */ if (system_supports_sme()) { unsigned long sme_vl = task_get_sme_vl(current); /* Ensure VL is set up for restoring data */ if (test_thread_flag(TIF_SME)) sme_set_vq(sve_vq_from_vl(sme_vl) - 1); write_sysreg_s(current->thread.svcr, SYS_SVCR); if (thread_za_enabled(¤t->thread)) sme_load_state(current->thread.sme_state, system_supports_sme2()); if (thread_sm_enabled(¤t->thread)) restore_ffr = system_supports_fa64(); } if (restore_sve_regs) { WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE); sve_load_state(sve_pffr(¤t->thread), ¤t->thread.uw.fpsimd_state.fpsr, restore_ffr); } else { WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD); fpsimd_load_state(¤t->thread.uw.fpsimd_state); } } /* * Ensure FPSIMD/SVE storage in memory for the loaded context is up to * date with respect to the CPU registers. Note carefully that the * current context is the context last bound to the CPU stored in * last, if KVM is involved this may be the guest VM context rather * than the host thread for the VM pointed to by current. This means * that we must always reference the state storage via last rather * than via current, if we are saving KVM state then it will have * ensured that the type of registers to save is set in last->to_save. */ static void fpsimd_save_user_state(void) { struct cpu_fp_state const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ bool save_sve_regs = false; bool save_ffr; unsigned int vl; WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; if (system_supports_fpmr()) *(last->fpmr) = read_sysreg_s(SYS_FPMR); /* * If a task is in a syscall the ABI allows us to only * preserve the state shared with FPSIMD so don't bother * saving the full SVE state in that case. */ if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) && !in_syscall(current_pt_regs())) || last->to_save == FP_STATE_SVE) { save_sve_regs = true; save_ffr = true; vl = last->sve_vl; } if (system_supports_sme()) { u64 *svcr = last->svcr; *svcr = read_sysreg_s(SYS_SVCR); if (*svcr & SVCR_ZA_MASK) sme_save_state(last->sme_state, system_supports_sme2()); /* If we are in streaming mode override regular SVE. */ if (*svcr & SVCR_SM_MASK) { save_sve_regs = true; save_ffr = system_supports_fa64(); vl = last->sme_vl; } } if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) { /* Get the configured VL from RDVL, will account for SM */ if (WARN_ON(sve_get_vl() != vl)) { /* * Can't save the user regs, so current would * re-enter user with corrupt state. * There's no way to recover, so kill it: */ force_signal_inject(SIGKILL, SI_KERNEL, 0, 0); return; } sve_save_state((char *)last->sve_state + sve_ffr_offset(vl), &last->st->fpsr, save_ffr); *last->fp_type = FP_STATE_SVE; } else { fpsimd_save_state(last->st); *last->fp_type = FP_STATE_FPSIMD; } } /* * All vector length selection from userspace comes through here. * We're on a slow path, so some sanity-checks are included. * If things go wrong there's a bug somewhere, but try to fall back to a * safe choice. */ static unsigned int find_supported_vector_length(enum vec_type type, unsigned int vl) { struct vl_info *info = &vl_info[type]; int bit; int max_vl = info->max_vl; if (WARN_ON(!sve_vl_valid(vl))) vl = info->min_vl; if (WARN_ON(!sve_vl_valid(max_vl))) max_vl = info->min_vl; if (vl > max_vl) vl = max_vl; if (vl < info->min_vl) vl = info->min_vl; bit = find_next_bit(info->vq_map, SVE_VQ_MAX, __vq_to_bit(sve_vq_from_vl(vl))); return sve_vl_from_vq(__bit_to_vq(bit)); } #if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL) static int vec_proc_do_default_vl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct vl_info *info = table->extra1; enum vec_type type = info->type; int ret; int vl = get_default_vl(type); struct ctl_table tmp_table = { .data = &vl, .maxlen = sizeof(vl), }; ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); if (ret || !write) return ret; /* Writing -1 has the special meaning "set to max": */ if (vl == -1) vl = info->max_vl; if (!sve_vl_valid(vl)) return -EINVAL; set_default_vl(type, find_supported_vector_length(type, vl)); return 0; } static struct ctl_table sve_default_vl_table[] = { { .procname = "sve_default_vector_length", .mode = 0644, .proc_handler = vec_proc_do_default_vl, .extra1 = &vl_info[ARM64_VEC_SVE], }, }; static int __init sve_sysctl_init(void) { if (system_supports_sve()) if (!register_sysctl("abi", sve_default_vl_table)) return -EINVAL; return 0; } #else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) static struct ctl_table sme_default_vl_table[] = { { .procname = "sme_default_vector_length", .mode = 0644, .proc_handler = vec_proc_do_default_vl, .extra1 = &vl_info[ARM64_VEC_SME], }, }; static int __init sme_sysctl_init(void) { if (system_supports_sme()) if (!register_sysctl("abi", sme_default_vl_table)) return -EINVAL; return 0; } #else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ static int __init sme_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) #ifdef CONFIG_CPU_BIG_ENDIAN static __uint128_t arm64_cpu_to_le128(__uint128_t x) { u64 a = swab64(x); u64 b = swab64(x >> 64); return ((__uint128_t)a << 64) | b; } #else static __uint128_t arm64_cpu_to_le128(__uint128_t x) { return x; } #endif #define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, unsigned int vq) { unsigned int i; __uint128_t *p; for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t *)ZREG(sst, vq, i); *p = arm64_cpu_to_le128(fst->vregs[i]); } } /* * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to * task->thread.sve_state. * * Task can be a non-runnable task, or current. In the latter case, * the caller must have ownership of the cpu FPSIMD context before calling * this function. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.uw.fpsimd_state must be up to date before calling this * function. */ static void fpsimd_to_sve(struct task_struct *task) { unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; if (!system_supports_sve() && !system_supports_sme()) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); __fpsimd_to_sve(sst, fst, vq); } /* * Transfer the SVE state in task->thread.sve_state to * task->thread.uw.fpsimd_state. * * Task can be a non-runnable task, or current. In the latter case, * the caller must have ownership of the cpu FPSIMD context before calling * this function. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.sve_state must be up to date before calling this function. */ static void sve_to_fpsimd(struct task_struct *task) { unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; __uint128_t const *p; if (!system_supports_sve() && !system_supports_sme()) return; vl = thread_get_cur_vl(&task->thread); vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); } } void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK, SYS_SCTLR_EL1); } #ifdef CONFIG_ARM64_SVE /* * Call __sve_free() directly only if you know task can't be scheduled * or preempted. */ static void __sve_free(struct task_struct *task) { kfree(task->thread.sve_state); task->thread.sve_state = NULL; } static void sve_free(struct task_struct *task) { WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); __sve_free(task); } /* * Return how many bytes of memory are required to store the full SVE * state for task, given task's currently configured vector length. */ size_t sve_state_size(struct task_struct const *task) { unsigned int vl = 0; if (system_supports_sve()) vl = task_get_sve_vl(task); if (system_supports_sme()) vl = max(vl, task_get_sme_vl(task)); return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); } /* * Ensure that task->thread.sve_state is allocated and sufficiently large. * * This function should be used only in preparation for replacing * task->thread.sve_state with new data. The memory is always zeroed * here to prevent stale data from showing through: this is done in * the interest of testability and predictability: except in the * do_sve_acc() case, there is no ABI requirement to hide stale data * written previously be task. */ void sve_alloc(struct task_struct *task, bool flush) { if (task->thread.sve_state) { if (flush) memset(task->thread.sve_state, 0, sve_state_size(task)); return; } /* This is a small allocation (maximum ~8KB) and Should Not Fail. */ task->thread.sve_state = kzalloc(sve_state_size(task), GFP_KERNEL); } /* * Force the FPSIMD state shared with SVE to be updated in the SVE state * even if the SVE state is the current active state. * * This should only be called by ptrace. task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. */ void fpsimd_force_sync_to_sve(struct task_struct *task) { fpsimd_to_sve(task); } /* * Ensure that task->thread.sve_state is up to date with respect to * the user task, irrespective of when SVE is in use or not. * * This should only be called by ptrace. task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. */ void fpsimd_sync_to_sve(struct task_struct *task) { if (!test_tsk_thread_flag(task, TIF_SVE) && !thread_sm_enabled(&task->thread)) fpsimd_to_sve(task); } /* * Ensure that task->thread.uw.fpsimd_state is up to date with respect to * the user task, irrespective of whether SVE is in use or not. * * This should only be called by ptrace. task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. */ void sve_sync_to_fpsimd(struct task_struct *task) { if (task->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(task); } /* * Ensure that task->thread.sve_state is up to date with respect to * the task->thread.uw.fpsimd_state. * * This should only be called by ptrace to merge new FPSIMD register * values into a task for which SVE is currently active. * task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.uw.fpsimd_state must already have been initialised with * the new FPSIMD register values to be merged in. */ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; if (!test_tsk_thread_flag(task, TIF_SVE) && !thread_sm_enabled(&task->thread)) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); __fpsimd_to_sve(sst, fst, vq); } int vec_set_vector_length(struct task_struct *task, enum vec_type type, unsigned long vl, unsigned long flags) { bool free_sme = false; if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT | PR_SVE_SET_VL_ONEXEC)) return -EINVAL; if (!sve_vl_valid(vl)) return -EINVAL; /* * Clamp to the maximum vector length that VL-agnostic code * can work with. A flag may be assigned in the future to * allow setting of larger vector lengths without confusing * older software. */ if (vl > VL_ARCH_MAX) vl = VL_ARCH_MAX; vl = find_supported_vector_length(type, vl); if (flags & (PR_SVE_VL_INHERIT | PR_SVE_SET_VL_ONEXEC)) task_set_vl_onexec(task, type, vl); else /* Reset VL to system default on next exec: */ task_set_vl_onexec(task, type, 0); /* Only actually set the VL if not deferred: */ if (flags & PR_SVE_SET_VL_ONEXEC) goto out; if (vl == task_get_vl(task, type)) goto out; /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); fpsimd_save_user_state(); } fpsimd_flush_task_state(task); if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || thread_sm_enabled(&task->thread)) { sve_to_fpsimd(task); task->thread.fp_type = FP_STATE_FPSIMD; } if (system_supports_sme()) { if (type == ARM64_VEC_SME || !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) { /* * We are changing the SME VL or weren't using * SME anyway, discard the state and force a * reallocation. */ task->thread.svcr &= ~(SVCR_SM_MASK | SVCR_ZA_MASK); clear_tsk_thread_flag(task, TIF_SME); free_sme = true; } } if (task == current) put_cpu_fpsimd_context(); task_set_vl(task, type, vl); /* * Free the changed states if they are not in use, SME will be * reallocated to the correct size on next use and we just * allocate SVE now in case it is needed for use in streaming * mode. */ sve_free(task); sve_alloc(task, true); if (free_sme) sme_free(task); out: update_tsk_thread_flag(task, vec_vl_inherit_flag(type), flags & PR_SVE_VL_INHERIT); return 0; } /* * Encode the current vector length and flags for return. * This is only required for prctl(): ptrace has separate fields. * SVE and SME use the same bits for _ONEXEC and _INHERIT. * * flags are as for vec_set_vector_length(). */ static int vec_prctl_status(enum vec_type type, unsigned long flags) { int ret; if (flags & PR_SVE_SET_VL_ONEXEC) ret = task_get_vl_onexec(current, type); else ret = task_get_vl(current, type); if (test_thread_flag(vec_vl_inherit_flag(type))) ret |= PR_SVE_VL_INHERIT; return ret; } /* PR_SVE_SET_VL */ int sve_set_current_vl(unsigned long arg) { unsigned long vl, flags; int ret; vl = arg & PR_SVE_VL_LEN_MASK; flags = arg & ~vl; if (!system_supports_sve() || is_compat_task()) return -EINVAL; ret = vec_set_vector_length(current, ARM64_VEC_SVE, vl, flags); if (ret) return ret; return vec_prctl_status(ARM64_VEC_SVE, flags); } /* PR_SVE_GET_VL */ int sve_get_current_vl(void) { if (!system_supports_sve() || is_compat_task()) return -EINVAL; return vec_prctl_status(ARM64_VEC_SVE, 0); } #ifdef CONFIG_ARM64_SME /* PR_SME_SET_VL */ int sme_set_current_vl(unsigned long arg) { unsigned long vl, flags; int ret; vl = arg & PR_SME_VL_LEN_MASK; flags = arg & ~vl; if (!system_supports_sme() || is_compat_task()) return -EINVAL; ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags); if (ret) return ret; return vec_prctl_status(ARM64_VEC_SME, flags); } /* PR_SME_GET_VL */ int sme_get_current_vl(void) { if (!system_supports_sme() || is_compat_task()) return -EINVAL; return vec_prctl_status(ARM64_VEC_SME, 0); } #endif /* CONFIG_ARM64_SME */ static void vec_probe_vqs(struct vl_info *info, DECLARE_BITMAP(map, SVE_VQ_MAX)) { unsigned int vq, vl; bitmap_zero(map, SVE_VQ_MAX); for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) { write_vl(info->type, vq - 1); /* self-syncing */ switch (info->type) { case ARM64_VEC_SVE: vl = sve_get_vl(); break; case ARM64_VEC_SME: vl = sme_get_vl(); break; default: vl = 0; break; } /* Minimum VL identified? */ if (sve_vq_from_vl(vl) > vq) break; vq = sve_vq_from_vl(vl); /* skip intervening lengths */ set_bit(__vq_to_bit(vq), map); } } /* * Initialise the set of known supported VQs for the boot CPU. * This is called during kernel boot, before secondary CPUs are brought up. */ void __init vec_init_vq_map(enum vec_type type) { struct vl_info *info = &vl_info[type]; vec_probe_vqs(info, info->vq_map); bitmap_copy(info->vq_partial_map, info->vq_map, SVE_VQ_MAX); } /* * If we haven't committed to the set of supported VQs yet, filter out * those not supported by the current CPU. * This function is called during the bring-up of early secondary CPUs only. */ void vec_update_vq_map(enum vec_type type) { struct vl_info *info = &vl_info[type]; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); vec_probe_vqs(info, tmp_map); bitmap_and(info->vq_map, info->vq_map, tmp_map, SVE_VQ_MAX); bitmap_or(info->vq_partial_map, info->vq_partial_map, tmp_map, SVE_VQ_MAX); } /* * Check whether the current CPU supports all VQs in the committed set. * This function is called during the bring-up of late secondary CPUs only. */ int vec_verify_vq_map(enum vec_type type) { struct vl_info *info = &vl_info[type]; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); unsigned long b; vec_probe_vqs(info, tmp_map); bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX); if (bitmap_intersects(tmp_map, info->vq_map, SVE_VQ_MAX)) { pr_warn("%s: cpu%d: Required vector length(s) missing\n", info->name, smp_processor_id()); return -EINVAL; } if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available()) return 0; /* * For KVM, it is necessary to ensure that this CPU doesn't * support any vector length that guests may have probed as * unsupported. */ /* Recover the set of supported VQs: */ bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX); /* Find VQs supported that are not globally supported: */ bitmap_andnot(tmp_map, tmp_map, info->vq_map, SVE_VQ_MAX); /* Find the lowest such VQ, if any: */ b = find_last_bit(tmp_map, SVE_VQ_MAX); if (b >= SVE_VQ_MAX) return 0; /* no mismatches */ /* * Mismatches above sve_max_virtualisable_vl are fine, since * no guest is allowed to configure ZCR_EL2.LEN to exceed this: */ if (sve_vl_from_vq(__bit_to_vq(b)) <= info->max_virtualisable_vl) { pr_warn("%s: cpu%d: Unsupported vector length(s) present\n", info->name, smp_processor_id()); return -EINVAL; } return 0; } static void __init sve_efi_setup(void) { int max_vl = 0; int i; if (!IS_ENABLED(CONFIG_EFI)) return; for (i = 0; i < ARRAY_SIZE(vl_info); i++) max_vl = max(vl_info[i].max_vl, max_vl); /* * alloc_percpu() warns and prints a backtrace if this goes wrong. * This is evidence of a crippled system and we are returning void, * so no attempt is made to handle this situation here. */ if (!sve_vl_valid(max_vl)) goto fail; efi_sve_state = __alloc_percpu( SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES); if (!efi_sve_state) goto fail; return; fail: panic("Cannot allocate percpu memory for EFI SVE save/restore"); } void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1); isb(); write_sysreg_s(0, SYS_ZCR_EL1); } void __init sve_setup(void) { struct vl_info *info = &vl_info[ARM64_VEC_SVE]; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); unsigned long b; int max_bit; if (!system_supports_sve()) return; /* * The SVE architecture mandates support for 128-bit vectors, * so sve_vq_map must have at least SVE_VQ_MIN set. * If something went wrong, at least try to patch it up: */ if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map))) set_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map); max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX); info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit)); /* * For the default VL, pick the maximum supported value <= 64. * VL == 64 is guaranteed not to grow the signal frame. */ set_sve_default_vl(find_supported_vector_length(ARM64_VEC_SVE, 64)); bitmap_andnot(tmp_map, info->vq_partial_map, info->vq_map, SVE_VQ_MAX); b = find_last_bit(tmp_map, SVE_VQ_MAX); if (b >= SVE_VQ_MAX) /* No non-virtualisable VLs found */ info->max_virtualisable_vl = SVE_VQ_MAX; else if (WARN_ON(b == SVE_VQ_MAX - 1)) /* No virtualisable VLs? This is architecturally forbidden. */ info->max_virtualisable_vl = SVE_VQ_MIN; else /* b + 1 < SVE_VQ_MAX */ info->max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1)); if (info->max_virtualisable_vl > info->max_vl) info->max_virtualisable_vl = info->max_vl; pr_info("%s: maximum available vector length %u bytes per vector\n", info->name, info->max_vl); pr_info("%s: default vector length %u bytes per vector\n", info->name, get_sve_default_vl()); /* KVM decides whether to support mismatched systems. Just warn here: */ if (sve_max_virtualisable_vl() < sve_max_vl()) pr_warn("%s: unvirtualisable vector lengths present\n", info->name); sve_efi_setup(); } /* * Called from the put_task_struct() path, which cannot get here * unless dead_task is really dead and not schedulable. */ void fpsimd_release_task(struct task_struct *dead_task) { __sve_free(dead_task); sme_free(dead_task); } #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME /* * Ensure that task->thread.sme_state is allocated and sufficiently large. * * This function should be used only in preparation for replacing * task->thread.sme_state with new data. The memory is always zeroed * here to prevent stale data from showing through: this is done in * the interest of testability and predictability, the architecture * guarantees that when ZA is enabled it will be zeroed. */ void sme_alloc(struct task_struct *task, bool flush) { if (task->thread.sme_state) { if (flush) memset(task->thread.sme_state, 0, sme_state_size(task)); return; } /* This could potentially be up to 64K. */ task->thread.sme_state = kzalloc(sme_state_size(task), GFP_KERNEL); } static void sme_free(struct task_struct *task) { kfree(task->thread.sme_state); task->thread.sme_state = NULL; } void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p) { /* Set priority for all PEs to architecturally defined minimum */ write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK, SYS_SMPRI_EL1); /* Allow SME in kernel */ write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); isb(); /* Ensure all bits in SMCR are set to known values */ write_sysreg_s(0, SYS_SMCR_EL1); /* Allow EL0 to access TPIDR2 */ write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); isb(); } void cpu_enable_sme2(const struct arm64_cpu_capabilities *__always_unused p) { /* This must be enabled after SME */ BUILD_BUG_ON(ARM64_SME2 <= ARM64_SME); /* Allow use of ZT0 */ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK, SYS_SMCR_EL1); } void cpu_enable_fa64(const struct arm64_cpu_capabilities *__always_unused p) { /* This must be enabled after SME */ BUILD_BUG_ON(ARM64_SME_FA64 <= ARM64_SME); /* Allow use of FA64 */ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK, SYS_SMCR_EL1); } void __init sme_setup(void) { struct vl_info *info = &vl_info[ARM64_VEC_SME]; int min_bit, max_bit; if (!system_supports_sme()) return; /* * SME doesn't require any particular vector length be * supported but it does require at least one. We should have * disabled the feature entirely while bringing up CPUs but * let's double check here. The bitmap is SVE_VQ_MAP sized for * sharing with SVE. */ WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX)); min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX); info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit)); max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX); info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit)); WARN_ON(info->min_vl > info->max_vl); /* * For the default VL, pick the maximum supported value <= 32 * (256 bits) if there is one since this is guaranteed not to * grow the signal frame when in streaming mode, otherwise the * minimum available VL will be used. */ set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32)); pr_info("SME: minimum available vector length %u bytes per vector\n", info->min_vl); pr_info("SME: maximum available vector length %u bytes per vector\n", info->max_vl); pr_info("SME: default vector length %u bytes per vector\n", get_sme_default_vl()); } void sme_suspend_exit(void) { u64 smcr = 0; if (!system_supports_sme()) return; if (system_supports_fa64()) smcr |= SMCR_ELx_FA64; if (system_supports_sme2()) smcr |= SMCR_ELx_EZT0; write_sysreg_s(smcr, SYS_SMCR_EL1); write_sysreg_s(0, SYS_SMPRI_EL1); } #endif /* CONFIG_ARM64_SME */ static void sve_init_regs(void) { /* * Convert the FPSIMD state to SVE, zeroing all the state that * is not shared with FPSIMD. If (as is likely) the current * state is live in the registers then do this there and * update our metadata for the current task including * disabling the trap, otherwise update our in-memory copy. * We are guaranteed to not be in streaming mode, we can only * take a SVE trap when not in streaming mode and we can't be * in streaming mode when taking a SME trap. */ if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; sve_set_vq(vq_minus_one); sve_flush_live(true, vq_minus_one); fpsimd_bind_task_to_cpu(); } else { fpsimd_to_sve(current); current->thread.fp_type = FP_STATE_SVE; } } /* * Trapped SVE access * * Storage is allocated for the full SVE state, the current FPSIMD * register contents are migrated across, and the access trap is * disabled. * * TIF_SVE should be clear on entry: otherwise, fpsimd_restore_current_state() * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ void do_sve_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } sve_alloc(current, true); if (!current->thread.sve_state) { force_sig(SIGKILL); return; } get_cpu_fpsimd_context(); if (test_and_set_thread_flag(TIF_SVE)) WARN_ON(1); /* SVE access shouldn't have trapped */ /* * Even if the task can have used streaming mode we can only * generate SVE access traps in normal SVE mode and * transitioning out of streaming mode may discard any * streaming mode state. Always clear the high bits to avoid * any potential errors tracking what is properly initialised. */ sve_init_regs(); put_cpu_fpsimd_context(); } /* * Trapped SME access * * Storage is allocated for the full SVE and SME state, the current * FPSIMD register contents are migrated to SVE if SVE is not already * active, and the access trap is disabled. * * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state() * would have disabled the SME access trap for userspace during * ret_to_user, making an SME access trap impossible in that case. */ void do_sme_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use SME, the hardware could still trap: */ if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } /* * If this not a trap due to SME being disabled then something * is being used in the wrong mode, report as SIGILL. */ if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } sve_alloc(current, false); sme_alloc(current, true); if (!current->thread.sve_state || !current->thread.sme_state) { force_sig(SIGKILL); return; } get_cpu_fpsimd_context(); /* With TIF_SME userspace shouldn't generate any traps */ if (test_and_set_thread_flag(TIF_SME)) WARN_ON(1); if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = sve_vq_from_vl(task_get_sme_vl(current)) - 1; sme_set_vq(vq_minus_one); fpsimd_bind_task_to_cpu(); } put_cpu_fpsimd_context(); } /* * Trapped FP/ASIMD access. */ void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use FPSIMD, the hardware could still trap: */ if (!system_supports_fpsimd()) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } /* * When FPSIMD is enabled, we should never take a trap unless something * has gone very wrong. */ BUG(); } /* * Raise a SIGFPE for the current process. */ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; if (esr & ESR_ELx_FP_EXC_TFV) { if (esr & FPEXC_IOF) si_code = FPE_FLTINV; else if (esr & FPEXC_DZF) si_code = FPE_FLTDIV; else if (esr & FPEXC_OFF) si_code = FPE_FLTOVF; else if (esr & FPEXC_UFF) si_code = FPE_FLTUND; else if (esr & FPEXC_IXF) si_code = FPE_FLTRES; } send_sig_fault(SIGFPE, si_code, (void __user *)instruction_pointer(regs), current); } static void fpsimd_load_kernel_state(struct task_struct *task) { struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); /* * Elide the load if this CPU holds the most recent kernel mode * FPSIMD context of the current task. */ if (last->st == &task->thread.kernel_fpsimd_state && task->thread.kernel_fpsimd_cpu == smp_processor_id()) return; fpsimd_load_state(&task->thread.kernel_fpsimd_state); } static void fpsimd_save_kernel_state(struct task_struct *task) { struct cpu_fp_state cpu_fp_state = { .st = &task->thread.kernel_fpsimd_state, .to_save = FP_STATE_FPSIMD, }; fpsimd_save_state(&task->thread.kernel_fpsimd_state); fpsimd_bind_state_to_cpu(&cpu_fp_state); task->thread.kernel_fpsimd_cpu = smp_processor_id(); } /* * Invalidate any task's FPSIMD state that is present on this cpu. * The FPSIMD context should be acquired with get_cpu_fpsimd_context() * before calling this function. */ static void fpsimd_flush_cpu_state(void) { WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); /* * Leaving streaming mode enabled will cause issues for any kernel * NEON and leaving streaming mode or ZA enabled may increase power * consumption. */ if (system_supports_sme()) sme_smstop(); set_thread_flag(TIF_FOREIGN_FPSTATE); } void fpsimd_thread_switch(struct task_struct *next) { bool wrong_task, wrong_cpu; if (!system_supports_fpsimd()) return; WARN_ON_ONCE(!irqs_disabled()); /* Save unsaved fpsimd state, if any: */ if (test_thread_flag(TIF_KERNEL_FPSTATE)) fpsimd_save_kernel_state(current); else fpsimd_save_user_state(); if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) { fpsimd_load_kernel_state(next); fpsimd_flush_cpu_state(); } else { /* * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's * state. For kernel threads, FPSIMD registers are never * loaded with user mode FPSIMD state and so wrong_task and * wrong_cpu will always be true. */ wrong_task = __this_cpu_read(fpsimd_last_state.st) != &next->thread.uw.fpsimd_state; wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, wrong_task || wrong_cpu); } } static void fpsimd_flush_thread_vl(enum vec_type type) { int vl, supported_vl; /* * Reset the task vector length as required. This is where we * ensure that all user tasks have a valid vector length * configured: no kernel task can become a user task without * an exec and hence a call to this function. By the time the * first call to this function is made, all early hardware * probing is complete, so __sve_default_vl should be valid. * If a bug causes this to go wrong, we make some noise and * try to fudge thread.sve_vl to a safe value here. */ vl = task_get_vl_onexec(current, type); if (!vl) vl = get_default_vl(type); if (WARN_ON(!sve_vl_valid(vl))) vl = vl_info[type].min_vl; supported_vl = find_supported_vector_length(type, vl); if (WARN_ON(supported_vl != vl)) vl = supported_vl; task_set_vl(current, type, vl); /* * If the task is not set to inherit, ensure that the vector * length will be reset by a subsequent exec: */ if (!test_thread_flag(vec_vl_inherit_flag(type))) task_set_vl_onexec(current, type, 0); } void fpsimd_flush_thread(void) { void *sve_state = NULL; void *sme_state = NULL; if (!system_supports_fpsimd()) return; get_cpu_fpsimd_context(); fpsimd_flush_task_state(current); memset(¤t->thread.uw.fpsimd_state, 0, sizeof(current->thread.uw.fpsimd_state)); if (system_supports_sve()) { clear_thread_flag(TIF_SVE); /* Defer kfree() while in atomic context */ sve_state = current->thread.sve_state; current->thread.sve_state = NULL; fpsimd_flush_thread_vl(ARM64_VEC_SVE); } if (system_supports_sme()) { clear_thread_flag(TIF_SME); /* Defer kfree() while in atomic context */ sme_state = current->thread.sme_state; current->thread.sme_state = NULL; fpsimd_flush_thread_vl(ARM64_VEC_SME); current->thread.svcr = 0; } current->thread.fp_type = FP_STATE_FPSIMD; put_cpu_fpsimd_context(); kfree(sve_state); kfree(sme_state); } /* * Save the userland FPSIMD state of 'current' to memory, but only if the state * currently held in the registers does in fact belong to 'current' */ void fpsimd_preserve_current_state(void) { if (!system_supports_fpsimd()) return; get_cpu_fpsimd_context(); fpsimd_save_user_state(); put_cpu_fpsimd_context(); } /* * Like fpsimd_preserve_current_state(), but ensure that * current->thread.uw.fpsimd_state is updated so that it can be copied to * the signal frame. */ void fpsimd_signal_preserve_current_state(void) { fpsimd_preserve_current_state(); if (current->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(current); } /* * Called by KVM when entering the guest. */ void fpsimd_kvm_prepare(void) { if (!system_supports_sve()) return; /* * KVM does not save host SVE state since we can only enter * the guest from a syscall so the ABI means that only the * non-saved SVE state needs to be saved. If we have left * SVE enabled for performance reasons then update the task * state to be FPSIMD only. */ get_cpu_fpsimd_context(); if (test_and_clear_thread_flag(TIF_SVE)) { sve_to_fpsimd(current); current->thread.fp_type = FP_STATE_FPSIMD; } put_cpu_fpsimd_context(); } /* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling * this function. */ static void fpsimd_bind_task_to_cpu(void) { struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sme_state = current->thread.sme_state; last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; last->fpmr = ¤t->thread.uw.fpmr; last->fp_type = ¤t->thread.fp_type; last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id(); /* * Toggle SVE and SME trapping for userspace if needed, these * are serialsied by ret_to_user(). */ if (system_supports_sme()) { if (test_thread_flag(TIF_SME)) sme_user_enable(); else sme_user_disable(); } if (system_supports_sve()) { if (test_thread_flag(TIF_SVE)) sve_user_enable(); else sve_user_disable(); } } void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state) { struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); WARN_ON(!system_supports_fpsimd()); WARN_ON(!in_softirq() && !irqs_disabled()); *last = *state; } /* * Load the userland FPSIMD state of 'current' from memory, but only if the * FPSIMD state already held in the registers is /not/ the most recent FPSIMD * state of 'current'. This is called when we are preparing to return to * userspace to ensure that userspace sees a good register state. */ void fpsimd_restore_current_state(void) { /* * TIF_FOREIGN_FPSTATE is set on the init task and copied by * arch_dup_task_struct() regardless of whether FP/SIMD is detected. * Thus user threads can have this set even when FP/SIMD hasn't been * detected. * * When FP/SIMD is detected, begin_new_exec() will set * TIF_FOREIGN_FPSTATE via flush_thread() -> fpsimd_flush_thread(), * and fpsimd_thread_switch() will set TIF_FOREIGN_FPSTATE when * switching tasks. We detect FP/SIMD before we exec the first user * process, ensuring this has TIF_FOREIGN_FPSTATE set and * do_notify_resume() will call fpsimd_restore_current_state() to * install the user FP/SIMD context. * * When FP/SIMD is not detected, nothing else will clear or set * TIF_FOREIGN_FPSTATE prior to the first return to userspace, and * we must clear TIF_FOREIGN_FPSTATE to avoid do_notify_resume() * looping forever calling fpsimd_restore_current_state(). */ if (!system_supports_fpsimd()) { clear_thread_flag(TIF_FOREIGN_FPSTATE); return; } get_cpu_fpsimd_context(); if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { task_fpsimd_load(); fpsimd_bind_task_to_cpu(); } put_cpu_fpsimd_context(); } /* * Load an updated userland FPSIMD state for 'current' from memory and set the * flag that indicates that the FPSIMD register contents are the most recent * FPSIMD state of 'current'. This is used by the signal code to restore the * register state when returning from a signal handler in FPSIMD only cases, * any SVE context will be discarded. */ void fpsimd_update_current_state(struct user_fpsimd_state const *state) { if (WARN_ON(!system_supports_fpsimd())) return; get_cpu_fpsimd_context(); current->thread.uw.fpsimd_state = *state; if (test_thread_flag(TIF_SVE)) fpsimd_to_sve(current); task_fpsimd_load(); fpsimd_bind_task_to_cpu(); clear_thread_flag(TIF_FOREIGN_FPSTATE); put_cpu_fpsimd_context(); } /* * Invalidate live CPU copies of task t's FPSIMD state * * This function may be called with preemption enabled. The barrier() * ensures that the assignment to fpsimd_cpu is visible to any * preemption/softirq that could race with set_tsk_thread_flag(), so * that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared. * * The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any * subsequent code. */ void fpsimd_flush_task_state(struct task_struct *t) { t->thread.fpsimd_cpu = NR_CPUS; /* * If we don't support fpsimd, bail out after we have * reset the fpsimd_cpu for this task and clear the * FPSTATE. */ if (!system_supports_fpsimd()) return; barrier(); set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE); barrier(); } /* * Save the FPSIMD state to memory and invalidate cpu view. * This function must be called with preemption disabled. */ void fpsimd_save_and_flush_cpu_state(void) { unsigned long flags; if (!system_supports_fpsimd()) return; WARN_ON(preemptible()); local_irq_save(flags); fpsimd_save_user_state(); fpsimd_flush_cpu_state(); local_irq_restore(flags); } #ifdef CONFIG_KERNEL_MODE_NEON /* * Kernel-side NEON support functions */ /* * kernel_neon_begin(): obtain the CPU FPSIMD registers for use by the calling * context * * Must not be called unless may_use_simd() returns true. * Task context in the FPSIMD registers is saved back to memory as necessary. * * A matching call to kernel_neon_end() must be made before returning from the * calling context. * * The caller may freely use the FPSIMD registers until kernel_neon_end() is * called. */ void kernel_neon_begin(void) { if (WARN_ON(!system_supports_fpsimd())) return; BUG_ON(!may_use_simd()); get_cpu_fpsimd_context(); /* Save unsaved fpsimd state, if any: */ if (test_thread_flag(TIF_KERNEL_FPSTATE)) { BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()); fpsimd_save_kernel_state(current); } else { fpsimd_save_user_state(); /* * Set the thread flag so that the kernel mode FPSIMD state * will be context switched along with the rest of the task * state. * * On non-PREEMPT_RT, softirqs may interrupt task level kernel * mode FPSIMD, but the task will not be preemptible so setting * TIF_KERNEL_FPSTATE for those would be both wrong (as it * would mark the task context FPSIMD state as requiring a * context switch) and unnecessary. * * On PREEMPT_RT, softirqs are serviced from a separate thread, * which is scheduled as usual, and this guarantees that these * softirqs are not interrupting use of the FPSIMD in kernel * mode in task context. So in this case, setting the flag here * is always appropriate. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()) set_thread_flag(TIF_KERNEL_FPSTATE); } /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); put_cpu_fpsimd_context(); } EXPORT_SYMBOL_GPL(kernel_neon_begin); /* * kernel_neon_end(): give the CPU FPSIMD registers back to the current task * * Must be called from a context in which kernel_neon_begin() was previously * called, with no call to kernel_neon_end() in the meantime. * * The caller must not use the FPSIMD registers after this function is called, * unless kernel_neon_begin() is called again in the meantime. */ void kernel_neon_end(void) { if (!system_supports_fpsimd()) return; /* * If we are returning from a nested use of kernel mode FPSIMD, restore * the task context kernel mode FPSIMD state. This can only happen when * running in softirq context on non-PREEMPT_RT. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() && test_thread_flag(TIF_KERNEL_FPSTATE)) fpsimd_load_kernel_state(current); else clear_thread_flag(TIF_KERNEL_FPSTATE); } EXPORT_SYMBOL_GPL(kernel_neon_end); #ifdef CONFIG_EFI static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); static DEFINE_PER_CPU(bool, efi_sve_state_used); static DEFINE_PER_CPU(bool, efi_sm_state); /* * EFI runtime services support functions * * The ABI for EFI runtime services allows EFI to use FPSIMD during the call. * This means that for EFI (and only for EFI), we have to assume that FPSIMD * is always used rather than being an optional accelerator. * * These functions provide the necessary support for ensuring FPSIMD * save/restore in the contexts from which EFI is used. * * Do not use them for any other purpose -- if tempted to do so, you are * either doing something wrong or you need to propose some refactoring. */ /* * __efi_fpsimd_begin(): prepare FPSIMD for making an EFI runtime services call */ void __efi_fpsimd_begin(void) { if (!system_supports_fpsimd()) return; WARN_ON(preemptible()); if (may_use_simd()) { kernel_neon_begin(); } else { /* * If !efi_sve_state, SVE can't be in use yet and doesn't need * preserving: */ if (system_supports_sve() && likely(efi_sve_state)) { char *sve_state = this_cpu_ptr(efi_sve_state); bool ffr = true; u64 svcr; __this_cpu_write(efi_sve_state_used, true); if (system_supports_sme()) { svcr = read_sysreg_s(SYS_SVCR); __this_cpu_write(efi_sm_state, svcr & SVCR_SM_MASK); /* * Unless we have FA64 FFR does not * exist in streaming mode. */ if (!system_supports_fa64()) ffr = !(svcr & SVCR_SM_MASK); } sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, ffr); if (system_supports_sme()) sysreg_clear_set_s(SYS_SVCR, SVCR_SM_MASK, 0); } else { fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state)); } __this_cpu_write(efi_fpsimd_state_used, true); } } /* * __efi_fpsimd_end(): clean up FPSIMD after an EFI runtime services call */ void __efi_fpsimd_end(void) { if (!system_supports_fpsimd()) return; if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) { kernel_neon_end(); } else { if (system_supports_sve() && likely(__this_cpu_read(efi_sve_state_used))) { char const *sve_state = this_cpu_ptr(efi_sve_state); bool ffr = true; /* * Restore streaming mode; EFI calls are * normal function calls so should not return in * streaming mode. */ if (system_supports_sme()) { if (__this_cpu_read(efi_sm_state)) { sysreg_clear_set_s(SYS_SVCR, 0, SVCR_SM_MASK); /* * Unless we have FA64 FFR does not * exist in streaming mode. */ if (!system_supports_fa64()) ffr = false; } } sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, ffr); __this_cpu_write(efi_sve_state_used, false); } else { fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state)); } } } #endif /* CONFIG_EFI */ #endif /* CONFIG_KERNEL_MODE_NEON */ #ifdef CONFIG_CPU_PM static int fpsimd_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { switch (cmd) { case CPU_PM_ENTER: fpsimd_save_and_flush_cpu_state(); break; case CPU_PM_EXIT: break; case CPU_PM_ENTER_FAILED: default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block fpsimd_cpu_pm_notifier_block = { .notifier_call = fpsimd_cpu_pm_notifier, }; static void __init fpsimd_pm_init(void) { cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block); } #else static inline void fpsimd_pm_init(void) { } #endif /* CONFIG_CPU_PM */ #ifdef CONFIG_HOTPLUG_CPU static int fpsimd_cpu_dead(unsigned int cpu) { per_cpu(fpsimd_last_state.st, cpu) = NULL; return 0; } static inline void fpsimd_hotplug_init(void) { cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead", NULL, fpsimd_cpu_dead); } #else static inline void fpsimd_hotplug_init(void) { } #endif void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__always_unused p) { unsigned long enable = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN; write_sysreg(read_sysreg(CPACR_EL1) | enable, CPACR_EL1); isb(); } /* * FP/SIMD support code initialisation. */ static int __init fpsimd_init(void) { if (cpu_have_named_feature(FP)) { fpsimd_pm_init(); fpsimd_hotplug_init(); } else { pr_notice("Floating-point is not implemented\n"); } if (!cpu_have_named_feature(ASIMD)) pr_notice("Advanced SIMD is not implemented\n"); sve_sysctl_init(); sme_sysctl_init(); return 0; } core_initcall(fpsimd_init); |
| 32 32 12 12 44 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * * We implement four types of file locks: BSD locks, posix locks, open * file description locks, and leases. For details about BSD locks, * see the flock(2) man page; for details about the other three, see * fcntl(2). * * * Locking conflicts and dependencies: * If multiple threads attempt to lock the same byte (or flock the same file) * only one can be granted the lock, and other must wait their turn. * The first lock has been "applied" or "granted", the others are "waiting" * and are "blocked" by the "applied" lock.. * * Waiting and applied locks are all kept in trees whose properties are: * * - the root of a tree may be an applied or waiting lock. * - every other node in the tree is a waiting lock that * conflicts with every ancestor of that node. * * Every such tree begins life as a waiting singleton which obviously * satisfies the above properties. * * The only ways we modify trees preserve these properties: * * 1. We may add a new leaf node, but only after first verifying that it * conflicts with all of its ancestors. * 2. We may remove the root of a tree, creating a new singleton * tree from the root and N new trees rooted in the immediate * children. * 3. If the root of a tree is not currently an applied lock, we may * apply it (if possible). * 4. We may upgrade the root of the tree (either extend its range, * or upgrade its entire range from read to write). * * When an applied lock is modified in a way that reduces or downgrades any * part of its range, we remove all its children (2 above). This particularly * happens when a lock is unlocked. * * For each of those child trees we "wake up" the thread which is * waiting for the lock so it can continue handling as follows: if the * root of the tree applies, we do so (3). If it doesn't, it must * conflict with some applied lock. We remove (wake up) all of its children * (2), and add it is a new leaf to the tree rooted in the applied * lock (1). We then repeat the process recursively with those * children. * */ #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/filelock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> #include <linux/sysctl.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> #include <linux/uaccess.h> static struct file_lock *file_lock(struct file_lock_core *flc) { return container_of(flc, struct file_lock, c); } static struct file_lease *file_lease(struct file_lock_core *flc) { return container_of(flc, struct file_lease, c); } static bool lease_breaking(struct file_lease *fl) { return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); } static int target_leasetype(struct file_lease *fl) { if (fl->c.flc_flags & FL_UNLOCK_PENDING) return F_UNLCK; if (fl->c.flc_flags & FL_DOWNGRADE_PENDING) return F_RDLCK; return fl->c.flc_type; } static int leases_enable = 1; static int lease_break_time = 45; #ifdef CONFIG_SYSCTL static struct ctl_table locks_sysctls[] = { { .procname = "leases-enable", .data = &leases_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_MMU { .procname = "lease-break-time", .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_MMU */ }; static int __init init_fs_locks_sysctls(void) { register_sysctl_init("fs", locks_sysctls); return 0; } early_initcall(init_fs_locks_sysctls); #endif /* CONFIG_SYSCTL */ /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock. * Global serialization is done using file_rwsem. * * Note that alterations to the list also require that the relevant flc_lock is * held. */ struct file_lock_list_struct { spinlock_t lock; struct hlist_head hlist; }; static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. * It is protected by blocked_lock_lock. * * We hash locks by lockowner in order to optimize searching for the lock a * particular lockowner is waiting on. * * FIXME: make this value scale via some heuristic? We generally will want more * buckets when we have more lockowners holding locks, but that's a little * difficult to determine without knowing what the workload will look like. */ #define BLOCKED_HASH_BITS 7 static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); /* * This lock protects the blocked_hash. Generally, if you're accessing it, you * want to be holding this lock. * * In addition, it also protects the fl->fl_blocked_requests list, and the * fl->fl_blocker pointer for file_lock structures that are acting as lock * requests (in contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the * flc_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); static struct kmem_cache *flctx_cache __ro_after_init; static struct kmem_cache *filelock_cache __ro_after_init; static struct kmem_cache *filelease_cache __ro_after_init; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *ctx; /* paired with cmpxchg() below */ ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); if (!ctx) goto out; spin_lock_init(&ctx->flc_lock); INIT_LIST_HEAD(&ctx->flc_flock); INIT_LIST_HEAD(&ctx->flc_posix); INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); return ctx; } static void locks_dump_ctx_list(struct list_head *list, char *list_type) { struct file_lock_core *flc; list_for_each_entry(flc, list, flc_list) pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, flc->flc_owner, flc->flc_flags, flc->flc_type, flc->flc_pid); } static void locks_check_ctx_lists(struct inode *inode) { struct file_lock_context *ctx = inode->i_flctx; if (unlikely(!list_empty(&ctx->flc_flock) || !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_lease))) { pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); } } static void locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { struct file_lock_core *flc; struct inode *inode = file_inode(filp); list_for_each_entry(flc, list, flc_list) if (flc->flc_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, flc->flc_owner, flc->flc_flags, flc->flc_type, flc->flc_pid); } void locks_free_lock_context(struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } static void locks_init_lock_heads(struct file_lock_core *flc) { INIT_HLIST_NODE(&flc->flc_link); INIT_LIST_HEAD(&flc->flc_list); INIT_LIST_HEAD(&flc->flc_blocked_requests); INIT_LIST_HEAD(&flc->flc_blocked_member); init_waitqueue_head(&flc->flc_wait); } /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); /* Allocate an empty lock structure. */ struct file_lease *locks_alloc_lease(void) { struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lease); void locks_release_private(struct file_lock *fl) { struct file_lock_core *flc = &fl->c; BUG_ON(waitqueue_active(&flc->flc_wait)); BUG_ON(!list_empty(&flc->flc_list)); BUG_ON(!list_empty(&flc->flc_blocked_requests)); BUG_ON(!list_empty(&flc->flc_blocked_member)); BUG_ON(!hlist_unhashed(&flc->flc_link)); if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); fl->fl_ops = NULL; } if (fl->fl_lmops) { if (fl->fl_lmops->lm_put_owner) { fl->fl_lmops->lm_put_owner(flc->flc_owner); flc->flc_owner = NULL; } fl->fl_lmops = NULL; } } EXPORT_SYMBOL_GPL(locks_release_private); /** * locks_owner_has_blockers - Check for blocking lock requests * @flctx: file lock context * @owner: lock owner * * Return values: * %true: @owner has at least one blocker * %false: @owner has no blockers */ bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { struct file_lock_core *flc; spin_lock(&flctx->flc_lock); list_for_each_entry(flc, &flctx->flc_posix, flc_list) { if (flc->flc_owner != owner) continue; if (!list_empty(&flc->flc_blocked_requests)) { spin_unlock(&flctx->flc_lock); return true; } } spin_unlock(&flctx->flc_lock); return false; } EXPORT_SYMBOL_GPL(locks_owner_has_blockers); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } EXPORT_SYMBOL(locks_free_lock); /* Free a lease which is not in use. */ void locks_free_lease(struct file_lease *fl) { kmem_cache_free(filelease_cache, fl); } EXPORT_SYMBOL(locks_free_lease); static void locks_dispose_list(struct list_head *dispose) { struct file_lock_core *flc; while (!list_empty(dispose)) { flc = list_first_entry(dispose, struct file_lock_core, flc_list); list_del_init(&flc->flc_list); if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) locks_free_lease(file_lease(flc)); else locks_free_lock(file_lock(flc)); } } void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lock); void locks_init_lease(struct file_lease *fl) { memset(fl, 0, sizeof(*fl)); locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lease); /* * Initialize a new lock from an existing file_lock structure. */ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { new->c.flc_owner = fl->c.flc_owner; new->c.flc_pid = fl->c.flc_pid; new->c.flc_file = NULL; new->c.flc_flags = fl->c.flc_flags; new->c.flc_type = fl->c.flc_type; new->fl_start = fl->fl_start; new->fl_end = fl->fl_end; new->fl_lmops = fl->fl_lmops; new->fl_ops = NULL; if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) fl->fl_lmops->lm_get_owner(fl->c.flc_owner); } } EXPORT_SYMBOL(locks_copy_conflock); void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { /* "new" must be a freshly-initialized lock */ WARN_ON_ONCE(new->fl_ops); locks_copy_conflock(new, fl); new->c.flc_file = fl->c.flc_file; new->fl_ops = fl->fl_ops; if (fl->fl_ops) { if (fl->fl_ops->fl_copy_lock) fl->fl_ops->fl_copy_lock(new, fl); } } EXPORT_SYMBOL(locks_copy_lock); static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) { struct file_lock *f; /* * As ctx->flc_lock is held, new requests cannot be added to * ->flc_blocked_requests, so we don't need a lock to check if it * is empty. */ if (list_empty(&fl->c.flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); list_splice_init(&fl->c.flc_blocked_requests, &new->c.flc_blocked_requests); list_for_each_entry(f, &new->c.flc_blocked_requests, c.flc_blocked_member) f->c.flc_blocker = &new->c; spin_unlock(&blocked_lock_lock); } static inline int flock_translate_cmd(int cmd) { switch (cmd) { case LOCK_SH: return F_RDLCK; case LOCK_EX: return F_WRLCK; case LOCK_UN: return F_UNLCK; } return -EINVAL; } /* Fill in a file_lock structure with an appropriate FLOCK lock. */ static void flock_make_lock(struct file *filp, struct file_lock *fl, int type) { locks_init_lock(fl); fl->c.flc_file = filp; fl->c.flc_owner = filp; fl->c.flc_pid = current->tgid; fl->c.flc_flags = FL_FLOCK; fl->c.flc_type = type; fl->fl_end = OFFSET_MAX; } static int assign_type(struct file_lock_core *flc, int type) { switch (type) { case F_RDLCK: case F_WRLCK: case F_UNLCK: flc->flc_type = type; break; default: return -EINVAL; } return 0; } static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock64 *l) { switch (l->l_whence) { case SEEK_SET: fl->fl_start = 0; break; case SEEK_CUR: fl->fl_start = filp->f_pos; break; case SEEK_END: fl->fl_start = i_size_read(file_inode(filp)); break; default: return -EINVAL; } if (l->l_start > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_start += l->l_start; if (fl->fl_start < 0) return -EINVAL; /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ if (l->l_len > 0) { if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_end = fl->fl_start + (l->l_len - 1); } else if (l->l_len < 0) { if (fl->fl_start + l->l_len < 0) return -EINVAL; fl->fl_end = fl->fl_start - 1; fl->fl_start += l->l_len; } else fl->fl_end = OFFSET_MAX; fl->c.flc_owner = current->files; fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; fl->c.flc_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; return assign_type(&fl->c, l->l_type); } /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX * style lock. */ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock *l) { struct flock64 ll = { .l_type = l->l_type, .l_whence = l->l_whence, .l_start = l->l_start, .l_len = l->l_len, }; return flock64_to_posix_lock(filp, fl, &ll); } /* default lease lock manager operations */ static bool lease_break_callback(struct file_lease *fl) { kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); return false; } static void lease_setup(struct file_lease *fl, void **priv) { struct file *filp = fl->c.flc_file; struct fasync_struct *fa = *priv; /* * fasync_insert_entry() returns the old entry if any. If there was no * old entry, then it used "priv" and inserted it into the fasync list. * Clear the pointer to indicate that it shouldn't be freed. */ if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa)) *priv = NULL; __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, }; /* * Initialize a lease, use the default lock manager operations */ static int lease_init(struct file *filp, int type, struct file_lease *fl) { if (assign_type(&fl->c, type) != 0) return -EINVAL; fl->c.flc_owner = filp; fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; fl->c.flc_flags = FL_LEASE; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ static struct file_lease *lease_alloc(struct file *filp, int type) { struct file_lease *fl = locks_alloc_lease(); int error = -ENOMEM; if (fl == NULL) return ERR_PTR(error); error = lease_init(filp, type, fl); if (error) { locks_free_lease(fl); return ERR_PTR(error); } return fl; } /* Check if two locks overlap each other. */ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) { return ((fl1->fl_end >= fl2->fl_start) && (fl2->fl_end >= fl1->fl_start)); } /* * Check whether two locks have the same owner. */ static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2) { return fl1->flc_owner == fl2->flc_owner; } /* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); percpu_rwsem_assert_held(&file_rwsem); spin_lock(&fll->lock); flc->flc_link_cpu = smp_processor_id(); hlist_add_head(&flc->flc_link, &fll->hlist); spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll; percpu_rwsem_assert_held(&file_rwsem); /* * Avoid taking lock if already unhashed. This is safe since this check * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&flc->flc_link)) return; fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu); spin_lock(&fll->lock); hlist_del_init(&flc->flc_link); spin_unlock(&fll->lock); } static unsigned long posix_owner_key(struct file_lock_core *flc) { return (unsigned long) flc->flc_owner; } static void locks_insert_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter)); } static void locks_delete_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_del(&waiter->flc_link); } /* Remove waiter from blocker's block list. * When blocker ends up pointing to itself then the list is empty. * * Must be called with blocked_lock_lock held. */ static void __locks_unlink_block(struct file_lock_core *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->flc_blocked_member); } static void __locks_wake_up_blocks(struct file_lock_core *blocker) { while (!list_empty(&blocker->flc_blocked_requests)) { struct file_lock_core *waiter; struct file_lock *fl; waiter = list_first_entry(&blocker->flc_blocked_requests, struct file_lock_core, flc_blocked_member); fl = file_lock(waiter); __locks_unlink_block(waiter); if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) && fl->fl_lmops && fl->fl_lmops->lm_notify) fl->fl_lmops->lm_notify(fl); else locks_wake_up(fl); /* * The setting of flc_blocker to NULL marks the "done" * point in deleting a block. Paired with acquire at the top * of locks_delete_block(). */ smp_store_release(&waiter->flc_blocker, NULL); } } static int __locks_delete_block(struct file_lock_core *waiter) { int status = -ENOENT; /* * If fl_blocker is NULL, it won't be set again as this thread "owns" * the lock and is the only one that might try to claim the lock. * * We use acquire/release to manage fl_blocker so that we can * optimize away taking the blocked_lock_lock in many cases. * * The smp_load_acquire guarantees two things: * * 1/ that fl_blocked_requests can be tested locklessly. If something * was recently added to that list it must have been in a locked region * *before* the locked region when fl_blocker was set to NULL. * * 2/ that no other thread is accessing 'waiter', so it is safe to free * it. __locks_wake_up_blocks is careful not to touch waiter after * fl_blocker is released. * * If a lockless check of fl_blocker shows it to be NULL, we know that * no new locks can be inserted into its fl_blocked_requests list, and * can avoid doing anything further if the list is empty. */ if (!smp_load_acquire(&waiter->flc_blocker) && list_empty(&waiter->flc_blocked_requests)) return status; spin_lock(&blocked_lock_lock); if (waiter->flc_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_unlink_block(waiter); /* * The setting of fl_blocker to NULL marks the "done" point in deleting * a block. Paired with acquire at the top of this function. */ smp_store_release(&waiter->flc_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } /** * locks_delete_block - stop waiting for a file lock * @waiter: the lock which was waiting * * lockd/nfsd need to disconnect the lock while working on it. */ int locks_delete_block(struct file_lock *waiter) { return __locks_delete_block(&waiter->c); } EXPORT_SYMBOL(locks_delete_block); /* Insert waiter into blocker's block list. * We use a circular list so that processes can be easily woken up in * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * * Must be called with both the flc_lock and blocked_lock_lock held. The * fl_blocked_requests list itself is protected by the blocked_lock_lock, * but by ensuring that the flc_lock is also held on insertions we can avoid * taking the blocked_lock_lock in some cases when we see that the * fl_blocked_requests list is empty. * * Rather than just adding to the list, we check for conflicts with any existing * waiters, and add beneath any waiter that blocks the new waiter. * Thus wakeups don't happen until needed. */ static void __locks_insert_block(struct file_lock_core *blocker, struct file_lock_core *waiter, bool conflict(struct file_lock_core *, struct file_lock_core *)) { struct file_lock_core *flc; BUG_ON(!list_empty(&waiter->flc_blocked_member)); new_blocker: list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member) if (conflict(flc, waiter)) { blocker = flc; goto new_blocker; } waiter->flc_blocker = blocker; list_add_tail(&waiter->flc_blocked_member, &blocker->flc_blocked_requests); if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX) locks_insert_global_blocked(waiter); /* The requests in waiter->flc_blocked are known to conflict with * waiter, but might not conflict with blocker, or the requests * and lock which block it. So they all need to be woken. */ __locks_wake_up_blocks(waiter); } /* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock_core *blocker, struct file_lock_core *waiter, bool conflict(struct file_lock_core *, struct file_lock_core *)) { spin_lock(&blocked_lock_lock); __locks_insert_block(blocker, waiter, conflict); spin_unlock(&blocked_lock_lock); } /* * Wake up processes blocked waiting for blocker. * * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock_core *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new * blocked requests are only added to the list under the flc_lock, and * the flc_lock is always held here. Note that removal from the * fl_blocked_requests list does not require the flc_lock, so we must * recheck list_empty() after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); __locks_wake_up_blocks(blocker); spin_unlock(&blocked_lock_lock); } static void locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before) { list_add_tail(&fl->flc_list, before); locks_insert_global_locks(fl); } static void locks_unlink_lock_ctx(struct file_lock_core *fl) { locks_delete_global_locks(fl); list_del_init(&fl->flc_list); locks_wake_up_blocks(fl); } static void locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose) { locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->flc_list, dispose); else locks_free_lock(file_lock(fl)); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ static bool locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { if (sys_flc->flc_type == F_WRLCK) return true; if (caller_flc->flc_type == F_WRLCK) return true; return false; } /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific * checking before calling the locks_conflict(). */ static bool posix_locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { struct file_lock *caller_fl = file_lock(caller_flc); struct file_lock *sys_fl = file_lock(sys_flc); /* POSIX locks owned by the same process do not conflict with * each other. */ if (posix_same_owner(caller_flc, sys_flc)) return false; /* Check whether they overlap */ if (!locks_overlap(caller_fl, sys_fl)) return false; return locks_conflict(caller_flc, sys_flc); } /* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK * path so checks for additional GETLK-specific things like F_UNLCK. */ static bool posix_test_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { struct file_lock_core *caller = &caller_fl->c; struct file_lock_core *sys = &sys_fl->c; /* F_UNLCK checks any locks on the same fd. */ if (lock_is_unlock(caller_fl)) { if (!posix_same_owner(caller, sys)) return false; return locks_overlap(caller_fl, sys_fl); } return posix_locks_conflict(caller, sys); } /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific * checking before calling the locks_conflict(). */ static bool flock_locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { /* FLOCK locks referring to the same filp do not conflict with * each other. */ if (caller_flc->flc_file == sys_flc->flc_file) return false; return locks_conflict(caller_flc, sys_flc); } void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; struct inode *inode = file_inode(filp); void *owner; void (*func)(void); ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->c.flc_type = F_UNLCK; return; } retry: spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) { if (!posix_test_locks_conflict(fl, cfl)) continue; if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { owner = cfl->fl_lmops->lm_mod_owner; func = cfl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); (*func)(); module_put(owner); goto retry; } locks_copy_conflock(fl, cfl); goto out; } fl->c.flc_type = F_UNLCK; out: spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); /* * Deadlock detection: * * We attempt to detect deadlocks that are due purely to posix file * locks. * * We assume that a task can be waiting for at most one lock at a time. * So for any acquired lock, the process holding that lock may be * waiting on at most one other lock. That lock in turns may be held by * someone waiting for at most one other lock. Given a requested lock * caller_fl which is about to wait for a conflicting lock block_fl, we * follow this chain of waiters to ensure we are not about to create a * cycle. * * Since we do this before we ever put a process to sleep on a lock, we * are ensured that there is never a cycle; that is what guarantees that * the while() loop in posix_locks_deadlock() eventually completes. * * Note: the above assumption may not be true when handling lock * requests from a broken NFS client. It may also fail in the presence * of tasks (such as posix threads) sharing the same open file table. * To handle those cases, we just bail out after a few iterations. * * For FL_OFDLCK locks, the owner is the filp, not the files_struct. * Because the owner is not even nominally tied to a thread of * execution, the deadlock detection below can't reasonably work well. Just * skip it for those. * * In principle, we could do a more limited deadlock detection on FL_OFDLCK * locks that just checks for the case where two tasks are attempting to * upgrade from read to write locks on the same inode. */ #define MAX_DEADLK_ITERATIONS 10 /* Find a lock that the owner of the given @blocker is blocking on. */ static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker) { struct file_lock_core *flc; hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) { if (posix_same_owner(flc, blocker)) { while (flc->flc_blocker) flc = flc->flc_blocker; return flc; } } return NULL; } /* Must be called with the blocked_lock_lock held! */ static bool posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { struct file_lock_core *caller = &caller_fl->c; struct file_lock_core *blocker = &block_fl->c; int i = 0; lockdep_assert_held(&blocked_lock_lock); /* * This deadlock detector can't reasonably detect deadlocks with * FL_OFDLCK locks, since they aren't owned by a process, per-se. */ if (caller->flc_flags & FL_OFDLCK) return false; while ((blocker = what_owner_is_waiting_for(blocker))) { if (i++ > MAX_DEADLK_ITERATIONS) return false; if (posix_same_owner(caller, blocker)) return true; } return false; } /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks * after any leases, but before any posix locks. * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ static int flock_lock_inode(struct inode *inode, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock *fl; struct file_lock_context *ctx; int error = 0; bool found = false; LIST_HEAD(dispose); ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) { if (request->c.flc_type != F_UNLCK) return -ENOMEM; return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0; } if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->c.flc_flags & FL_ACCESS) goto find_conflict; list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { if (request->c.flc_file != fl->c.flc_file) continue; if (request->c.flc_type == fl->c.flc_type) goto out; found = true; locks_delete_lock_ctx(&fl->c, &dispose); break; } if (lock_is_unlock(request)) { if ((request->c.flc_flags & FL_EXISTS) && !found) error = -ENOENT; goto out; } find_conflict: list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { if (!flock_locks_conflict(&request->c, &fl->c)) continue; error = -EAGAIN; if (!(request->c.flc_flags & FL_SLEEP)) goto out; error = FILE_LOCK_DEFERRED; locks_insert_block(&fl->c, &request->c, flock_locks_conflict); goto out; } if (request->c.flc_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock); new_fl = NULL; error = 0; out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); trace_flock_lock_inode(inode, request, error); return error; } static int posix_lock_inode(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); void *owner; void (*func)(void); ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) return lock_is_unlock(request) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. * * In some cases we can be sure, that no new locks will be needed */ if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK || request->fl_start != 0 || request->fl_end != OFFSET_MAX)) { new_fl = locks_alloc_lock(); new_fl2 = locks_alloc_lock(); } retry: percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->c.flc_type != F_UNLCK) { list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { if (!posix_locks_conflict(&request->c, &fl->c)) continue; if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable && (*fl->fl_lmops->lm_lock_expirable)(fl)) { owner = fl->fl_lmops->lm_mod_owner; func = fl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); (*func)(); module_put(owner); goto retry; } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; if (!(request->c.flc_flags & FL_SLEEP)) goto out; /* * Deadlock detection and insertion into the blocked * locks list must be done while holding the same lock! */ error = -EDEADLK; spin_lock(&blocked_lock_lock); /* * Ensure that we don't find any locks blocked on this * request during deadlock detection. */ __locks_wake_up_blocks(&request->c); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(&fl->c, &request->c, posix_locks_conflict); } spin_unlock(&blocked_lock_lock); goto out; } } /* If we're just looking for a conflict, we're done. */ error = 0; if (request->c.flc_flags & FL_ACCESS) goto out; /* Find the first old lock with the same owner as the new lock */ list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { if (posix_same_owner(&request->c, &fl->c)) break; } /* Process locks with this owner. */ list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) { if (!posix_same_owner(&request->c, &fl->c)) break; /* Detect adjacent or overlapping regions (if same lock type) */ if (request->c.flc_type == fl->c.flc_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ if (fl->fl_start - 1 > request->fl_end) break; /* If we come here, the new and old lock are of the * same type and adjacent or overlapping. Make one * lock yielding from the lower start address of both * locks to the higher end address. */ if (fl->fl_start > request->fl_start) fl->fl_start = request->fl_start; else request->fl_start = fl->fl_start; if (fl->fl_end < request->fl_end) fl->fl_end = request->fl_end; else request->fl_end = fl->fl_end; if (added) { locks_delete_lock_ctx(&fl->c, &dispose); continue; } request = fl; added = true; } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) continue; if (fl->fl_start > request->fl_end) break; if (lock_is_unlock(request)) added = true; if (fl->fl_start < request->fl_start) left = fl; /* If the next lock in the list has a higher end * address than the new one, insert the new one here. */ if (fl->fl_end > request->fl_end) { right = fl; break; } if (fl->fl_start >= request->fl_start) { /* The new lock completely replaces an old * one (This may happen several times). */ if (added) { locks_delete_lock_ctx(&fl->c, &dispose); continue; } /* * Replace the old lock with new_fl, and * remove the old one. It's safe to do the * insert here since we know that we won't be * using new_fl later, and that the lock is * just replacing an existing lock. */ error = -ENOLCK; if (!new_fl) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); request = new_fl; new_fl = NULL; locks_insert_lock_ctx(&request->c, &fl->c.flc_list); locks_delete_lock_ctx(&fl->c, &dispose); added = true; } } } /* * The above code only modifies existing locks in case of merging or * replacing. If new lock(s) need to be inserted all modifications are * done below this, so it's safe yet to bail out. */ error = -ENOLCK; /* "no luck" */ if (right && left == right && !new_fl2) goto out; error = 0; if (!added) { if (lock_is_unlock(request)) { if (request->c.flc_flags & FL_EXISTS) error = -ENOENT; goto out; } if (!new_fl) { error = -ENOLCK; goto out; } locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list); fl = new_fl; new_fl = NULL; } if (right) { if (left == right) { /* The new lock breaks the old one in two pieces, * so we have to use the second new lock. */ left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); locks_insert_lock_ctx(&left->c, &fl->c.flc_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(&right->c); } if (left) { left->fl_end = request->fl_start - 1; locks_wake_up_blocks(&left->c); } out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); trace_posix_lock_inode(inode, request, error); /* * Free any unused locks. */ if (new_fl) locks_free_lock(new_fl); if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); return error; } /** * posix_lock_file - Apply a POSIX-style lock to a file * @filp: The file to apply the lock to * @fl: The lock to be applied * @conflock: Place to return a copy of the conflicting lock, if found. * * Add a POSIX style lock to a file. * We merge adjacent & overlapping locks whenever possible. * POSIX locks are sorted by owner task, then by starting address * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); /** * posix_lock_inode_wait - Apply a POSIX-style lock to a file * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * * Apply a POSIX style lock request to an inode. */ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } static void lease_clear_pending(struct file_lease *fl, int arg) { switch (arg) { case F_UNLCK: fl->c.flc_flags &= ~FL_UNLOCK_PENDING; fallthrough; case F_RDLCK: fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING; } } /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { int error = assign_type(&fl->c, arg); if (error) return error; lease_clear_pending(fl, arg); locks_wake_up_blocks(&fl->c); if (arg == F_UNLCK) { struct file *filp = fl->c.flc_file; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } locks_delete_lock_ctx(&fl->c, dispose); } return 0; } EXPORT_SYMBOL(lease_modify); static bool past_time(unsigned long then) { if (!then) /* 0 is a special value meaning "this never expires": */ return false; return time_after(jiffies, then); } static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; struct file_lease *fl, *tmp; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) lease_modify(fl, F_UNLCK, dispose); } } static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc) { bool rc; struct file_lease *lease = file_lease(lc); struct file_lease *breaker = file_lease(bc); if (lease->fl_lmops->lm_breaker_owns_lease && lease->fl_lmops->lm_breaker_owns_lease(lease)) return false; if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) { rc = false; goto trace; } if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) { rc = false; goto trace; } rc = locks_conflict(bc, lc); trace: trace_leases_conflict(rc, lease, breaker); return rc; } static bool any_leases_conflict(struct inode *inode, struct file_lease *breaker) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock_core *flc; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(flc, &ctx->flc_lease, flc_list) { if (leases_conflict(flc, &breaker->c)) return true; } return false; } /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return * @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR: * break all leases * @type: FL_LEASE: break leases and delegations; FL_DELEG: break * only delegations * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on * a call to open() or truncate(). This function can sleep unless you * specified %O_NONBLOCK to your open(). */ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock_context *ctx; struct file_lease *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); new_fl->c.flc_flags = type; /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); if (!any_leases_conflict(inode, new_fl)) goto out; break_time = 0; if (lease_break_time > 0) { break_time = jiffies + lease_break_time * HZ; if (break_time == 0) break_time++; /* so that 0 means no break time */ } list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { if (!leases_conflict(&fl->c, &new_fl->c)) continue; if (want_write) { if (fl->c.flc_flags & FL_UNLOCK_PENDING) continue; fl->c.flc_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { if (lease_breaking(fl)) continue; fl->c.flc_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) locks_delete_lock_ctx(&fl->c, &dispose); } if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list); break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; locks_insert_block(&fl->c, &new_fl->c, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->c.flc_wait, list_empty(&new_fl->c.flc_blocked_member), break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); __locks_delete_block(&new_fl->c); if (error >= 0) { /* * Wait for the next conflicting lease that has not been * broken yet */ if (error == 0) time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; error = 0; } out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); free_lock: locks_free_lease(new_fl); return error; } EXPORT_SYMBOL(__break_lease); /** * lease_get_mtime - update modified time of an inode with exclusive lease * @inode: the inode * @time: pointer to a timespec which contains the last modified time * * This is to force NFS clients to flush their caches for files with * exclusive leases. The justification is that if someone has an * exclusive lease, then they could be modifying it. */ void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; struct file_lock_core *flc; ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); flc = list_first_entry_or_null(&ctx->flc_lease, struct file_lock_core, flc_list); if (flc && flc->flc_type == F_WRLCK) has_lease = true; spin_unlock(&ctx->flc_lock); } if (has_lease) *time = current_time(inode); } EXPORT_SYMBOL(lease_get_mtime); /** * fcntl_getlease - Enquire what lease is currently active * @filp: the file * * The value returned by this function will be one of * (if no lease break is pending): * * %F_RDLCK to indicate a shared lease is held. * * %F_WRLCK to indicate an exclusive lease is held. * * %F_UNLCK to indicate no lease is held. * * (if a lease break is pending): * * %F_RDLCK to indicate an exclusive lease needs to be * changed to a shared lease (or removed). * * %F_UNLCK to indicate the lease needs to be removed. * * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ int fcntl_getlease(struct file *filp) { struct file_lease *fl; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file != filp) continue; type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } return type; } /** * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * * Check to see if there's an existing open fd on this file that would * conflict with the lease we're trying to set. */ static int check_conflicting_open(struct file *filp, const int arg, int flags) { struct inode *inode = file_inode(filp); int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; if (flags & FL_DELEG) /* We leave these checks to the caller */ return 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; else if (arg != F_WRLCK) return 0; /* * Make sure that only read/write count is from lease requestor. * Note that this will result in denying write leases when i_writecount * is negative, which is what we want. (We shouldn't grant write leases * on files open for execution.) */ if (filp->f_mode & FMODE_WRITE) self_wcount = 1; else if (filp->f_mode & FMODE_READ) self_rcount = 1; if (atomic_read(&inode->i_writecount) != self_wcount || atomic_read(&inode->i_readcount) != self_rcount) return -EAGAIN; return 0; } static int generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv) { struct file_lease *fl, *my_fl = NULL, *lease; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->c.flc_flags & FL_DELEG; int error; LIST_HEAD(dispose); lease = *flp; trace_generic_add_lease(inode, lease); /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) return -ENOMEM; /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock * because delegations are an optional optimization, and if * there's some chance of a conflict--we'd rather not * bother, maybe that's a sign this just isn't a good file to * hand out a delegation on. */ if (is_deleg && !inode_trylock(inode)) return -EAGAIN; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(filp, arg, lease->c.flc_flags); if (error) goto out; /* * At this point, we know that if there is an exclusive * lease on this file, then we hold it on this filp * (otherwise our open of this file would have blocked). * And if we are trying to acquire an exclusive lease, * then the file is not open by anyone (including us) * except for this filp. */ error = -EAGAIN; list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file == filp && fl->c.flc_owner == lease->c.flc_owner) { my_fl = fl; continue; } /* * No exclusive leases if someone else has a lease on * this file: */ if (arg == F_WRLCK) goto out; /* * Modifying our existing lease is OK, but no getting a * new lease if someone else is opening for write: */ if (fl->c.flc_flags & FL_UNLOCK_PENDING) goto out; } if (my_fl != NULL) { lease = my_fl; error = lease->fl_lmops->lm_change(lease, arg, &dispose); if (error) goto out; goto out_setup; } error = -EINVAL; if (!leases_enable) goto out; locks_insert_lock_ctx(&lease->c, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting * open but before the lease was inserted. Check again for a * conflicting open and cancel the lease if there is one. * * We also add a barrier here to ensure that the insertion of the lock * precedes these checks. */ smp_mb(); error = check_conflicting_open(filp, arg, lease->c.flc_flags); if (error) { locks_unlink_lock_ctx(&lease->c); goto out; } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) *flp = NULL; return error; } static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lease *fl, *victim = NULL; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file == filp && fl->c.flc_owner == owner) { victim = fl; break; } } trace_generic_delete_lease(inode, victim); if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } /** * generic_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @flp: input - file_lock to use, output - file_lock inserted * @priv: private data for lm_setup (may be NULL if lm_setup * doesn't require it) * * The (input) flp->fl_lmops->lm_break function is required * by break_lease(). */ int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); case F_RDLCK: case F_WRLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; } return generic_add_lease(filp, arg, flp, priv); default: return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); /* * Kernel subsystems can register to be notified on any attempt to set * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd * to close files that it may have cached when there is an attempt to set a * conflicting lease. */ static struct srcu_notifier_head lease_notifier_chain; static inline void lease_notifier_chain_init(void) { srcu_init_notifier_head(&lease_notifier_chain); } static inline void setlease_notifier(int arg, struct file_lease *lease) { if (arg != F_UNLCK) srcu_notifier_call_chain(&lease_notifier_chain, arg, lease); } int lease_register_notifier(struct notifier_block *nb) { return srcu_notifier_chain_register(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { srcu_notifier_chain_unregister(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_unregister_notifier); int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { if (lease) setlease_notifier(arg, *lease); if (filp->f_op->setlease) return filp->f_op->setlease(filp, arg, lease, priv); else return generic_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(kernel_setlease); /** * vfs_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @lease: file_lock to use when adding a lease * @priv: private info for lm_setup when adding a lease (may be * NULL if lm_setup doesn't require it) * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It * may be NULL if the lm_setup operation doesn't require it. */ int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { struct inode *inode = file_inode(filp); vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode); int error; if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = security_file_lock(filp, arg); if (error) return error; return kernel_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(vfs_setlease); static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg) { struct file_lease *fl; struct fasync_struct *new; int error; fl = lease_alloc(filp, arg); if (IS_ERR(fl)) return PTR_ERR(fl); new = fasync_alloc(); if (!new) { locks_free_lease(fl); return -ENOMEM; } new->fa_fd = fd; error = vfs_setlease(filp, arg, &fl, (void **)&new); if (fl) locks_free_lease(fl); if (new) fasync_free(new); return error; } /** * fcntl_setlease - sets a lease on an open file * @fd: open file descriptor * @filp: file pointer * @arg: type of lease to obtain * * Call this fcntl to establish a lease on the file. * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, arg); } /** * flock_lock_inode_wait - Apply a FLOCK-style lock to a file * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a FLOCK style lock request to an inode. */ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /** * locks_lock_inode_wait - Apply a lock to an inode * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a POSIX or FLOCK style lock request to an inode. */ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int res = 0; switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: res = posix_lock_inode_wait(inode, fl); break; case FL_FLOCK: res = flock_lock_inode_wait(inode, fl); break; default: BUG(); } return res; } EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. * @fd: the file descriptor to lock. * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. * The @cmd can be one of: * * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED) * * %LOCK_MAND support has been removed from the kernel. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { int can_sleep, error, type; struct file_lock fl; struct fd f; /* * LOCK_MAND locks were broken for a long time in that they never * conflicted with one another and didn't prevent any sort of open, * read or write activity. * * Just ignore these requests now, to preserve legacy behavior, but * throw a warning to let people know that they don't actually work. */ if (cmd & LOCK_MAND) { pr_warn_once("%s(%d): Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n", current->comm, current->pid); return 0; } type = flock_translate_cmd(cmd & ~LOCK_NB); if (type < 0) return type; error = -EBADF; f = fdget(fd); if (!f.file) return error; if (type != F_UNLCK && !(f.file->f_mode & (FMODE_READ | FMODE_WRITE))) goto out_putf; flock_make_lock(f.file, &fl, type); error = security_file_lock(f.file, fl.c.flc_type); if (error) goto out_putf; can_sleep = !(cmd & LOCK_NB); if (can_sleep) fl.c.flc_flags |= FL_SLEEP; if (f.file->f_op->flock) error = f.file->f_op->flock(f.file, (can_sleep) ? F_SETLKW : F_SETLK, &fl); else error = locks_lock_file_wait(f.file, &fl); locks_release_private(&fl); out_putf: fdput(f); return error; } /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for * @fl: The lock to test; also used to hold result * * Returns -ERRNO on failure. Indicates presence of conflicting lock by * setting conf->fl_type to something other than F_UNLCK. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_test_lock); /** * locks_translate_pid - translate a file_lock's fl_pid number into a namespace * @fl: The file_lock who's fl_pid should be translated * @ns: The namespace into which the pid should be translated * * Used to translate a fl_pid into a namespace virtual pid number */ static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns) { pid_t vnr; struct pid *pid; if (fl->flc_flags & FL_OFDLCK) return -1; /* Remote locks report a negative pid value */ if (fl->flc_pid <= 0) return fl->flc_pid; /* * If the flock owner process is dead and its pid has been already * freed, the translation below won't work, but we still want to show * flock owner pid number in init pidns. */ if (ns == &init_pid_ns) return (pid_t) fl->flc_pid; rcu_read_lock(); pid = find_pid_ns(fl->flc_pid, &init_pid_ns); vnr = pid_nr_ns(pid, ns); rcu_read_unlock(); return vnr; } static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via * legacy 32bit flock. */ if (fl->fl_start > OFFT_OFFSET_MAX) return -EOVERFLOW; if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX) return -EOVERFLOW; #endif flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->c.flc_type; return 0; } #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->c.flc_type; } #endif /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; fl->c.flc_flags |= FL_OFDLCK; fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->c.flc_type; if (fl->c.flc_type != F_UNLCK) { error = posix_lock_to_flock(flock, fl); if (error) goto out; } out: locks_free_lock(fl); return error; } /** * vfs_lock_file - file byte range lock * @filp: The file to apply the lock to * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.) * @fl: The lock to be applied * @conf: Place to return a copy of the conflicting lock, if found. * * A caller that doesn't care about the conflicting lock may pass NULL * as the final argument. * * If the filesystem defines a private ->lock() method, then @conf will * be left unchanged; so a caller that cares should initialize it to * some acceptable default. * * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) * lm_grant is set. Additionally EXPORT_OP_ASYNC_LOCK in export_operations * flags need to be set. * * Callers expecting ->lock() to return asynchronously will only use F_SETLK, * not F_SETLKW; they will set FL_SLEEP if (and only if) the request is for a * blocking lock. When ->lock() does return asynchronously, it must return * FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine * with the result. If the request timed out the callback routine will return a * nonzero return code and the file system should release the lock. The file * system is also responsible to keep a corresponding posix lock when it * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); } EXPORT_SYMBOL_GPL(vfs_lock_file); static int do_lock_file_wait(struct file *filp, unsigned int cmd, struct file_lock *fl) { int error; error = security_file_lock(filp, fl->c.flc_type); if (error) return error; for (;;) { error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { switch (fl->c.flc_type) { case F_RDLCK: if (!(fl->c.flc_file->f_mode & FMODE_READ)) return -EBADF; break; case F_WRLCK: if (!(fl->c.flc_file->f_mode & FMODE_WRITE)) return -EBADF; } return 0; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = file_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; fallthrough; case F_SETLKW: file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Attempt to detect a close/fcntl race and recover by releasing the * lock that was just acquired. There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->c.flc_type != F_UNLCK && !(file_lock->c.flc_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { file_lock->c.flc_type = F_UNLCK; error = do_lock_file_wait(filp, cmd, file_lock); WARN_ON_ONCE(error); error = -EBADF; } } out: trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } #if BITS_PER_LONG == 32 /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock64_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; fl->c.flc_flags |= FL_OFDLCK; fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->c.flc_type; if (fl->c.flc_type != F_UNLCK) posix_lock_to_flock64(flock, fl); out: locks_free_lock(fl); return error; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK64; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; fallthrough; case F_SETLKW64: file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Attempt to detect a close/fcntl race and recover by releasing the * lock that was just acquired. There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->c.flc_type != F_UNLCK && !(file_lock->c.flc_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { file_lock->c.flc_type = F_UNLCK; error = do_lock_file_wait(filp, cmd, file_lock); WARN_ON_ONCE(error); error = -EBADF; } } out: locks_free_lock(file_lock); return error; } #endif /* BITS_PER_LONG == 32 */ /* * This function is called when the file is being removed * from the task's fd array. POSIX locks belonging to this task * are deleted at this time. */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; struct inode *inode = file_inode(filp); struct file_lock lock; struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; locks_init_lock(&lock); lock.c.flc_type = F_UNLCK; lock.c.flc_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; lock.c.flc_owner = owner; lock.c.flc_pid = current->tgid; lock.c.flc_file = filp; lock.fl_ops = NULL; lock.fl_lmops = NULL; error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); trace_locks_remove_posix(inode, &lock, error); } EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; struct inode *inode = file_inode(filp); if (list_empty(&flctx->flc_flock)) return; flock_make_lock(filp, &fl, F_UNLCK); fl.c.flc_flags |= FL_CLOSE; if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); else flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl); } /* The i_flctx must be valid when calling into here */ static void locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { struct file_lease *fl, *tmp; LIST_HEAD(dispose); if (list_empty(&ctx->flc_lease)) return; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) if (filp == fl->c.flc_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; ctx = locks_inode_context(file_inode(filp)); if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp, ctx); /* remove any leases */ locks_remove_lease(filp, ctx); spin_lock(&ctx->flc_lock); locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE"); spin_unlock(&ctx->flc_lock); } /** * vfs_cancel_lock - file byte range unblock lock * @filp: The file to apply the unblock to * @fl: The lock to be unblocked * * Used by lock managers to cancel blocked requests */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_cancel_lock); /** * vfs_inode_has_locks - are any file locks held on @inode? * @inode: inode to check for locks * * Return true if there are any FL_POSIX or FL_FLOCK locks currently * set on @inode. */ bool vfs_inode_has_locks(struct inode *inode) { struct file_lock_context *ctx; bool ret; ctx = locks_inode_context(inode); if (!ctx) return false; spin_lock(&ctx->flc_lock); ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); spin_unlock(&ctx->flc_lock); return ret; } EXPORT_SYMBOL_GPL(vfs_inode_has_locks); #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> struct locks_iterator { int li_cpu; loff_t li_pos; }; static void lock_get_status(struct seq_file *f, struct file_lock_core *flc, loff_t id, char *pfx, int repeat) { struct inode *inode = NULL; unsigned int pid; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); int type = flc->flc_type; struct file_lock *fl = file_lock(flc); pid = locks_translate_pid(flc, proc_pidns); /* * If lock owner is dead (and pid is freed) or not visible in current * pidns, zero is shown as a pid value. Check lock info from * init_pid_ns to get saved lock pid value. */ if (flc->flc_file != NULL) inode = file_inode(flc->flc_file); seq_printf(f, "%lld: ", id); if (repeat) seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx); if (flc->flc_flags & FL_POSIX) { if (flc->flc_flags & FL_ACCESS) seq_puts(f, "ACCESS"); else if (flc->flc_flags & FL_OFDLCK) seq_puts(f, "OFDLCK"); else seq_puts(f, "POSIX "); seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : "ADVISORY "); } else if (flc->flc_flags & FL_FLOCK) { seq_puts(f, "FLOCK ADVISORY "); } else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) { struct file_lease *lease = file_lease(flc); type = target_leasetype(lease); if (flc->flc_flags & FL_DELEG) seq_puts(f, "DELEG "); else seq_puts(f, "LEASE "); if (lease_breaking(lease)) seq_puts(f, "BREAKING "); else if (flc->flc_file) seq_puts(f, "ACTIVE "); else seq_puts(f, "BREAKER "); } else { seq_puts(f, "UNKNOWN UNKNOWN "); } seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : (type == F_RDLCK) ? "READ" : "UNLCK"); if (inode) { /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%lu ", pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { seq_printf(f, "%d <none>:0 ", pid); } if (flc->flc_flags & FL_POSIX) { if (fl->fl_end == OFFSET_MAX) seq_printf(f, "%Ld EOF\n", fl->fl_start); else seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end); } else { seq_puts(f, "0 EOF\n"); } } static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node) { struct file_lock_core *tmp; /* NULL node or root node */ if (node == NULL || node->flc_blocker == NULL) return NULL; /* Next member in the linked list could be itself */ tmp = list_next_entry(node, flc_blocked_member); if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests, flc_blocked_member) || tmp == node) { return NULL; } return tmp; } static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock_core *cur, *tmp; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); int level = 0; cur = hlist_entry(v, struct file_lock_core, flc_link); if (locks_translate_pid(cur, proc_pidns) == 0) return 0; /* View this crossed linked list as a binary tree, the first member of flc_blocked_requests * is the left child of current node, the next silibing in flc_blocked_member is the * right child, we can alse get the parent of current node from flc_blocker, so this * question becomes traversal of a binary tree */ while (cur != NULL) { if (level) lock_get_status(f, cur, iter->li_pos, "-> ", level); else lock_get_status(f, cur, iter->li_pos, "", level); if (!list_empty(&cur->flc_blocked_requests)) { /* Turn left */ cur = list_first_entry_or_null(&cur->flc_blocked_requests, struct file_lock_core, flc_blocked_member); level++; } else { /* Turn right */ tmp = get_next_blocked_member(cur); /* Fall back to parent node */ while (tmp == NULL && cur->flc_blocker != NULL) { cur = cur->flc_blocker; level--; tmp = get_next_blocked_member(cur); } cur = tmp; } } return 0; } static void __show_fd_locks(struct seq_file *f, struct list_head *head, int *id, struct file *filp, struct files_struct *files) { struct file_lock_core *fl; list_for_each_entry(fl, head, flc_list) { if (filp != fl->flc_file) continue; if (fl->flc_owner != files && fl->flc_owner != filp) continue; (*id)++; seq_puts(f, "lock:\t"); lock_get_status(f, fl, *id, "", 0); } } void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int id = 0; ctx = locks_inode_context(inode); if (!ctx) return; spin_lock(&ctx->flc_lock); __show_fd_locks(f, &ctx->flc_flock, &id, filp, files); __show_fd_locks(f, &ctx->flc_posix, &id, filp, files); __show_fd_locks(f, &ctx->flc_lease, &id, filp, files); spin_unlock(&ctx->flc_lock); } static void *locks_start(struct seq_file *f, loff_t *pos) __acquires(&blocked_lock_lock) { struct locks_iterator *iter = f->private; iter->li_pos = *pos + 1; percpu_down_write(&file_rwsem); spin_lock(&blocked_lock_lock); return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { struct locks_iterator *iter = f->private; ++iter->li_pos; return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) __releases(&blocked_lock_lock) { spin_unlock(&blocked_lock_lock); percpu_up_write(&file_rwsem); } static const struct seq_operations locks_seq_operations = { .start = locks_start, .next = locks_next, .stop = locks_stop, .show = locks_show, }; static int __init proc_locks_init(void) { proc_create_seq_private("locks", 0, NULL, &locks_seq_operations, sizeof(struct locks_iterator), NULL); return 0; } fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) { int i; flctx_cache = kmem_cache_create("file_lock_ctx", sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); filelease_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); spin_lock_init(&fll->lock); INIT_HLIST_HEAD(&fll->hlist); } lease_notifier_chain_init(); return 0; } core_initcall(filelock_init); |
| 134 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up(struct file_lock *fl) { wake_up(&fl->c.flc_wait); } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 84 84 84 84 84 84 84 84 84 84 84 84 84 84 84 84 28 84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include <linux/jump_label.h> #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/csd.h> #undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ __flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } static __always_inline void send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void send_call_function_ipi_mask(struct cpumask *mask) { trace_ipi_send_cpumask(mask, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } static __always_inline void csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) { trace_csd_function_entry(func, csd); func(info); trace_csd_function_exit(func, csd); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); /* * Parse the csdlock_debug= kernel boot parameter. * * If you need to restore the old "ext" value that once provided * additional debugging information, reapply the following commits: * * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") */ static int __init csdlock_debug(char *str) { int ret; unsigned int val = 0; ret = get_option(&str, &val); if (ret) { if (val) static_branch_enable(&csdlock_debug_enabled); else static_branch_disable(&csdlock_debug_enabled); } return 1; } __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ module_param(panic_on_ipistall, int, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(call_single_data_t *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline void csd_lock_record(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } static int csd_lock_wait_getcpu(call_single_data_t *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); return true; } ts2 = sched_clock(); /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) return false; firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ /* How long since this CSD lock was stuck. */ ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta, cpu, csd->func, csd->info); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering * on underflows when the TSC is out of sync between sockets. */ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } if (firsttime) dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static void __csd_lock_wait(call_single_data_t *csd) { int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = sched_clock(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } static __always_inline void csd_lock_wait(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); return; } smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else static void csd_lock_record(call_single_data_t *csd) { } static __always_inline void csd_lock_wait(call_single_data_t *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(call_single_data_t *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(call_single_data_t *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->node.u_flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * We have to check the type of the CSD before queueing it, because * once queued it can have its flags cleared by * flush_smp_call_function_queue() * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; csd = container_of(node, call_single_data_t, node.llist); func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* * The list addition should be visible to the target CPU when it pops * the head of the list to pull the entry off it in the IPI handler * because of normal cache coherency rules implied by the underlying * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, call_single_data_t *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->node.llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { __flush_smp_call_function_queue(true); } /** * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; atomic_t *tbt; lockdep_assert_irqs_disabled(); /* Allow waiters to send backtrace NMI from here onwards */ tbt = this_cpu_ptr(&trigger_backtrace); atomic_set_release(tbt, 1); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, node.llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } csd_lock_record(csd); csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->node.llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->node.llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) { csd = llist_entry(entry, typeof(*csd), node.llist); csd_do_func(sched_ttwu_pending, entry, csd); } } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * from task context (idle, migration thread) * * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to * handle queued SMP function calls before scheduling. * * The migration thread has to ensure that an eventually pending wakeup has * been handled before it migrates a task. */ void flush_smp_call_function_queue(void) { unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); __flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async() - Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. * * Return: %0 on success or negative errno value on error */ int smp_call_function_single_async(int cpu, call_single_data_t *csd) { int err = 0; preempt_disable(); if (csd->node.u_flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->node.u_flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /* * Flags to be used as scf_flags argument of smp_call_function_many_cond(). * * %SCF_WAIT: Wait until function execution is completed * %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask */ #define SCF_WAIT (1U << 0) #define SCF_RUN_LOCAL (1U << 1) static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, unsigned int scf_flags, smp_cond_func_t cond_func) { int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; int nr_cpus = 0; bool run_remote = false; bool run_local = false; lockdep_assert_preemption_disabled(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ if (cpu_online(this_cpu) && !oops_in_progress && !early_boot_irqs_disabled) lockdep_assert_irqs_enabled(); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Check if we need local execution. */ if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask)) run_local = true; /* Check if we need remote execution, i.e., any CPU excluding this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (cpu < nr_cpu_ids) run_remote = true; if (run_remote) { cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask); continue; } csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } } /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { unsigned long flags; local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags); } if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait * (atomically) until function has completed on other CPUs. If * %SCF_RUN_LOCAL is set, the function will also be run locally * if the local CPU is set in the @cpumask. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) set_nr_cpu_ids(nr_cpus); return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { unsigned int scf_flags = SCF_RUN_LOCAL; if (wait) scf_flags |= SCF_WAIT; preempt_disable(); smp_call_function_many_cond(mask, func, info, scf_flags, cond_func); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; for_each_possible_cpu(cpu) { preempt_disable(); if (cpu != smp_processor_id() && cpu_online(cpu)) wake_up_if_idle(cpu); preempt_enable(); } } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * struct smp_call_on_cpu_struct - Call a function on a specific CPU * @work: &work_struct * @done: &completion to signal * @func: function to call * @data: function's data argument * @ret: return value from @func * @cpu: target CPU (%-1 for any CPU) * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu-vm.c - vmalloc area based chunk allocation * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ #include "internal.h" static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { /* must not be used on pre-mapped chunk */ WARN_ON(chunk->immutable); return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /** * pcpu_get_pages - get temp pages array * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses * should be serialized by pcpu_alloc_mutex. * * RETURNS: * Pointer to temp pages array on success. */ static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } /** * pcpu_free_pages - free pages which were allocated for @chunk * @chunk: chunk pages were allocated for * @pages: array of pages to be freed, indexed by pcpu_page_idx() * @page_start: page index of the first page to be freed * @page_end: page index of the last page to be freed + 1 * * Free pages [@page_start and @page_end) in @pages for all units. * The pages were allocated for @chunk. */ static void pcpu_free_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page = pages[pcpu_page_idx(cpu, i)]; if (page) __free_page(page); } } } /** * pcpu_alloc_pages - allocates pages for @chunk * @chunk: target chunk * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end, gfp_t gfp) { unsigned int cpu, tcpu; int i; gfp |= __GFP_HIGHMEM; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); if (!*pagep) goto err; } } return 0; err: while (--i >= page_start) __free_page(pages[pcpu_page_idx(cpu, i)]); for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; for (i = page_start; i < page_end; i++) __free_page(pages[pcpu_page_idx(tcpu, i)]); } return -ENOMEM; } /** * pcpu_pre_unmap_flush - flush cache prior to unmapping * @chunk: chunk the regions to be flushed belongs to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages in [@page_start,@page_end) of @chunk are about to be * unmapped. Flush cache. As each flushing trial can be very * expensive, issue flush on the whole region at once rather than * doing it for each cpu. This could be an overkill but is more * scalable. */ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vunmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT)); } /** * pcpu_unmap_pages - unmap pages out of a pcpu_chunk * @chunk: chunk of interest * @pages: pages array which can be used to pass information to free * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * Corresponding elements in @pages were cleared by the caller and can * be used to carry information to pcpu_free_pages() which will be * called after all unmaps are finished. The caller should call * proper pre/post flush functions. */ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page; page = pcpu_chunk_page(chunk, cpu, i); WARN_ON(!page); pages[pcpu_page_idx(cpu, i)] = page; } __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), page_end - page_start); } } /** * pcpu_post_unmap_tlb_flush - flush TLB after unmapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush * TLB for the regions. This can be skipped if the area is to be * returned to vmalloc as vmalloc will handle TLB flushing lazily. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_tlb_kernel_range( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static int __pcpu_map_pages(unsigned long addr, struct page **pages, int nr_pages) { return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT), PAGE_KERNEL, pages, PAGE_SHIFT); } /** * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest * @pages: pages array containing pages to be mapped * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * * For each cpu, map pages [@page_start,@page_end) into @chunk. The * caller is responsible for calling pcpu_post_map_flush() after all * mappings are complete. * * This function is responsible for setting up whatever is necessary for * reverse lookup (addr -> chunk). */ static int pcpu_map_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu, tcpu; int i, err; for_each_possible_cpu(cpu) { err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), &pages[pcpu_page_idx(cpu, page_start)], page_end - page_start); if (err < 0) goto err; for (i = page_start; i < page_end; i++) pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], chunk); } return 0; err: for_each_possible_cpu(tcpu) { __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); if (tcpu == cpu) break; } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } /** * pcpu_post_map_flush - flush cache after mapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been mapped. Flush * cache. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } /** * pcpu_populate_chunk - populate and map an area of a pcpu_chunk * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. * * CONTEXT: * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp) { struct page **pages; pages = pcpu_get_pages(); if (!pages) return -ENOMEM; if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { pcpu_free_pages(chunk, pages, page_start, page_end); return -ENOMEM; } pcpu_post_map_flush(chunk, page_start, page_end); return 0; } /** * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk * @chunk: chunk to depopulate * @page_start: the start page * @page_end: the end page * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. * * Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the * region back to vmalloc() which will lazily flush the tlb. * * CONTEXT: * pcpu_alloc_mutex. */ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end) { struct page **pages; /* * If control reaches here, there must have been at least one * successful population attempt so the temp pages array must * be available now. */ pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ pcpu_pre_unmap_flush(chunk, page_start, page_end); pcpu_unmap_pages(chunk, pages, page_start, page_end); pcpu_free_pages(chunk, pages, page_start, page_end); } static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; } chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(chunk->base_addr); return chunk; } static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; pcpu_stats_chunk_dealloc(); trace_percpu_destroy_chunk(chunk->base_addr); if (chunk->data) pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } static struct page *pcpu_addr_to_page(void *addr) { return vmalloc_to_page(addr); } static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) { /* no extra restriction */ return 0; } /** * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim * @chunk: chunk of interest * * This is the entry point for percpu reclaim. If a chunk qualifies, it is then * isolated and managed in separate lists at the back of pcpu_slot: sidelined * and to_depopulate respectively. The to_depopulate list holds chunks slated * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once * they are on this list. Once depopulated, they are moved onto the sidelined * list which enables them to be pulled back in for allocation if no other chunk * can suffice the allocation. */ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) { /* do not reclaim either the first chunk or reserved chunk */ if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) return false; /* * If it is isolated, it may be on the sidelined list so move it back to * the to_depopulate list. If we hit at least 1/4 pages empty pages AND * there is no system-wide shortage of empty pages aside from this * chunk, move it to the to_depopulate list. */ return ((chunk->isolated && chunk->nr_empty_pop_pages) || (pcpu_nr_empty_pop_pages > (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); } |
| 17 17 11 11 11 9 9 9 9 8 9 9 9 4 4 1 4 4 4 3 3 3 3 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/mm/hugetlbpage.c * * Copyright (C) 2013 Linaro Ltd. * * Based on arch/x86/mm/hugetlbpage.c. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> /* * HugeTLB Support Matrix * * --------------------------------------------------- * | Page Size | CONT PTE | PMD | CONT PMD | PUD | * --------------------------------------------------- * | 4K | 64K | 2M | 32M | 1G | * | 16K | 2M | 32M | 1G | | * | 64K | 2M | 512M | 16G | | * --------------------------------------------------- */ /* * Reserve CMA areas for the largest supported gigantic * huge page when requested. Any other smaller gigantic * huge pages could still be served from those areas. */ #ifdef CONFIG_CMA void __init arm64_hugetlb_cma_reserve(void) { int order; if (pud_sect_supported()) order = PUD_SHIFT - PAGE_SHIFT; else order = CONT_PMD_SHIFT - PAGE_SHIFT; hugetlb_cma_reserve(order); } #endif /* CONFIG_CMA */ static bool __hugetlb_valid_size(unsigned long size) { switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return pud_sect_supported(); #endif case CONT_PMD_SIZE: case PMD_SIZE: case CONT_PTE_SIZE: return true; } return false; } #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { size_t pagesize = huge_page_size(h); if (!__hugetlb_valid_size(pagesize)) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); return false; } return true; } #endif static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { pgd_t *pgdp = pgd_offset(mm, addr); p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; *pgsize = PAGE_SIZE; p4dp = p4d_offset(pgdp, addr); pudp = pud_offset(p4dp, addr); pmdp = pmd_offset(pudp, addr); if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } return CONT_PTES; } static inline int num_contig_ptes(unsigned long size, size_t *pgsize) { int contig_ptes = 0; *pgsize = size; switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: if (pud_sect_supported()) contig_ptes = 1; break; #endif case PMD_SIZE: contig_ptes = 1; break; case CONT_PMD_SIZE: *pgsize = PMD_SIZE; contig_ptes = CONT_PMDS; break; case CONT_PTE_SIZE: *pgsize = PAGE_SIZE; contig_ptes = CONT_PTES; break; } return contig_ptes; } pte_t huge_ptep_get(pte_t *ptep) { int ncontig, i; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_present(orig_pte) || !pte_cont(orig_pte)) return orig_pte; ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize); for (i = 0; i < ncontig; i++, ptep++) { pte_t pte = __ptep_get(ptep); if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step. */ static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = __ptep_get(ptep); unsigned long i; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) { pte_t pte = __ptep_get_and_clear(mm, addr, ptep); /* * If HW_AFDBM is enabled, then the HW could turn on * the dirty or accessed bit for any page in the set, * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } static pte_t get_clear_contig_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig); struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, addr, addr + (pgsize * ncontig)); return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step for use cases where the * original pte is not needed. */ static void clear_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __ptep_get_and_clear(mm, addr, ptep); flush_tlb_range(&vma, saddr, addr); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { size_t pgsize; int i; int ncontig; unsigned long pfn, dpfn; pgprot_t hugeprot; ncontig = num_contig_ptes(sz, &pgsize); if (!pte_present(pte)) { for (i = 0; i < ncontig; i++, ptep++, addr += pgsize) __set_ptes(mm, addr, ptep, pte, 1); return; } if (!pte_cont(pte)) { __set_ptes(mm, addr, ptep, pte, 1); return; } pfn = pte_pfn(pte); dpfn = pgsize >> PAGE_SHIFT; hugeprot = pte_pgprot(pte); clear_flush(mm, addr, ptep, pgsize, ncontig); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep = NULL; pgdp = pgd_offset(mm, addr); p4dp = p4d_alloc(mm, pgdp, addr); if (!p4dp) return NULL; pudp = pud_alloc(mm, p4dp, addr); if (!pudp) return NULL; if (sz == PUD_SIZE) { ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); if (!pmdp) return NULL; WARN_ON(addr & (sz - 1)); ptep = pte_alloc_huge(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp))) ptep = huge_pmd_share(mm, vma, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (CONT_PMD_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); return (pte_t *)pmdp; } return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp, pud; pmd_t *pmdp, pmd; pgdp = pgd_offset(mm, addr); if (!pgd_present(READ_ONCE(*pgdp))) return NULL; p4dp = p4d_offset(pgdp, addr); if (!p4d_present(READ_ONCE(*p4dp))) return NULL; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ if (pud_leaf(pud) || !pud_present(pud)) return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; if (pmd_leaf(pmd) || !pmd_present(pmd)) return (pte_t *)pmdp; if (sz == CONT_PTE_SIZE) return pte_offset_huge(pmdp, (addr & CONT_PTE_MASK)); return NULL; } unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); switch (hp_size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return PGDIR_SIZE - PUD_SIZE; #endif case CONT_PMD_SIZE: return PUD_SIZE - CONT_PMD_SIZE; case PMD_SIZE: return PUD_SIZE - PMD_SIZE; case CONT_PTE_SIZE: return PMD_SIZE - CONT_PTE_SIZE; default: break; } return 0UL; } pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { size_t pagesize = 1UL << shift; entry = pte_mkhuge(entry); if (pagesize == CONT_PTE_SIZE) { entry = pte_mkcont(entry); } else if (pagesize == CONT_PMD_SIZE) { entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); } return entry; } void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { int i, ncontig; size_t pgsize; ncontig = num_contig_ptes(sz, &pgsize); for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __pte_clear(mm, addr, ptep); } pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { int ncontig; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_cont(orig_pte)) return __ptep_get_and_clear(mm, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig(mm, addr, ptep, pgsize, ncontig); } /* * huge_ptep_set_access_flags will update access flags (dirty, accesssed) * and write permission. * * For a contiguous huge pte range we need to check whether or not write * permission has to change only on the first pte in the set. Then for * all the contiguous ptes we need to check whether or not there is a * discrepancy between dirty or young. */ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) { int i; if (pte_write(pte) != pte_write(__ptep_get(ptep))) return 1; for (i = 0; i < ncontig; i++) { pte_t orig_pte = __ptep_get(ptep + i); if (pte_dirty(pte) != pte_dirty(orig_pte)) return 1; if (pte_young(pte) != pte_young(orig_pte)) return 1; } return 0; } int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { int ncontig, i; size_t pgsize = 0; unsigned long pfn = pte_pfn(pte), dpfn; struct mm_struct *mm = vma->vm_mm; pgprot_t hugeprot; pte_t orig_pte; if (!pte_cont(pte)) return __ptep_set_access_flags(vma, addr, ptep, pte, dirty); ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; if (!__cont_access_flags_changed(ptep, pte, ncontig)) return 0; orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte); if (pte_young(orig_pte)) pte = pte_mkyoung(pte); hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); return 1; } void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long pfn, dpfn; pgprot_t hugeprot; int ncontig, i; size_t pgsize; pte_t pte; if (!pte_cont(__ptep_get(ptep))) { __ptep_set_wrprotect(mm, addr, ptep); return; } ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); pte = pte_wrprotect(pte); hugeprot = pte_pgprot(pte); pfn = pte_pfn(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { struct mm_struct *mm = vma->vm_mm; size_t pgsize; int ncontig; if (!pte_cont(__ptep_get(ptep))) return ptep_clear_flush(vma, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); } static int __init hugetlbpage_init(void) { if (pud_sect_supported()) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT); return 0; } arch_initcall(hugetlbpage_init); bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable * in cases where cpu is affected with errata #2645198. */ if (pte_user_exec(__ptep_get(ptep))) return huge_ptep_clear_flush(vma, addr, ptep); } return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } |
| 3 3 3 4 1 3 3 3 5 4 5 4 3 2 1 2 1 2 3 8 5 5 5 5 5 5 15 14 14 14 14 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/eventfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #include <linux/file.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/kref.h> #include <linux/eventfd.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/idr.h> #include <linux/uio.h> static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { struct kref kref; wait_queue_head_t wqh; /* * Every time that a write(2) is performed on an eventfd, the * value of the __u64 being written is added to "count" and a * wakeup is performed on "wqh". If EFD_SEMAPHORE flag was not * specified, a read(2) will return the "count" value to userspace, * and will reset "count" to zero. The kernel side eventfd_signal() * also, adds to the "count" counter and issue a wakeup. */ __u64 count; unsigned int flags; int id; }; /** * eventfd_signal_mask - Increment the event counter * @ctx: [in] Pointer to the eventfd context. * @mask: [in] poll mask * * This function is supposed to be called by the kernel in paths that do not * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX * value, and we signal this as overflow condition by returning a EPOLLERR * to poll(2). */ void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask) { unsigned long flags; /* * Deadlock or stack overflow issues can happen if we recurse here * through waitqueue wakeup handlers. If the caller users potentially * nested waitqueues with custom wakeup handlers, then it should * check eventfd_signal_allowed() before calling this function. If * it returns false, the eventfd_signal() call should be deferred to a * safe context. */ if (WARN_ON_ONCE(current->in_eventfd)) return; spin_lock_irqsave(&ctx->wqh.lock, flags); current->in_eventfd = 1; if (ctx->count < ULLONG_MAX) ctx->count++; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask); current->in_eventfd = 0; spin_unlock_irqrestore(&ctx->wqh.lock, flags); } EXPORT_SYMBOL_GPL(eventfd_signal_mask); static void eventfd_free_ctx(struct eventfd_ctx *ctx) { if (ctx->id >= 0) ida_free(&eventfd_ida, ctx->id); kfree(ctx); } static void eventfd_free(struct kref *kref) { struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref); eventfd_free_ctx(ctx); } /** * eventfd_ctx_put - Releases a reference to the internal eventfd context. * @ctx: [in] Pointer to eventfd context. * * The eventfd context reference must have been previously acquired either * with eventfd_ctx_fdget() or eventfd_ctx_fileget(). */ void eventfd_ctx_put(struct eventfd_ctx *ctx) { kref_put(&ctx->kref, eventfd_free); } EXPORT_SYMBOL_GPL(eventfd_ctx_put); static int eventfd_release(struct inode *inode, struct file *file) { struct eventfd_ctx *ctx = file->private_data; wake_up_poll(&ctx->wqh, EPOLLHUP); eventfd_ctx_put(ctx); return 0; } static __poll_t eventfd_poll(struct file *file, poll_table *wait) { struct eventfd_ctx *ctx = file->private_data; __poll_t events = 0; u64 count; poll_wait(file, &ctx->wqh, wait); /* * All writes to ctx->count occur within ctx->wqh.lock. This read * can be done outside ctx->wqh.lock because we know that poll_wait * takes that lock (through add_wait_queue) if our caller will sleep. * * The read _can_ therefore seep into add_wait_queue's critical * section, but cannot move above it! add_wait_queue's spin_lock acts * as an acquire barrier and ensures that the read be ordered properly * against the writes. The following CAN happen and is safe: * * poll write * ----------------- ------------ * lock ctx->wqh.lock (in poll_wait) * count = ctx->count * __add_wait_queue * unlock ctx->wqh.lock * lock ctx->qwh.lock * ctx->count += n * if (waitqueue_active) * wake_up_locked_poll * unlock ctx->qwh.lock * eventfd_poll returns 0 * * but the following, which would miss a wakeup, cannot happen: * * poll write * ----------------- ------------ * count = ctx->count (INVALID!) * lock ctx->qwh.lock * ctx->count += n * **waitqueue_active is false** * **no wake_up_locked_poll!** * unlock ctx->qwh.lock * lock ctx->wqh.lock (in poll_wait) * __add_wait_queue * unlock ctx->wqh.lock * eventfd_poll returns 0 */ count = READ_ONCE(ctx->count); if (count > 0) events |= EPOLLIN; if (count == ULLONG_MAX) events |= EPOLLERR; if (ULLONG_MAX - 1 > count) events |= EPOLLOUT; return events; } void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { lockdep_assert_held(&ctx->wqh.lock); *cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count; ctx->count -= *cnt; } EXPORT_SYMBOL_GPL(eventfd_ctx_do_read); /** * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. * @ctx: [in] Pointer to eventfd context. * @wait: [in] Wait queue to be removed. * @cnt: [out] Pointer to the 64-bit counter value. * * Returns %0 if successful, or the following error codes: * * -EAGAIN : The operation would have blocked. * * This is used to atomically remove a wait queue entry from the eventfd wait * queue head, and read/reset the counter value. */ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt) { unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); eventfd_ctx_do_read(ctx, cnt); __remove_wait_queue(&ctx->wqh, wait); if (*cnt != 0 && waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLOUT); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return *cnt != 0 ? 0 : -EAGAIN; } EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue); static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct eventfd_ctx *ctx = file->private_data; __u64 ucnt = 0; if (iov_iter_count(to) < sizeof(ucnt)) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); if (!ctx->count) { if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { spin_unlock_irq(&ctx->wqh.lock); return -EAGAIN; } if (wait_event_interruptible_locked_irq(ctx->wqh, ctx->count)) { spin_unlock_irq(&ctx->wqh.lock); return -ERESTARTSYS; } } eventfd_ctx_do_read(ctx, &ucnt); current->in_eventfd = 1; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLOUT); current->in_eventfd = 0; spin_unlock_irq(&ctx->wqh.lock); if (unlikely(copy_to_iter(&ucnt, sizeof(ucnt), to) != sizeof(ucnt))) return -EFAULT; return sizeof(ucnt); } static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct eventfd_ctx *ctx = file->private_data; ssize_t res; __u64 ucnt; if (count != sizeof(ucnt)) return -EINVAL; if (copy_from_user(&ucnt, buf, sizeof(ucnt))) return -EFAULT; if (ucnt == ULLONG_MAX) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); res = -EAGAIN; if (ULLONG_MAX - ctx->count > ucnt) res = sizeof(ucnt); else if (!(file->f_flags & O_NONBLOCK)) { res = wait_event_interruptible_locked_irq(ctx->wqh, ULLONG_MAX - ctx->count > ucnt); if (!res) res = sizeof(ucnt); } if (likely(res > 0)) { ctx->count += ucnt; current->in_eventfd = 1; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); current->in_eventfd = 0; } spin_unlock_irq(&ctx->wqh.lock); return res; } #ifdef CONFIG_PROC_FS static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) { struct eventfd_ctx *ctx = f->private_data; __u64 cnt; spin_lock_irq(&ctx->wqh.lock); cnt = ctx->count; spin_unlock_irq(&ctx->wqh.lock); seq_printf(m, "eventfd-count: %16llx\n" "eventfd-id: %d\n" "eventfd-semaphore: %d\n", cnt, ctx->id, !!(ctx->flags & EFD_SEMAPHORE)); } #endif static const struct file_operations eventfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = eventfd_show_fdinfo, #endif .release = eventfd_release, .poll = eventfd_poll, .read_iter = eventfd_read, .write = eventfd_write, .llseek = noop_llseek, }; /** * eventfd_fget - Acquire a reference of an eventfd file descriptor. * @fd: [in] Eventfd file descriptor. * * Returns a pointer to the eventfd file structure in case of success, or the * following error pointer: * * -EBADF : Invalid @fd file descriptor. * -EINVAL : The @fd file descriptor is not an eventfd file. */ struct file *eventfd_fget(int fd) { struct file *file; file = fget(fd); if (!file) return ERR_PTR(-EBADF); if (file->f_op != &eventfd_fops) { fput(file); return ERR_PTR(-EINVAL); } return file; } EXPORT_SYMBOL_GPL(eventfd_fget); /** * eventfd_ctx_fdget - Acquires a reference to the internal eventfd context. * @fd: [in] Eventfd file descriptor. * * Returns a pointer to the internal eventfd context, otherwise the error * pointers returned by the following functions: * * eventfd_fget */ struct eventfd_ctx *eventfd_ctx_fdget(int fd) { struct eventfd_ctx *ctx; struct fd f = fdget(fd); if (!f.file) return ERR_PTR(-EBADF); ctx = eventfd_ctx_fileget(f.file); fdput(f); return ctx; } EXPORT_SYMBOL_GPL(eventfd_ctx_fdget); /** * eventfd_ctx_fileget - Acquires a reference to the internal eventfd context. * @file: [in] Eventfd file pointer. * * Returns a pointer to the internal eventfd context, otherwise the error * pointer: * * -EINVAL : The @fd file descriptor is not an eventfd file. */ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file) { struct eventfd_ctx *ctx; if (file->f_op != &eventfd_fops) return ERR_PTR(-EINVAL); ctx = file->private_data; kref_get(&ctx->kref); return ctx; } EXPORT_SYMBOL_GPL(eventfd_ctx_fileget); static int do_eventfd(unsigned int count, int flags) { struct eventfd_ctx *ctx; struct file *file; int fd; /* Check the EFD_* constants for consistency. */ BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK); BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0)); if (flags & ~EFD_FLAGS_SET) return -EINVAL; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; kref_init(&ctx->kref); init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL); flags &= EFD_SHARED_FCNTL_FLAGS; flags |= O_RDWR; fd = get_unused_fd_flags(flags); if (fd < 0) goto err; file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx, flags); if (IS_ERR(file)) { put_unused_fd(fd); fd = PTR_ERR(file); goto err; } file->f_mode |= FMODE_NOWAIT; fd_install(fd, file); return fd; err: eventfd_free_ctx(ctx); return fd; } SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) { return do_eventfd(count, flags); } SYSCALL_DEFINE1(eventfd, unsigned int, count) { return do_eventfd(count, 0); } |
| 16 16 157 157 157 157 156 16 16 16 16 16 16 16 15 16 16 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #include "internal.h" #ifdef CONFIG_MEMCG_KMEM static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static void list_lru_register(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { if (list_lru_memcg_aware(lru) && idx >= 0) { struct list_lru_memcg *mlru = xa_load(&lru->xa, idx); return mlru ? &mlru->node[nid] : NULL; } return &lru->node[nid].lru; } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } #endif /* CONFIG_MEMCG_KMEM */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (list_empty(item)) { l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); nlru->nr_items++; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ? mem_cgroup_from_slab_obj(item) : NULL; return list_lru_add(lru, item, nid, memcg); } EXPORT_SYMBOL_GPL(list_lru_add_obj); bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (!list_empty(item)) { l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_del_init(item); l->nr_items--; nlru->nr_items--; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_del); bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ? mem_cgroup_from_slab_obj(item) : NULL; return list_lru_del(lru, item, nid, memcg); } EXPORT_SYMBOL_GPL(list_lru_del_obj); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_one *l; long count; rcu_read_lock(); l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); if (unlikely(count < 0)) count = 0; return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return nlru->nr_items; } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; restart: l = list_lru_from_memcg_idx(lru, nid, memcg_idx); if (!l) goto out; list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, &nlru->lock, cb_arg); switch (ret) { case LRU_REMOVED_RETRY: assert_spin_locked(&nlru->lock); fallthrough; case LRU_REMOVED: isolated++; nlru->nr_items--; /* * If the lru lock has been dropped, our list * traversal is now invalid and so we have to * restart from scratch. */ if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_RETRY: /* * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ assert_spin_locked(&nlru->lock); goto restart; case LRU_STOP: assert_spin_locked(&nlru->lock); goto out; default: BUG(); } } out: return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock(&nlru->lock); ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); return ret; } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock_irq(&nlru->lock); ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock_irq(&nlru->lock); return ret; } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); #ifdef CONFIG_MEMCG_KMEM if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; unsigned long index; xa_for_each(&lru->xa, index, mlru) { struct list_lru_node *nlru = &lru->node[nid]; spin_lock(&nlru->lock); isolated += __list_lru_walk_one(lru, nid, index, isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); if (*nr_to_walk <= 0) break; } } #endif return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); l->nr_items = 0; } #ifdef CONFIG_MEMCG_KMEM static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp) { int nid; struct list_lru_memcg *mlru; mlru = kmalloc(struct_size(mlru, node, nr_node_ids), gfp); if (!mlru) return NULL; for_each_node(nid) init_one_lru(&mlru->node[nid]); return mlru; } static void memcg_list_lru_free(struct list_lru *lru, int src_idx) { struct list_lru_memcg *mlru = xa_erase_irq(&lru->xa, src_idx); /* * The __list_lru_walk_one() can walk the list of this node. * We need kvfree_rcu() here. And the walking of the list * is under lru->node[nid]->lock, which can serve as a RCU * read-side critical section. */ if (mlru) kvfree_rcu(mlru, rcu); } static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; } static void memcg_destroy_list_lru(struct list_lru *lru) { XA_STATE(xas, &lru->xa, 0); struct list_lru_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; xas_lock_irq(&xas); xas_for_each(&xas, mlru, ULONG_MAX) { kfree(mlru); xas_store(&xas, NULL); } xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, int src_idx, struct mem_cgroup *dst_memcg) { struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); src = list_lru_from_memcg_idx(lru, nid, src_idx); if (!src) goto out; dst = list_lru_from_memcg_idx(lru, nid, dst_idx); list_splice_init(&src->list, &dst->list); if (src->nr_items) { dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); src->nr_items = 0; } out: spin_unlock_irq(&nlru->lock); } static void memcg_reparent_list_lru(struct list_lru *lru, int src_idx, struct mem_cgroup *dst_memcg) { int i; for_each_node(i) memcg_reparent_list_lru_node(lru, i, src_idx, dst_memcg); memcg_list_lru_free(lru, src_idx); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { struct cgroup_subsys_state *css; struct list_lru *lru; int src_idx = memcg->kmemcg_id; /* * Change kmemcg_id of this cgroup and all its descendants to the * parent's id, and then move all entries from this cgroup's list_lrus * to ones of the parent. * * After we have finished, all list_lrus corresponding to this cgroup * are guaranteed to remain empty. So we can safely free this cgroup's * list lrus in memcg_list_lru_free(). * * Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc() * from allocating list lrus for this cgroup after memcg_list_lru_free() * call. */ rcu_read_lock(); css_for_each_descendant_pre(css, &memcg->css) { struct mem_cgroup *child; child = mem_cgroup_from_css(css); WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id); } rcu_read_unlock(); mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &memcg_list_lrus, list) memcg_reparent_list_lru(lru, src_idx, parent); mutex_unlock(&list_lrus_mutex); } static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, struct list_lru *lru) { int idx = memcg->kmemcg_id; return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { int i; unsigned long flags; struct list_lru_memcg_table { struct list_lru_memcg *mlru; struct mem_cgroup *memcg; } *table; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp); if (!table) return -ENOMEM; /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) { if (memcg_list_lru_allocated(memcg, lru)) break; table[i].memcg = memcg; table[i].mlru = memcg_init_list_lru_one(gfp); if (!table[i].mlru) { while (i--) kfree(table[i].mlru); kfree(table); return -ENOMEM; } } xas_lock_irqsave(&xas, flags); while (i--) { int index = READ_ONCE(table[i].memcg->kmemcg_id); struct list_lru_memcg *mlru = table[i].mlru; xas_set(&xas, index); retry: if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) { kfree(mlru); } else { xas_store(&xas, mlru); if (xas_error(&xas) == -ENOMEM) { xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) xas_set_err(&xas, 0); xas_lock_irqsave(&xas, flags); /* * The xas lock has been released, this memcg * can be reparented before us. So reload * memcg id. More details see the comments * in memcg_reparent_list_lrus(). */ index = READ_ONCE(table[i].memcg->kmemcg_id); if (index < 0) xas_set_err(&xas, 0); else if (!xas_error(&xas) && index != xas.xa_index) xas_set(&xas, index); goto retry; } } } /* xas_nomem() is used to free memory instead of memory allocation. */ if (xas.xa_alloc) xas_nomem(&xas, gfp); xas_unlock_irqrestore(&xas, flags); kfree(table); return xas_error(&xas); } #else static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG_KMEM */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker) { int i; #ifdef CONFIG_MEMCG_KMEM if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; if (mem_cgroup_kmem_disabled()) memcg_aware = false; #endif lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) return -ENOMEM; for_each_node(i) { spin_lock_init(&lru->node[i].lock); if (key) lockdep_set_class(&lru->node[i].lock, key); init_one_lru(&lru->node[i].lru); } memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG_KMEM lru->shrinker_id = -1; #endif } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 120 122 122 97 97 31 122 117 122 122 151 120 122 120 151 13 14 120 120 120 31 32 97 4 4 97 5 117 117 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* Are there any inode/mount/sb objects watched with priority prio or above? */ static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, int prio) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return false; return atomic_long_read(&sbinfo->watched_objects[prio]); } /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { return fsnotify_sb_has_priority_watchers(sb, 0); } /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path; if (file->f_mode & FMODE_NONOTIFY) return 0; path = &file->f_path; /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ if (mask & ALL_FSNOTIFY_PERM_EVENTS && !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, FSNOTIFY_PRIO_CONTENT)) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { __u32 fsnotify_mask = FS_ACCESS_PERM; /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection * must not be held. */ lockdep_assert_once(file_write_not_started(file)); if (!(perm_mask & MAY_READ)) return 0; return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_file_perm - permission hook before file access */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return fsnotify_file_area_perm(file, perm_mask, NULL, 0); } /* * fsnotify_open_perm - permission hook before file open */ static inline int fsnotify_open_perm(struct file *file) { int ret; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } return fsnotify_file(file, FS_OPEN_PERM); } #else static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; } static inline int fsnotify_open_perm(struct file *file) { return 0; } #endif /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/signalfd.h * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H #include <uapi/linux/signalfd.h> #include <linux/sched/signal.h> #ifdef CONFIG_SIGNALFD /* * Deliver the signal to listening signalfd. */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh))) wake_up(&tsk->sighand->signalfd_wqh); } extern void signalfd_cleanup(struct sighand_struct *sighand); #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } static inline void signalfd_cleanup(struct sighand_struct *sighand) { } #endif /* CONFIG_SIGNALFD */ #endif /* _LINUX_SIGNALFD_H */ |
| 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains the procedures for the handling of select and poll * * Created for Linux based loosely upon Mathius Lattner's minix * patches by Peter MacDonald. Heavily edited by Linus. * * 4 February 1994 * COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS * flag set in its personality we do *not* modify the given timeout * parameter to reflect time remaining. * * 24 January 2000 * Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation * of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian). */ #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/rt.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/personality.h> /* for STICKY_TIMEOUTS */ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/freezer.h> #include <net/busy_poll.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> /* * Estimate expected accuracy in ns from a timeval. * * After quite a bit of churning around, we've settled on * a simple thing of taking 0.1% of the timeout as the * slack, with a cap of 100 msec. * "nice" tasks get a 0.5% slack instead. * * Consider this comment an open invitation to come up with even * better solutions.. */ #define MAX_SLACK (100 * NSEC_PER_MSEC) static long __estimate_accuracy(struct timespec64 *tv) { long slack; int divfactor = 1000; if (tv->tv_sec < 0) return 0; if (task_nice(current) > 0) divfactor = divfactor / 5; if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor)) return MAX_SLACK; slack = tv->tv_nsec / divfactor; slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); if (slack > MAX_SLACK) return MAX_SLACK; return slack; } u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; /* * Realtime tasks get a slack of 0 for obvious reasons. */ if (rt_task(current)) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); if (ret < current->timer_slack_ns) return current->timer_slack_ns; return ret; } struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; struct poll_table_entry entries[]; }; #define POLL_TABLE_FULL(table) \ ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table)) /* * Ok, Peter made a complicated, but straightforward multiple_wait() function. * I have rewritten this, taking some shortcuts: This code may not be easy to * follow, but it should be free of race-conditions, and it's practical. If you * understand what I'm doing here, then you understand how the linux * sleep/wakeup mechanism works. * * Two very simple procedures, poll_wait() and poll_freewait() make all the * work. poll_wait() is an inline-function defined in <linux/poll.h>, * as all select/poll functions have to call it to add an entry to the * poll table. */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p); void poll_initwait(struct poll_wqueues *pwq) { init_poll_funcptr(&pwq->pt, __pollwait); pwq->polling_task = current; pwq->triggered = 0; pwq->error = 0; pwq->table = NULL; pwq->inline_index = 0; } EXPORT_SYMBOL(poll_initwait); static void free_poll_entry(struct poll_table_entry *entry) { remove_wait_queue(entry->wait_address, &entry->wait); fput(entry->filp); } void poll_freewait(struct poll_wqueues *pwq) { struct poll_table_page * p = pwq->table; int i; for (i = 0; i < pwq->inline_index; i++) free_poll_entry(pwq->inline_entries + i); while (p) { struct poll_table_entry * entry; struct poll_table_page *old; entry = p->entry; do { entry--; free_poll_entry(entry); } while (entry > p->entries); old = p; p = p->next; free_page((unsigned long) old); } } EXPORT_SYMBOL(poll_freewait); static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) return p->inline_entries + p->inline_index++; if (!table || POLL_TABLE_FULL(table)) { struct poll_table_page *new_table; new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; return NULL; } new_table->entry = new_table->entries; new_table->next = table; p->table = new_table; table = new_table; } return table->entry++; } static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); /* * Although this function is called under waitqueue lock, LOCK * doesn't imply write barrier and the users expect write * barrier semantics on wakeup functions. The following * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() * and is paired with smp_store_mb() in poll_schedule_timeout. */ smp_wmb(); pwq->triggered = 1; /* * Perform the default wake up operation using a dummy * waitqueue. * * TODO: This is hacky but there currently is no interface to * pass in @sync. @sync is scheduled to be removed and once * that happens, wake_up_process() can be used directly. */ return default_wake_function(&dummy_wait, mode, sync, key); } static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; entry = container_of(wait, struct poll_table_entry, wait); if (key && !(key_to_poll(key) & entry->key)) return 0; return __pollwake(wait, mode, sync, key); } /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); } static int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack) { int rc = -EINTR; set_current_state(state); if (!pwq->triggered) rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * Prepare for the next iteration. * * The following smp_store_mb() serves two purposes. First, it's * the counterpart rmb of the wmb in pollwake() such that data * written before wake up is always visible after wake up. * Second, the full barrier guarantees that triggered clearing * doesn't pass event check of the next iteration. Note that * this problem doesn't exist for the first iteration as * add_wait_queue() has full barrier semantics. */ smp_store_mb(pwq->triggered, 0); return rc; } /** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec64 variable for the final timeout * @sec: seconds (from user space) * @nsec: nanoseconds (from user space) * * Note, we do not use a timespec for the user space value here, That * way we can use the function for timeval and compat interfaces as well. * * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. */ int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec) { struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec}; if (!timespec64_valid(&ts)) return -EINVAL; /* Optimize for the zero timeout value here */ if (!sec && !nsec) { to->tv_sec = to->tv_nsec = 0; } else { ktime_get_ts64(to); *to = timespec64_add_safe(*to, ts); } return 0; } enum poll_time_type { PT_TIMEVAL = 0, PT_OLD_TIMEVAL = 1, PT_TIMESPEC = 2, PT_OLD_TIMESPEC = 3, }; static int poll_select_finish(struct timespec64 *end_time, void __user *p, enum poll_time_type pt_type, int ret) { struct timespec64 rts; restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); if (!p) return ret; if (current->personality & STICKY_TIMEOUTS) goto sticky; /* No update for zero timeout */ if (!end_time->tv_sec && !end_time->tv_nsec) return ret; ktime_get_ts64(&rts); rts = timespec64_sub(*end_time, rts); if (rts.tv_sec < 0) rts.tv_sec = rts.tv_nsec = 0; switch (pt_type) { case PT_TIMEVAL: { struct __kernel_old_timeval rtv; if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec)) memset(&rtv, 0, sizeof(rtv)); rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_OLD_TIMEVAL: { struct old_timeval32 rtv; rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_TIMESPEC: if (!put_timespec64(&rts, p)) return ret; break; case PT_OLD_TIMESPEC: if (!put_old_timespec32(&rts, p)) return ret; break; default: BUG(); } /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to * cause a fault after the select has completed * successfully. However, because we're not updating the * timeval, we can't restart the system call. */ sticky: if (ret == -ERESTARTNOHAND) ret = -EINTR; return ret; } /* * Scalable version of the fd_set. */ typedef struct { unsigned long *in, *out, *ex; unsigned long *res_in, *res_out, *res_ex; } fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG (8*sizeof(long)) #define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */ static inline int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { nr = FDS_BYTES(nr); if (ufdset) return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; memset(fdset, 0, nr); return 0; } static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { if (ufdset) return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); return 0; } static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { memset(fdset, 0, FDS_BYTES(nr)); } #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) #define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n)) static int max_select_fd(unsigned long n, fd_set_bits *fds) { unsigned long *open_fds; unsigned long set; int max; struct fdtable *fdt; /* handle last in-complete long-word first */ set = ~(~0UL << (n & (BITS_PER_LONG-1))); n /= BITS_PER_LONG; fdt = files_fdtable(current->files); open_fds = fdt->open_fds + n; max = 0; if (set) { set &= BITS(fds, n); if (set) { if (!(set & ~*open_fds)) goto get_max; return -EBADF; } } while (n) { open_fds--; n--; set = BITS(fds, n); if (!set) continue; if (set & ~*open_fds) return -EBADF; if (max) continue; get_max: do { max++; set >>= 1; } while (set); max += n * BITS_PER_LONG; } return max; } #define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ EPOLLNVAL) #define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ EPOLLNVAL) #define POLLEX_SET (EPOLLPRI | EPOLLNVAL) static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) wait->_key |= POLLOUT_SET; } static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); rcu_read_unlock(); if (retval < 0) return retval; n = retval; poll_initwait(&table); wait = &table.pt; if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; bool can_busy_loop = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; for (i = 0; i < n; ++rinp, ++routp, ++rexp) { unsigned long in, out, ex, all_bits, bit = 1, j; unsigned long res_in = 0, res_out = 0, res_ex = 0; __poll_t mask; in = *inp++; out = *outp++; ex = *exp++; all_bits = in | out | ex; if (all_bits == 0) { i += BITS_PER_LONG; continue; } for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) { struct fd f; if (i >= n) break; if (!(bit & all_bits)) continue; mask = EPOLLNVAL; f = fdget(i); if (f.file) { wait_key_set(wait, in, out, bit, busy_flag); mask = vfs_poll(f.file, wait); fdput(f); } if ((mask & POLLIN_SET) && (in & bit)) { res_in |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |= bit; retval++; wait->_qproc = NULL; } /* got something, stop busy polling */ if (retval) { can_busy_loop = false; busy_flag = 0; /* * only remember a returned * POLL_BUSY_LOOP if we asked for it */ } else if (busy_flag & mask) can_busy_loop = true; } if (res_in) *rinp = res_in; if (res_out) *routp = res_out; if (res_ex) *rexp = res_ex; cond_resched(); } wait->_qproc = NULL; if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } poll_freewait(&table); return retval; } /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int ret, max_fds; size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; if (size > (SIZE_MAX / 6)) goto out_nofds; alloc_size = 6 * size; bits = kvmalloc(alloc_size, GFP_KERNEL); if (!bits) goto out_nofds; } fds.in = bits; fds.out = bits + size; fds.ex = bits + 2*size; fds.res_in = bits + 3*size; fds.res_out = bits + 4*size; fds.res_ex = bits + 5*size; if ((ret = get_fd_set(n, inp, fds.in)) || (ret = get_fd_set(n, outp, fds.out)) || (ret = get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (set_fd_set(n, inp, fds.res_in) || set_fd_set(n, outp, fds.res_out) || set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kvfree(bits); out_nofds: return ret; } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct __kernel_old_timeval tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret); } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, void __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } /* * Most architectures can't handle 7-argument syscalls. So we provide a * 6-argument version where the sixth argument is a pointer to a structure * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ struct sigset_argpack { sigset_t __user *p; size_t size; }; static inline int get_sigset_argpack(struct sigset_argpack *to, struct sigset_argpack __user *from) { // the path is hot enough for overhead of copy_from_user() to matter if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_OLD_TIMESPEC); } #endif #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) { struct sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif struct poll_list { struct poll_list *next; unsigned int len; struct pollfd entries[]; }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) /* * Fish for pollable events on the pollfd->fd file descriptor. We're only * interested in events matching the pollfd->events mask, and the result * matching that mask is both recorded in pollfd->revents and returned. The * pwait poll_table will be used by the fd-provided poll handler for waiting, * if pwait->_qproc is non-NULL. */ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, bool *can_busy_poll, __poll_t busy_flag) { int fd = pollfd->fd; __poll_t mask = 0, filter; struct fd f; if (fd < 0) goto out; mask = EPOLLNVAL; f = fdget(fd); if (!f.file) goto out; /* userland u16 ->events contains POLL... bitmap */ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; pwait->_key = filter | busy_flag; mask = vfs_poll(f.file, pwait); if (mask & busy_flag) *can_busy_poll = true; mask &= filter; /* Mask out unneeded events. */ fdput(f); out: /* ... and so does ->revents */ pollfd->revents = mangle_poll(mask); return mask; } static int do_poll(struct poll_list *list, struct poll_wqueues *wait, struct timespec64 *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); for (;;) { struct poll_list *walk; bool can_busy_loop = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; pfd = walk->entries; pfd_end = pfd + walk->len; for (; pfd != pfd_end; pfd++) { /* * Fish for events. If we found one, record it * and kill poll_table->_qproc, so we don't * needlessly register any other waiters after * this. They'll get immediately deregistered * when we break out and return. */ if (do_pollfd(pfd, pt, &can_busy_loop, busy_flag)) { count++; pt->_qproc = NULL; /* found something, stop busy polling */ busy_flag = 0; can_busy_loop = false; } } } /* * All waiters have already been registered, so don't provide * a poll_table->_qproc to them on the next loop iteration. */ pt->_qproc = NULL; if (!count) { count = wait->error; if (signal_pending(current)) count = -ERESTARTNOHAND; } if (count || timed_out) break; /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } return count; } #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; struct poll_list *const head = (struct poll_list *)stack_pps; struct poll_list *walk = head; unsigned int todo = nfds; unsigned int len; if (nfds > rlimit(RLIMIT_NOFILE)) return -EINVAL; len = min_t(unsigned int, nfds, N_STACK_PPS); for (;;) { walk->next = NULL; walk->len = len; if (!len) break; if (copy_from_user(walk->entries, ufds + nfds-todo, sizeof(struct pollfd) * walk->len)) goto out_fds; if (walk->len >= todo) break; todo -= walk->len; len = min(todo, POLLFD_PER_PAGE); walk = walk->next = kmalloc(struct_size(walk, entries, len), GFP_KERNEL); if (!walk) { err = -ENOMEM; goto out_fds; } } poll_initwait(&table); fdcount = do_poll(head, &table, end_time); poll_freewait(&table); if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) goto out_fds; for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; unsigned int j; for (j = walk->len; j; fds++, ufds++, j--) unsafe_put_user(fds->revents, &ufds->revents, Efault); } user_write_access_end(); err = fdcount; out_fds: walk = head->next; while (walk) { struct poll_list *pos = walk; walk = walk->next; kfree(pos); } return err; Efault: user_write_access_end(); err = -EFAULT; goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) { struct pollfd __user *ufds = restart_block->poll.ufds; int nfds = restart_block->poll.nfds; struct timespec64 *to = NULL, end_time; int ret; if (restart_block->poll.has_timeout) { end_time.tv_sec = restart_block->poll.tv_sec; end_time.tv_nsec = restart_block->poll.tv_nsec; to = &end_time; } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) ret = set_restart_fn(restart_block, do_restart_poll); return ret; } SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout_msecs) { struct timespec64 end_time, *to = NULL; int ret; if (timeout_msecs >= 0) { to = &end_time; poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) { struct restart_block *restart_block; restart_block = ¤t->restart_block; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; if (timeout_msecs >= 0) { restart_block->poll.tv_sec = end_time.tv_sec; restart_block->poll.tv_nsec = end_time.tv_nsec; restart_block->poll.has_timeout = 1; } else restart_block->poll.has_timeout = 0; ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif #ifdef CONFIG_COMPAT #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (ufdset) { return compat_get_bitmap(fdset, ufdset, nr); } else { zero_fd_set(nr, fdset); return 0; } } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (!ufdset) return 0; return compat_put_bitmap(ufdset, fdset, nr); } /* * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ static int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { bits = kmalloc_array(6, size, GFP_KERNEL); ret = -ENOMEM; if (!bits) goto out_nofds; } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); fds.res_in = (unsigned long *) (bits + 3*size); fds.res_out = (unsigned long *) (bits + 4*size); fds.res_ex = (unsigned long *) (bits + 5*size); if ((ret = compat_get_fd_set(n, inp, fds.in)) || (ret = compat_get_fd_set(n, outp, fds.out)) || (ret = compat_get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (compat_set_fd_set(n, inp, fds.res_in) || compat_set_fd_set(n, outp, fds.res_out) || compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kfree(bits); out_nofds: return ret; } static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; struct old_timeval32 tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret); } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } struct compat_sel_arg_struct { compat_ulong_t n; compat_uptr_t inp; compat_uptr_t outp; compat_uptr_t exp; compat_uptr_t tvp; }; COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { struct compat_sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), compat_ptr(a.exp), compat_ptr(a.tvp)); } static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, void __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } struct compat_sigset_argpack { compat_uptr_t p; compat_size_t size; }; static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, struct compat_sigset_argpack __user *from) { if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_OLD_TIMESPEC); } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif /* New compat syscall for 64 bit time_t*/ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ #define LOOKUP_DIRECTORY 0x0002 /* require a directory */ #define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ #define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ #define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ #define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN 0x0100 /* ... in open */ #define LOOKUP_CREATE 0x0200 /* ... in object creation */ #define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ #define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ /* internal use only */ #define LOOKUP_PARENT 0x0010 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ #define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); static inline int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { return user_path_at_empty(dfd, name, flags, path, NULL); } struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ #include <linux/args.h> #include <linux/array_size.h> #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ #include <linux/err.h> /* for ERR_PTR() */ #include <linux/errno.h> /* for E2BIG */ #include <linux/overflow.h> /* for check_mul_overflow() */ #include <linux/stdarg.h> #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); extern void *memdup_user(const void __user *, size_t) __realloc_size(2); extern void *vmemdup_user(const void __user *, size_t) __realloc_size(2); extern void *memdup_user_nul(const void __user *, size_t); /** * memdup_array_user - duplicate array from user space * @src: source address in user space * @n: number of array members to copy * @size: size of one array member * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ static inline __realloc_size(2, 3) void *memdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; if (check_mul_overflow(n, size, &nbytes)) return ERR_PTR(-EOVERFLOW); return memdup_user(src, nbytes); } /** * vmemdup_array_user - duplicate array from user space * @src: source address in user space * @n: number of array members to copy * @size: size of one array member * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ static inline __realloc_size(2, 3) void *vmemdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; if (check_mul_overflow(n, size, &nbytes)) return ERR_PTR(-EOVERFLOW); return vmemdup_user(src, nbytes); } /* * Include machine specific inline routines */ #include <asm/string.h> #ifndef __HAVE_ARCH_STRCPY extern char * strcpy(char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCPY extern char * strncpy(char *,const char *, __kernel_size_t); #endif ssize_t sized_strscpy(char *, const char *, size_t); /* * The 2 argument style can only be used when dst is an array with a * known size. */ #define __strscpy0(dst, src, ...) \ sized_strscpy(dst, src, sizeof(dst) + __must_be_array(dst)) #define __strscpy1(dst, src, size) sized_strscpy(dst, src, size) #define __strscpy_pad0(dst, src, ...) \ sized_strscpy_pad(dst, src, sizeof(dst) + __must_be_array(dst)) #define __strscpy_pad1(dst, src, size) sized_strscpy_pad(dst, src, size) /** * strscpy - Copy a C-string into a sized buffer * @dst: Where to copy the string to * @src: Where to copy the string from * @...: Size of destination buffer (optional) * * Copy the source string @src, or as much of it as fits, into the * destination @dst buffer. The behavior is undefined if the string * buffers overlap. The destination @dst buffer is always NUL terminated, * unless it's zero-sized. * * The size argument @... is only required when @dst is not an array, or * when the copy needs to be smaller than sizeof(@dst). * * Preferred to strncpy() since it always returns a valid string, and * doesn't unnecessarily force the tail of the destination buffer to be * zero padded. If padding is desired please use strscpy_pad(). * * Returns the number of characters copied in @dst (not including the * trailing %NUL) or -E2BIG if @size is 0 or the copy from @src was * truncated. */ #define strscpy(dst, src, ...) \ CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__) #define sized_strscpy_pad(dest, src, count) ({ \ char *__dst = (dest); \ const char *__src = (src); \ const size_t __count = (count); \ ssize_t __wrote; \ \ __wrote = sized_strscpy(__dst, __src, __count); \ if (__wrote >= 0 && __wrote < __count) \ memset(__dst + __wrote + 1, 0, __count - __wrote - 1); \ __wrote; \ }) /** * strscpy_pad() - Copy a C-string into a sized buffer * @dst: Where to copy the string to * @src: Where to copy the string from * @...: Size of destination buffer * * Copy the string, or as much of it as fits, into the dest buffer. The * behavior is undefined if the string buffers overlap. The destination * buffer is always %NUL terminated, unless it's zero-sized. * * If the source string is shorter than the destination buffer, the * remaining bytes in the buffer will be filled with %NUL bytes. * * For full explanation of why you may want to consider using the * 'strscpy' functions please see the function docstring for strscpy(). * * Returns: * * The number of characters copied (not including the trailing %NULs) * * -E2BIG if count is 0 or @src was truncated. */ #define strscpy_pad(dst, src, ...) \ CONCATENATE(__strscpy_pad, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__) #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif #ifndef __HAVE_ARCH_STRNCAT extern char * strncat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCAT extern size_t strlcat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCMP extern int strcmp(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCMP extern int strncmp(const char *,const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCASECMP extern int strcasecmp(const char *s1, const char *s2); #endif #ifndef __HAVE_ARCH_STRNCASECMP extern int strncasecmp(const char *s1, const char *s2, size_t n); #endif #ifndef __HAVE_ARCH_STRCHR extern char * strchr(const char *,int); #endif #ifndef __HAVE_ARCH_STRCHRNUL extern char * strchrnul(const char *,int); #endif extern char * strnchrnul(const char *, size_t, int); #ifndef __HAVE_ARCH_STRNCHR extern char * strnchr(const char *, size_t, int); #endif #ifndef __HAVE_ARCH_STRRCHR extern char * strrchr(const char *,int); #endif extern char * __must_check skip_spaces(const char *); extern char *strim(char *); static inline __must_check char *strstrip(char *str) { return strim(str); } #ifndef __HAVE_ARCH_STRSTR extern char * strstr(const char *, const char *); #endif #ifndef __HAVE_ARCH_STRNSTR extern char * strnstr(const char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRLEN extern __kernel_size_t strlen(const char *); #endif #ifndef __HAVE_ARCH_STRNLEN extern __kernel_size_t strnlen(const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRPBRK extern char * strpbrk(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRSEP extern char * strsep(char **,const char *); #endif #ifndef __HAVE_ARCH_STRSPN extern __kernel_size_t strspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRCSPN extern __kernel_size_t strcspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET16 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET32 extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET64 extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); #endif static inline void *memset_l(unsigned long *p, unsigned long v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, v, n); else return memset64((uint64_t *)p, v, n); } static inline void *memset_p(void **p, void *v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, (uintptr_t)v, n); else return memset64((uint64_t *)p, (uintptr_t)v, n); } extern void **__memcat_p(void **a, void **b); #define memcat_p(a, b) ({ \ BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ "type mismatch in memcat_p()"); \ (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ }) #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMMOVE extern void * memmove(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSCAN extern void * memscan(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_BCMP extern int bcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); } #endif void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *str, char old, char new); extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_size(2); #define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); /* lib/cmdline.c */ extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); extern unsigned long long memparse(const char *ptr, char **retptr); extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern bool sysfs_streq(const char *s1, const char *s2); int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); /** * sysfs_match_string - matches given string in an array * @_a: array of strings * @_s: string to match with * * Helper for __sysfs_match_string(). Calculates the size of @a automatically. */ #define sysfs_match_string(_a, _s) __sysfs_match_string(_a, ARRAY_SIZE(_a), _s) #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); int ptr_to_hashval(const void *ptr, unsigned long *hashval_out); /** * strstarts - does @str start with @prefix? * @str: string to examine * @prefix: prefix to look for. */ static inline bool strstarts(const char *str, const char *prefix) { return strncmp(str, prefix, strlen(prefix)) == 0; } size_t memweight(const void *ptr, size_t bytes); /** * memzero_explicit - Fill a region of memory (e.g. sensitive * keying data) with 0s. * @s: Pointer to the start of the area. * @count: The size of the area. * * Note: usually using memset() is just fine (!), but in cases * where clearing out _local_ data at the end of a scope is * necessary, memzero_explicit() should be used instead in * order to prevent the compiler from optimising away zeroing. * * memzero_explicit() doesn't need an arch-specific version as * it just invokes the one of memset() implicitly. */ static inline void memzero_explicit(void *s, size_t count) { memset(s, 0, count); barrier_data(s); } /** * kbasename - return the last part of a pathname. * * @path: path to extract the filename from. */ static inline const char *kbasename(const char *path) { const char *tail = strrchr(path, '/'); return tail ? tail + 1 : path; } #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #include <linux/fortify-string.h> #endif #ifndef unsafe_memcpy #define unsafe_memcpy(dst, src, bytes, justification) \ memcpy(dst, src, bytes) #endif void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad); /** * strtomem_pad - Copy NUL-terminated string to non-NUL-terminated buffer * * @dest: Pointer of destination character array (marked as __nonstring) * @src: Pointer to NUL-terminated string * @pad: Padding character to fill any remaining bytes of @dest after copy * * This is a replacement for strncpy() uses where the destination is not * a NUL-terminated string, but with bounds checking on the source size, and * an explicit padding character. If padding is not required, use strtomem(). * * Note that the size of @dest is not an argument, as the length of @dest * must be discoverable by the compiler. */ #define strtomem_pad(dest, src, pad) do { \ const size_t _dest_len = __builtin_object_size(dest, 1); \ const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ _dest_len == (size_t)-1); \ memcpy_and_pad(dest, _dest_len, src, \ strnlen(src, min(_src_len, _dest_len)), pad); \ } while (0) /** * strtomem - Copy NUL-terminated string to non-NUL-terminated buffer * * @dest: Pointer of destination character array (marked as __nonstring) * @src: Pointer to NUL-terminated string * * This is a replacement for strncpy() uses where the destination is not * a NUL-terminated string, but with bounds checking on the source size, and * without trailing padding. If padding is required, use strtomem_pad(). * * Note that the size of @dest is not an argument, as the length of @dest * must be discoverable by the compiler. */ #define strtomem(dest, src) do { \ const size_t _dest_len = __builtin_object_size(dest, 1); \ const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ _dest_len == (size_t)-1); \ memcpy(dest, src, strnlen(src, min(_src_len, _dest_len))); \ } while (0) /** * memtostr - Copy a possibly non-NUL-term string to a NUL-term string * @dest: Pointer to destination NUL-terminates string * @src: Pointer to character array (likely marked as __nonstring) * * This is a replacement for strncpy() uses where the source is not * a NUL-terminated string. * * Note that sizes of @dest and @src must be known at compile-time. */ #define memtostr(dest, src) do { \ const size_t _dest_len = __builtin_object_size(dest, 1); \ const size_t _src_len = __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ !__builtin_constant_p(_src_len) || \ _dest_len == 0 || _dest_len == (size_t)-1 || \ _src_len == 0 || _src_len == (size_t)-1); \ memcpy(dest, src, _copy_len); \ dest[_copy_len] = '\0'; \ } while (0) /** * memtostr_pad - Copy a possibly non-NUL-term string to a NUL-term string * with NUL padding in the destination * @dest: Pointer to destination NUL-terminates string * @src: Pointer to character array (likely marked as __nonstring) * * This is a replacement for strncpy() uses where the source is not * a NUL-terminated string. * * Note that sizes of @dest and @src must be known at compile-time. */ #define memtostr_pad(dest, src) do { \ const size_t _dest_len = __builtin_object_size(dest, 1); \ const size_t _src_len = __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ !__builtin_constant_p(_src_len) || \ _dest_len == 0 || _dest_len == (size_t)-1 || \ _src_len == 0 || _src_len == (size_t)-1); \ memcpy(dest, src, _copy_len); \ memset(&dest[_copy_len], 0, _dest_len - _copy_len); \ } while (0) /** * memset_after - Set a value after a struct member to the end of a struct * * @obj: Address of target struct instance * @v: Byte value to repeatedly write * @member: after which struct member to start writing bytes * * This is good for clearing padding following the given member. */ #define memset_after(obj, v, member) \ ({ \ u8 *__ptr = (u8 *)(obj); \ typeof(v) __val = (v); \ memset(__ptr + offsetofend(typeof(*(obj)), member), __val, \ sizeof(*(obj)) - offsetofend(typeof(*(obj)), member)); \ }) /** * memset_startat - Set a value starting at a member to the end of a struct * * @obj: Address of target struct instance * @v: Byte value to repeatedly write * @member: struct member to start writing at * * Note that if there is padding between the prior member and the target * member, memset_after() should be used to clear the prior padding. */ #define memset_startat(obj, v, member) \ ({ \ u8 *__ptr = (u8 *)(obj); \ typeof(v) __val = (v); \ memset(__ptr + offsetof(typeof(*(obj)), member), __val, \ sizeof(*(obj)) - offsetof(typeof(*(obj)), member)); \ }) /** * str_has_prefix - Test if a string has a given prefix * @str: The string to test * @prefix: The string to see if @str starts with * * A common way to test a prefix of a string is to do: * strncmp(str, prefix, sizeof(prefix) - 1) * * But this can lead to bugs due to typos, or if prefix is a pointer * and not a constant. Instead use str_has_prefix(). * * Returns: * * strlen(@prefix) if @str starts with @prefix * * 0 if @str does not start with @prefix */ static __always_inline size_t str_has_prefix(const char *str, const char *prefix) { size_t len = strlen(prefix); return strncmp(str, prefix, len) == 0 ? len : 0; } #endif /* _LINUX_STRING_H_ */ |
| 74 2 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/mmap.c * * Copyright (C) 2012 ARM Ltd. */ #include <linux/io.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/types.h> #include <asm/cpufeature.h> #include <asm/page.h> static pgprot_t protection_map[16] __ro_after_init = { [VM_NONE] = PAGE_NONE, [VM_READ] = PAGE_READONLY, [VM_WRITE] = PAGE_READONLY, [VM_WRITE | VM_READ] = PAGE_READONLY, /* PAGE_EXECONLY if Enhanced PAN */ [VM_EXEC] = PAGE_READONLY_EXEC, [VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, [VM_EXEC | VM_WRITE] = PAGE_READONLY_EXEC, [VM_EXEC | VM_WRITE | VM_READ] = PAGE_READONLY_EXEC, [VM_SHARED] = PAGE_NONE, [VM_SHARED | VM_READ] = PAGE_READONLY, [VM_SHARED | VM_WRITE] = PAGE_SHARED, [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, /* PAGE_EXECONLY if Enhanced PAN */ [VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC, [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC }; /* * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. */ int valid_phys_addr_range(phys_addr_t addr, size_t size) { /* * Check whether addr is covered by a memory region without the * MEMBLOCK_NOMAP attribute, and whether that region covers the * entire range. In theory, this could lead to false negatives * if the range is covered by distinct but adjacent memory regions * that only differ in other attributes. However, few of such * attributes have been defined, and it is debatable whether it * follows that /dev/mem read() calls should be able traverse * such boundaries. */ return memblock_is_region_memory(addr, size) && memblock_is_map_memory(addr); } /* * Do not allow /dev/mem mappings beyond the supported physical range. */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK); } static int __init adjust_protection_map(void) { /* * With Enhanced PAN we can honour the execute-only permissions as * there is no PAN override with such mappings. */ if (cpus_have_cap(ARM64_HAS_EPAN)) { protection_map[VM_EXEC] = PAGE_EXECONLY; protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; } if (lpa2_is_enabled()) for (int i = 0; i < ARRAY_SIZE(protection_map); i++) pgprot_val(protection_map[i]) &= ~PTE_SHARED; return 0; } arch_initcall(adjust_protection_map); pgprot_t vm_get_page_prot(unsigned long vm_flags) { pteval_t prot = pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); if (vm_flags & VM_ARM64_BTI) prot |= PTE_GP; /* * There are two conditions required for returning a Normal Tagged * memory type: (1) the user requested it via PROT_MTE passed to * mmap() or mprotect() and (2) the corresponding vma supports MTE. We * register (1) as VM_MTE in the vma->vm_flags and (2) as * VM_MTE_ALLOWED. Note that the latter can only be set during the * mmap() call since mprotect() does not accept MAP_* flags. * Checking for VM_MTE only is sufficient since arch_validate_flags() * does not permit (VM_MTE & !VM_MTE_ALLOWED). */ if (vm_flags & VM_MTE) prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED); return __pgprot(prot); } EXPORT_SYMBOL(vm_get_page_prot); |
| 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/coproc.h * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Authors: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__ #define __ARM64_KVM_SYS_REGS_LOCAL_H__ #include <linux/bsearch.h> #define reg_to_encoding(x) \ sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) struct sys_reg_params { u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; u64 regval; bool is_write; }; #define encoding_to_params(reg) \ ((struct sys_reg_params){ .Op0 = sys_reg_Op0(reg), \ .Op1 = sys_reg_Op1(reg), \ .CRn = sys_reg_CRn(reg), \ .CRm = sys_reg_CRm(reg), \ .Op2 = sys_reg_Op2(reg) }) #define esr_sys64_to_params(esr) \ ((struct sys_reg_params){ .Op0 = ((esr) >> 20) & 3, \ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) #define esr_cp1x_32_to_params(esr) \ ((struct sys_reg_params){ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) struct sys_reg_desc { /* Sysreg string for debug */ const char *name; enum { AA32_DIRECT, AA32_LO, AA32_HI, } aarch32_map; /* MRS/MSR instruction which accesses it. */ u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, struct sys_reg_params *, const struct sys_reg_desc *); /* * Initialization for vcpu. Return initialized value, or KVM * sanitized value for ID registers. */ u64 (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *); /* Index into sys_reg[], or 0 if we don't need to save it. */ int reg; /* Value (usually reset value), or write mask for idregs */ u64 val; /* Custom get/set_user functions, fallback to generic if NULL */ int (*get_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val); int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val); /* Return mask of REG_* runtime visibility overrides */ unsigned int (*visibility)(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd); }; #define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ #define REG_HIDDEN_USER (1 << 1) /* hidden from userspace only */ #define REG_RAZ (1 << 2) /* RAZ from userspace and guest */ #define REG_USER_WI (1 << 3) /* WI from userspace only */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, char *fmt, ...) { va_list va; va_start(va, fmt); /* Look, we even formatted it for you to paste into the table! */ kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", &(struct va_format){ fmt, &va }, p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); va_end(va); } static inline void print_sys_reg_instr(const struct sys_reg_params *p) { /* GCC warns on an empty format string */ print_sys_reg_msg(p, "%s", ""); } static inline bool ignore_write(struct kvm_vcpu *vcpu, const struct sys_reg_params *p) { return true; } static inline bool read_zero(struct kvm_vcpu *vcpu, struct sys_reg_params *p) { p->regval = 0; return true; } /* Reset functions */ static inline u64 reset_unknown(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL; return __vcpu_sys_reg(vcpu, r->reg); } static inline u64 reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_sys_reg(vcpu, r->reg) = r->val; return __vcpu_sys_reg(vcpu, r->reg); } static inline unsigned int sysreg_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return 0; return r->visibility(vcpu, r); } static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_HIDDEN; } static inline bool sysreg_hidden_user(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; return r->visibility(vcpu, r) & (REG_HIDDEN | REG_HIDDEN_USER); } static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_RAZ; } static inline bool sysreg_user_write_ignore(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_USER_WI; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, const struct sys_reg_desc *i2) { BUG_ON(i1 == i2); if (!i1) return 1; else if (!i2) return -1; if (i1->Op0 != i2->Op0) return i1->Op0 - i2->Op0; if (i1->Op1 != i2->Op1) return i1->Op1 - i2->Op1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; return i1->Op2 - i2->Op2; } static inline int match_sys_reg(const void *key, const void *elt) { const unsigned long pval = (unsigned long)key; const struct sys_reg_desc *r = elt; return pval - reg_to_encoding(r); } static inline const struct sys_reg_desc * find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[], unsigned int num) { unsigned long pval = reg_to_encoding(params); return __inline_bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg); } const struct sys_reg_desc *get_reg_by_id(u64 id, const struct sys_reg_desc table[], unsigned int num); int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index); #define AA32(_x) .aarch32_map = AA32_##_x #define Op0(_x) .Op0 = _x #define Op1(_x) .Op1 = _x #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x #define Op2(_x) .Op2 = _x #define SYS_DESC(reg) \ .name = #reg, \ Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */ |
| 81 81 81 81 81 81 81 81 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/insn.h> #include <asm/kprobes.h> #include <asm/patching.h> #include <asm/sections.h> static DEFINE_RAW_SPINLOCK(patch_lock); static bool is_exit_text(unsigned long addr) { /* discarded with init text/data */ return system_state < SYSTEM_RUNNING && addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end; } static bool is_image_text(unsigned long addr) { return core_kernel_text(addr) || is_exit_text(addr); } static void __kprobes *patch_map(void *addr, int fixmap) { unsigned long uintaddr = (uintptr_t) addr; bool image = is_image_text(uintaddr); struct page *page; if (image) page = phys_to_page(__pa_symbol(addr)); else if (IS_ENABLED(CONFIG_EXECMEM)) page = vmalloc_to_page(addr); else return addr; BUG_ON(!page); return (void *)set_fixmap_offset(fixmap, page_to_phys(page) + (uintaddr & ~PAGE_MASK)); } static void __kprobes patch_unmap(int fixmap) { clear_fixmap(fixmap); } /* * In ARMv8-A, A64 instructions have a fixed length of 32 bits and are always * little-endian. */ int __kprobes aarch64_insn_read(void *addr, u32 *insnp) { int ret; __le32 val; ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE); if (!ret) *insnp = le32_to_cpu(val); return ret; } static int __kprobes __aarch64_insn_write(void *addr, __le32 insn) { void *waddr = addr; unsigned long flags = 0; int ret; raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); raw_spin_unlock_irqrestore(&patch_lock, flags); return ret; } int __kprobes aarch64_insn_write(void *addr, u32 insn) { return __aarch64_insn_write(addr, cpu_to_le32(insn)); } noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val) { u64 *waddr; unsigned long flags; int ret; raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); ret = copy_to_kernel_nofault(waddr, &val, sizeof(val)); patch_unmap(FIX_TEXT_POKE0); raw_spin_unlock_irqrestore(&patch_lock, flags); return ret; } typedef void text_poke_f(void *dst, void *src, size_t patched, size_t len); static void *__text_poke(text_poke_f func, void *addr, void *src, size_t len) { unsigned long flags; size_t patched = 0; size_t size; void *waddr; void *ptr; raw_spin_lock_irqsave(&patch_lock, flags); while (patched < len) { ptr = addr + patched; size = min_t(size_t, PAGE_SIZE - offset_in_page(ptr), len - patched); waddr = patch_map(ptr, FIX_TEXT_POKE0); func(waddr, src, patched, size); patch_unmap(FIX_TEXT_POKE0); patched += size; } raw_spin_unlock_irqrestore(&patch_lock, flags); flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len); return addr; } static void text_poke_memcpy(void *dst, void *src, size_t patched, size_t len) { copy_to_kernel_nofault(dst, src + patched, len); } static void text_poke_memset(void *dst, void *src, size_t patched, size_t len) { u32 c = *(u32 *)src; memset32(dst, c, len / 4); } /** * aarch64_insn_copy - Copy instructions into (an unused part of) RX memory * @dst: address to modify * @src: source of the copy * @len: length to copy * * Useful for JITs to dump new code blocks into unused regions of RX memory. */ noinstr void *aarch64_insn_copy(void *dst, void *src, size_t len) { /* A64 instructions must be word aligned */ if ((uintptr_t)dst & 0x3) return NULL; return __text_poke(text_poke_memcpy, dst, src, len); } /** * aarch64_insn_set - memset for RX memory regions. * @dst: address to modify * @insn: value to set * @len: length of memory region. * * Useful for JITs to fill regions of RX memory with illegal instructions. */ noinstr void *aarch64_insn_set(void *dst, u32 insn, size_t len) { if ((uintptr_t)dst & 0x3) return NULL; return __text_poke(text_poke_memset, dst, &insn, len); } int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) { u32 *tp = addr; int ret; /* A64 instructions must be word aligned */ if ((uintptr_t)tp & 0x3) return -EINVAL; ret = aarch64_insn_write(tp, insn); if (ret == 0) caches_clean_inval_pou((uintptr_t)tp, (uintptr_t)tp + AARCH64_INSN_SIZE); return ret; } struct aarch64_insn_patch { void **text_addrs; u32 *new_insns; int insn_cnt; atomic_t cpu_count; }; static int __kprobes aarch64_insn_patch_text_cb(void *arg) { int i, ret = 0; struct aarch64_insn_patch *pp = arg; /* The last CPU becomes master */ if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); /* Notify other processors with an additional increment. */ atomic_inc(&pp->cpu_count); } else { while (atomic_read(&pp->cpu_count) <= num_online_cpus()) cpu_relax(); isb(); } return ret; } int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt) { struct aarch64_insn_patch patch = { .text_addrs = addrs, .new_insns = insns, .insn_cnt = cnt, .cpu_count = ATOMIC_INIT(0), }; if (cnt <= 0) return -EINVAL; return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch, cpu_online_mask); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 6 6 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ARM64_KVM_NESTED_H #define __ARM64_KVM_NESTED_H #include <linux/bitfield.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_pgtable.h> static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu) { return (!__is_defined(__KVM_NVHE_HYPERVISOR__) && cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2)); } /* Translation helpers from non-VHE EL2 to EL1 */ static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2) { return (u64)FIELD_GET(TCR_EL2_PS_MASK, tcr_el2) << TCR_IPS_SHIFT; } static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) { return TCR_EPD1_MASK | /* disable TTBR1_EL1 */ ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) | tcr_el2_ps_to_tcr_el1_ips(tcr) | (tcr & TCR_EL2_TG0_MASK) | (tcr & TCR_EL2_ORGN0_MASK) | (tcr & TCR_EL2_IRGN0_MASK) | (tcr & TCR_EL2_T0SZ_MASK); } static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2) { u64 cpacr_el1 = CPACR_ELx_RES1; if (cptr_el2 & CPTR_EL2_TTA) cpacr_el1 |= CPACR_ELx_TTA; if (!(cptr_el2 & CPTR_EL2_TFP)) cpacr_el1 |= CPACR_ELx_FPEN; if (!(cptr_el2 & CPTR_EL2_TZ)) cpacr_el1 |= CPACR_ELx_ZEN; cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM); return cpacr_el1; } static inline u64 translate_sctlr_el2_to_sctlr_el1(u64 val) { /* Only preserve the minimal set of bits we support */ val &= (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB | SCTLR_ELx_WXN | SCTLR_ELx_EE); val |= SCTLR_EL1_RES1; return val; } static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0) { /* Clear the ASID field */ return ttbr0 & ~GENMASK_ULL(63, 48); } extern bool forward_smc_trap(struct kvm_vcpu *vcpu); extern void kvm_init_nested(struct kvm *kvm); extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu); extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu); extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu); union tlbi_info; extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid, const union tlbi_info *info, void (*)(struct kvm_s2_mmu *, const union tlbi_info *)); extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu); extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu); struct kvm_s2_trans { phys_addr_t output; unsigned long block_size; bool writable; bool readable; int level; u32 esr; u64 upper_attr; }; static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans) { return trans->output; } static inline unsigned long kvm_s2_trans_size(struct kvm_s2_trans *trans) { return trans->block_size; } static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans) { return trans->esr; } static inline bool kvm_s2_trans_readable(struct kvm_s2_trans *trans) { return trans->readable; } static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans) { return trans->writable; } static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans) { return !(trans->upper_attr & BIT(54)); } extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa, struct kvm_s2_trans *result); extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans); extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2); extern void kvm_nested_s2_wp(struct kvm *kvm); extern void kvm_nested_s2_unmap(struct kvm *kvm); extern void kvm_nested_s2_flush(struct kvm *kvm); unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val); static inline bool kvm_supported_tlbi_s1e1_op(struct kvm_vcpu *vpcu, u32 instr) { struct kvm *kvm = vpcu->kvm; u8 CRm = sys_reg_CRm(instr); if (!(sys_reg_Op0(instr) == TLBI_Op0 && sys_reg_Op1(instr) == TLBI_Op1_EL1)) return false; if (!(sys_reg_CRn(instr) == TLBI_CRn_XS || (sys_reg_CRn(instr) == TLBI_CRn_nXS && kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)))) return false; if (CRm == TLBI_CRm_nROS && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) return false; if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS || CRm == TLBI_CRm_RNS) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) return false; return true; } static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr) { struct kvm *kvm = vpcu->kvm; u8 CRm = sys_reg_CRm(instr); if (!(sys_reg_Op0(instr) == TLBI_Op0 && sys_reg_Op1(instr) == TLBI_Op1_EL2)) return false; if (!(sys_reg_CRn(instr) == TLBI_CRn_XS || (sys_reg_CRn(instr) == TLBI_CRn_nXS && kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)))) return false; if (CRm == TLBI_CRm_IPAIS || CRm == TLBI_CRm_IPAONS) return false; if (CRm == TLBI_CRm_nROS && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) return false; if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS || CRm == TLBI_CRm_RNS) && !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) return false; return true; } int kvm_init_nv_sysregs(struct kvm *kvm); #ifdef CONFIG_ARM64_PTR_AUTH bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr); #else static inline bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr) { /* We really should never execute this... */ WARN_ON_ONCE(1); *elr = 0xbad9acc0debadbad; return false; } #endif #define KVM_NV_GUEST_MAP_SZ (KVM_PGTABLE_PROT_SW1 | KVM_PGTABLE_PROT_SW0) static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans) { return FIELD_PREP(KVM_NV_GUEST_MAP_SZ, trans->level); } #endif /* __ARM64_KVM_NESTED_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H #include <linux/bpf.h> #include <linux/bpf-cgroup-defs.h> #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/percpu.h> #include <linux/rbtree.h> #include <net/sock.h> #include <uapi/linux/bpf.h> struct sock; struct sockaddr; struct cgroup; struct sk_buff; struct bpf_map; struct bpf_prog; struct bpf_sock_ops_kern; struct bpf_cgroup_storage; struct ctl_table; struct ctl_table_header; struct task_struct; unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, const struct bpf_insn *insn); unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, const struct bpf_insn *insn); unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, const struct bpf_insn *insn); #ifdef CONFIG_CGROUP_BPF #define CGROUP_ATYPE(type) \ case BPF_##type: return type static inline enum cgroup_bpf_attach_type to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) { switch (attach_type) { CGROUP_ATYPE(CGROUP_INET_INGRESS); CGROUP_ATYPE(CGROUP_INET_EGRESS); CGROUP_ATYPE(CGROUP_INET_SOCK_CREATE); CGROUP_ATYPE(CGROUP_SOCK_OPS); CGROUP_ATYPE(CGROUP_DEVICE); CGROUP_ATYPE(CGROUP_INET4_BIND); CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; } } #undef CGROUP_ATYPE extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE]; #define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype]) #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) struct bpf_cgroup_storage_map; struct bpf_storage_buffer { struct rcu_head rcu; char data[]; }; struct bpf_cgroup_storage { union { struct bpf_storage_buffer *buf; void __percpu *percpu_buf; }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; struct list_head list_map; struct list_head list_cg; struct rb_node node; struct rcu_head rcu; }; struct bpf_cgroup_link { struct bpf_link link; struct cgroup *cgroup; enum bpf_attach_type type; }; struct bpf_prog_list { struct hlist_node node; struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, int *optname, sockptr_t optval, int *optlen, char **kernel_optval); int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen, int max_optlen, int retval); int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, int optname, void *optval, int *optlen, int retval); static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return BPF_CGROUP_STORAGE_PERCPU; return BPF_CGROUP_STORAGE_SHARED; } struct bpf_cgroup_storage * cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, void *key, bool locked); struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags); /* Opportunistic check to see whether we have any BPF program attached*/ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, enum cgroup_bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_prog_array *array; array = rcu_access_pointer(cgrp->bpf.effective[type]); return array != &bpf_empty_prog_array.hdr; } /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS) && sk && \ sk_fullsock(sk)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) && \ cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_SK_PROG(sk, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ __ret = __cgroup_bpf_run_filter_sk(sk, atype); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_CREATE) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET_SOCK_RELEASE) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET4_POST_BIND) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ atype, NULL, NULL); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ }) /* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags * via upper bits of return code. The only flag that is supported * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ #define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ } \ __ret; \ }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ ((cgroup_bpf_enabled(CGROUP_INET4_CONNECT) || \ cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by * sk_to_full_sk(). * * e.g. sock_ops->sk is a request_sock and it is under syncookie mode. * Its listener-sk is not attached to the rsk_listener. * In this case, the caller holds the listener-sk (unlocked), * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with * the listener-sk such that the cgroup-bpf-progs of the * listener-sk will be run. * * Regardless of syncookie mode or not, * calling bpf_setsockopt on listener-sk will not make sense anyway, * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here. */ #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ CGROUP_SOCK_OPS); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ sock_ops, \ CGROUP_SOCK_OPS); \ } \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_DEVICE)) \ __ret = __cgroup_bpf_check_dev_permission(atype, major, minor, \ access, \ CGROUP_DEVICE); \ \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ CGROUP_SYSCTL); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT) && \ cgroup_bpf_sock_enabled(sock, CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ kernel_optval); \ __ret; \ }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ copy_from_sockptr(&__ret, optlen, sizeof(int)); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ max_optlen, retval) \ ({ \ int __ret = retval; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \ cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ level, optname)) \ __ret = __cgroup_bpf_run_filter_getsockopt( \ sock, level, optname, optval, optlen, \ max_optlen, retval); \ __ret; \ }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ optlen, retval) \ ({ \ int __ret = retval; \ if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ }) int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); const struct bpf_func_proto * cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); #else static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { return -EINVAL; } static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EINVAL; } static inline int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline const struct bpf_func_proto * cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value) { return 0; } static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags) { return 0; } #define cgroup_bpf_enabled(atype) (0) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) #endif /* CONFIG_CGROUP_BPF */ #endif /* _BPF_CGROUP_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_STATE_H #define _LINUX_CONTEXT_TRACKING_STATE_H #include <linux/percpu.h> #include <linux/static_key.h> #include <linux/context_tracking_irq.h> /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ #define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ CONTEXT_KERNEL = 0, CONTEXT_IDLE = 1, CONTEXT_USER = 2, CONTEXT_GUEST = 3, CONTEXT_MAX = 4, }; /* Even value for idle, else odd. */ #define RCU_DYNTICKS_IDX CONTEXT_MAX #define CT_STATE_MASK (CONTEXT_MAX - 1) #define CT_DYNTICKS_MASK (~CT_STATE_MASK) struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING_USER /* * When active is false, probes are unset in order * to minimize overhead: TIF flags are cleared * and calls to user_enter/exit are ignored. This * may be further optimized using static keys. */ bool active; int recursion; #endif #ifdef CONFIG_CONTEXT_TRACKING atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE long dynticks_nesting; /* Track process nesting level. */ long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); #endif #ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; } #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE static __always_inline int ct_dynticks(void) { return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK; } static __always_inline int ct_dynticks_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read(&ct->state) & CT_DYNTICKS_MASK; } static __always_inline int ct_dynticks_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK; } static __always_inline long ct_dynticks_nesting(void) { return __this_cpu_read(context_tracking.dynticks_nesting); } static __always_inline long ct_dynticks_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->dynticks_nesting; } static __always_inline long ct_dynticks_nmi_nesting(void) { return __this_cpu_read(context_tracking.dynticks_nmi_nesting); } static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->dynticks_nmi_nesting; } #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ #ifdef CONFIG_CONTEXT_TRACKING_USER extern struct static_key_false context_tracking_key; static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } static inline bool context_tracking_enabled_this_cpu(void) { return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } /** * ct_state() - return the current context tracking state if known * * Returns the current cpu's context tracking state if context tracking * is enabled. If context tracking is disabled, returns * CONTEXT_DISABLED. This should be used primarily for debugging. */ static __always_inline int ct_state(void) { int ret; if (!context_tracking_enabled()) return CONTEXT_DISABLED; preempt_disable(); ret = __ct_state(); preempt_enable(); return ret; } #else static __always_inline bool context_tracking_enabled(void) { return false; } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING_USER */ #endif |
| 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/sysreg-sr.h> #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_nested.h> /* * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and * pstate, which are handled as part of the el2 return state) on every * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. */ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); /** * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU * * @vcpu: The VCPU pointer * * Load system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_load() function * and loading system register state early avoids having to load them on * every entry to the VM. */ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); /* * When running a normal EL1 guest, we only load a new vcpu * after a context switch, which imvolves a DSB, so all * speculative EL1&0 walks will have already completed. * If running NV, the vcpu may transition between vEL1 and * vEL2 without a context switch, so make sure we complete * those walks before loading a new context. */ if (vcpu_has_nv(vcpu)) dsb(nsh); /* * Load guest EL1 and user state * * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); __sysreg_restore_el1_state(guest_ctxt); vcpu_set_flag(vcpu, SYSREGS_ON_CPU); } /** * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU * * @vcpu: The VCPU pointer * * Save guest system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_put() function * and deferring saving system register state until we're no longer running the * VCPU avoids having to save them on every exit from the VM. */ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); __sysreg32_save_state(vcpu); /* Restore host user state */ __sysreg_restore_user_state(host_ctxt); vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } |
| 2 2 2 4 4 4 4 4 4 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ static int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ static unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ static int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ static int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ static unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100 * BDI_RATIO_SCALE) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; if (bg_thresh >= thresh) bg_thresh = thresh / 2; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; return dirty; } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } #ifdef CONFIG_SYSCTL static int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } static int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } static int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; } static int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } #endif static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac, long nr) { __fprop_add_percpu_max(&dom->completions, completions, max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; wb_stat_mod(wb, WB_WRITTEN, nr); wb_domain_writeout_add(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; static int bdi_check_pages_limit(unsigned long pages) { unsigned long max_dirty_pages = global_dirtyable_memory(); if (pages > max_dirty_pages) return -EINVAL; return 0; } static unsigned long bdi_ratio_from_pages(unsigned long pages) { unsigned long background_thresh; unsigned long dirty_thresh; unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; } static u64 bdi_get_bytes(unsigned int ratio) { unsigned long background_thresh; unsigned long dirty_thresh; u64 bytes; global_dirty_limits(&background_thresh, &dirty_thresh); bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100; return bytes; } static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { unsigned int delta; int ret = 0; if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { if (min_ratio < bdi->min_ratio) { delta = bdi->min_ratio - min_ratio; bdi_min_ratio -= delta; bdi->min_ratio = min_ratio; } else { delta = min_ratio - bdi->min_ratio; if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) { bdi_min_ratio += delta; bdi->min_ratio = min_ratio; } else { ret = -EINVAL; } } } spin_unlock_bh(&bdi_lock); return ret; } static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { int ret = 0; if (max_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio); } int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE); } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE); } EXPORT_SYMBOL(bdi_set_max_ratio); u64 bdi_get_min_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->min_ratio); } int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; unsigned long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); return __bdi_set_min_ratio(bdi, min_ratio); } u64 bdi_get_max_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->max_ratio); } int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; unsigned long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit) { if (strict_limit > 1) return -EINVAL; spin_lock_bh(&bdi_lock); if (strict_limit) bdi->capabilities |= BDI_CAP_STRICTLIMIT; else bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; spin_unlock_bh(&bdi_lock); return 0; } static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } /** * __wb_calc_thresh - @wb's share of dirty threshold * @dtc: dirty_throttle_context of interest * @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc * * Note that balance_dirty_pages() will only seriously take dirty throttling * threshold as a hard limit when sleeping max_pause per page is not enough * to keep the dirty pages under control. For example, when the device is * completely stalled due to some error conditions, or when there are 1000 * dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. For dirty throttling limit, the term * "dirty" in the context of dirty balancing includes all PG_dirty and * PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this wb's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE); wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE)) wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; return __wb_calc_thresh(&gdtc, thresh); } unsigned long cgwb_calc_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; unsigned long filepages = 0, headroom = 0, writeback = 0; gdtc.avail = global_dirtyable_memory(); gdtc.dirty = global_node_page_state(NR_FILE_DIRTY) + global_node_page_state(NR_WRITEBACK); mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc.dirty, &writeback); mdtc.dirty += writeback; mdtc_calc_avail(&mdtc, filepages, headroom); domain_dirty_limits(&mdtc); return __wb_calc_thresh(&mdtc, mdtc.thresh); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 * * * * * * * * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to folio_redirty_for_writepage(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; WRITE_ONCE(wb->avg_write_bandwidth, avg); } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_dirty_limit(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL)); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed; unsigned long dirtied; unsigned long written; spin_lock(&wb->list_lock); /* * Lockless checks for elapsed time are racy and delayed update after * IO completion doesn't do it at all (to make sure written pages are * accounted reasonably quickly). Make sure elapsed >= 1 to avoid * division errors. */ elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); if (update_ratelimit) { domain_update_dirty_limit(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_dirty_limit(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); wb->dirtied_stamp = dirtied; wb->written_stamp = written; WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, false); } /* Interval after which we consider wb idle and don't estimate bandwidth */ #define WB_BANDWIDTH_IDLE_JIF (HZ) static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) { unsigned long now = jiffies; unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); if (elapsed > WB_BANDWIDTH_IDLE_JIF && !atomic_read(&wb->writeback_inodes)) { spin_lock(&wb->list_lock); wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); wb->written_stamp = wb_stat(wb, WB_WRITTEN); WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth)); long lo = ilog2(READ_ONCE(wb->dirty_ratelimit)); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh); dtc->wb_bg_thresh = dtc->thresh ? div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied, unsigned int flags) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_dirty; long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; int ret = 0; for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; unsigned long m_dirty = 0; /* stop bogus uninit warnings */ unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; nr_dirty = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_dirty + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { wb_dirty_limits(gdtc); dirty = gdtc->wb_dirty; thresh = gdtc->wb_thresh; bg_thresh = gdtc->wb_bg_thresh; } else { dirty = gdtc->dirty; thresh = gdtc->thresh; bg_thresh = gdtc->bg_thresh; } if (mdtc) { unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc->dirty += writeback; mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); if (unlikely(strictlimit)) { wb_dirty_limits(mdtc); m_dirty = mdtc->wb_dirty; m_thresh = mdtc->wb_thresh; m_bg_thresh = mdtc->wb_bg_thresh; } else { m_dirty = mdtc->dirty; m_thresh = mdtc->thresh; m_bg_thresh = mdtc->bg_thresh; } } /* * In laptop mode, we wait until hitting the higher threshold * before starting background writeout, and then write out all * the way down to the lower threshold. So slow writers cause * minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (!laptop_mode && nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the wb limits are ramping up in case of !strictlimit. * * In strictlimit case make decision based on the wb counters * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. * * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } if (dirty_exceeded != wb->dirty_exceeded) wb->dirty_exceeded = dirty_exceeded; if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); /* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } return ret; } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited_flags - Balance dirty memory state. * @mapping: address_space which was dirtied. * @flags: BDP flags. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * See balance_dirty_pages_ratelimited() for details. * * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to * indicate that memory is out of balance and the caller must wait * for I/O to complete. Otherwise, it will return 0 to indicate * that either memory was already in balance, or it was able to sleep * until the amount of dirty memory returned to balance. */ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int ret = 0; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return ret; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb); return ret; } EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags); /** * balance_dirty_pages_ratelimited - balance dirty memory state. * @mapping: address_space which was dirtied. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * Once we're over the dirty memory limit we decrease the ratelimiting * by a lot, to prevent individual processes from overshooting the limit * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { balance_dirty_pages_ratelimited_flags(mapping, 0); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; unsigned long reclaimable; unsigned long thresh; /* * Similar to balance_dirty_pages() but ignores pages being written * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; thresh = __wb_calc_thresh(gdtc, gdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else reclaimable = wb_stat(wb, WB_RECLAIMABLE); if (reclaimable > thresh) return true; if (mdtc) { unsigned long filepages, headroom, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) return true; thresh = __wb_calc_thresh(mdtc, mdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else reclaimable = wb_stat(wb, WB_RECLAIMABLE); if (reclaimable > thresh) return true; } return false; } #ifdef CONFIG_SYSCTL /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ static int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #endif void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } #ifdef CONFIG_SYSCTL /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_HIGHMEM { .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; #endif /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_page_writeback_sysctls); #endif } /** * tag_pages_for_writeback - tag pages to be written by writeback * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The caller * can then use the TOWRITE tag to identify pages eligible for writeback. * This mechanism is used to avoid livelocking of writeback by a process * steadily creating new dirty pages in the file (thus it is important for this * function to be quick so that it can tag pages faster than a dirtying process * can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); static bool folio_prepare_writeback(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio) { /* * Folio truncated or invalidated. We can freely skip it then, * even for data integrity operations: the folio has disappeared * concurrently, so there could be no real expectation of this * data integrity operation even if there is now a new, dirty * folio at the same pagecache index. */ if (unlikely(folio->mapping != mapping)) return false; /* * Did somebody else write it for us? */ if (!folio_test_dirty(folio)) return false; if (folio_test_writeback(folio)) { if (wbc->sync_mode == WB_SYNC_NONE) return false; folio_wait_writeback(folio); } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) return false; return true; } static xa_mark_t wbc_to_tag(struct writeback_control *wbc) { if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) return PAGECACHE_TAG_TOWRITE; return PAGECACHE_TAG_DIRTY; } static pgoff_t wbc_end(struct writeback_control *wbc) { if (wbc->range_cyclic) return -1; return wbc->range_end >> PAGE_SHIFT; } static struct folio *writeback_get_folio(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio; retry: folio = folio_batch_next(&wbc->fbatch); if (!folio) { folio_batch_release(&wbc->fbatch); cond_resched(); filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc), wbc_to_tag(wbc), &wbc->fbatch); folio = folio_batch_next(&wbc->fbatch); if (!folio) return NULL; } folio_lock(folio); if (unlikely(!folio_prepare_writeback(mapping, wbc, folio))) { folio_unlock(folio); goto retry; } trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); return folio; } /** * writeback_iter - iterate folio of a mapping for writeback * @mapping: address space structure to write * @wbc: writeback context * @folio: previously iterated folio (%NULL to start) * @error: in-out pointer for writeback errors (see below) * * This function returns the next folio for the writeback operation described by * @wbc on @mapping and should be called in a while loop in the ->writepages * implementation. * * To start the writeback operation, %NULL is passed in the @folio argument, and * for every subsequent iteration the folio returned previously should be passed * back in. * * If there was an error in the per-folio writeback inside the writeback_iter() * loop, @error should be set to the error value. * * Once the writeback described in @wbc has finished, this function will return * %NULL and if there was an error in any iteration restore it to @error. * * Note: callers should not manually break out of the loop using break or goto * but must keep calling writeback_iter() until it returns %NULL. * * Return: the folio to write or %NULL if the loop is done. */ struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error) { if (!folio) { folio_batch_init(&wbc->fbatch); wbc->saved_err = *error = 0; /* * For range cyclic writeback we remember where we stopped so * that we can continue where we stopped. * * For non-cyclic writeback we always start at the beginning of * the passed in range. */ if (wbc->range_cyclic) wbc->index = mapping->writeback_index; else wbc->index = wbc->range_start >> PAGE_SHIFT; /* * To avoid livelocks when other processes dirty new pages, we * first tag pages which should be written back and only then * start writing them. * * For data-integrity writeback we have to be careful so that we * do not miss some pages (e.g., because some other process has * cleared the TOWRITE tag we set). The rule we follow is that * TOWRITE tag can be cleared only by the process clearing the * DIRTY tag (and submitting the page for I/O). */ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, wbc->index, wbc_end(wbc)); } else { wbc->nr_to_write -= folio_nr_pages(folio); WARN_ON_ONCE(*error > 0); /* * For integrity writeback we have to keep going until we have * written all the folios we tagged for writeback above, even if * we run past wbc->nr_to_write or encounter errors. * We stash away the first error we encounter in wbc->saved_err * so that it can be retrieved when we're done. This is because * the file system may still have state to clear for each folio. * * For background writeback we exit as soon as we run past * wbc->nr_to_write or encounter the first error. */ if (wbc->sync_mode == WB_SYNC_ALL) { if (*error && !wbc->saved_err) wbc->saved_err = *error; } else { if (*error || wbc->nr_to_write <= 0) goto done; } } folio = writeback_get_folio(mapping, wbc); if (!folio) { /* * To avoid deadlocks between range_cyclic writeback and callers * that hold pages in PageWriteback to aggregate I/O until * the writeback iteration finishes, we do not loop back to the * start of the file. Doing so causes a page lock/page * writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping * back to the start of the file violates that rule and causes * deadlocks. */ if (wbc->range_cyclic) mapping->writeback_index = 0; /* * Return the first error we encountered (if there was any) to * the caller. */ *error = wbc->saved_err; } return folio; done: if (wbc->range_cyclic) mapping->writeback_index = folio->index + folio_nr_pages(folio); folio_batch_release(&wbc->fbatch); return NULL; } EXPORT_SYMBOL_GPL(writeback_iter); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * Return: %0 on success, negative error code otherwise * * Note: please use writeback_iter() instead. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { struct folio *folio = NULL; int error; while ((folio = writeback_iter(mapping, wbc, folio, &error))) { error = writepage(folio, wbc, data); if (error == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); error = 0; } } return error; } EXPORT_SYMBOL(write_cache_pages); static int writeback_use_writepage(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio = NULL; struct blk_plug plug; int err; blk_start_plug(&plug); while ((folio = writeback_iter(mapping, wbc, folio, &err))) { err = mapping->a_ops->writepage(&folio->page, wbc); if (err == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); err = 0; } mapping_set_error(mapping, err); } blk_finish_plug(&plug); return err; } int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) { ret = mapping->a_ops->writepages(mapping, wbc); } else if (mapping->a_ops->writepage) { ret = writeback_use_writepage(mapping, wbc); } else { /* deal with chardevs and other special files */ ret = 0; } if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* * Lacking an allocation context or the locality or writeback * state of any of the inode's pages, throttle based on * writeback activity on the local node. It's as good a * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted * but if there's constant writeback being submitted, this makes sure * writeback bandwidth is updated once in a while. */ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) wb_update_bandwidth(wb); return ret; } /* * For address_spaces which do not use buffers nor write back. */ bool noop_dirty_folio(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio); return false; } EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * * Caller must hold folio_memcg_lock(). * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; long nr = folio_nr_pages(folio); inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); __node_stat_mod_folio(folio, NR_DIRTIED, nr); wb_stat_mod(wb, WB_RECLAIMABLE, nr); wb_stat_mod(wb, WB_DIRTIED, nr); task_io_account_write(nr * PAGE_SIZE); current->nr_dirtied += nr; __this_cpu_add(bdp_ratelimits, nr); mem_cgroup_track_foreign_dirty(folio, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold folio_memcg_lock(). */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); task_io_account_cancelled_write(nr * PAGE_SIZE); } /* * Mark the folio dirty, and set it dirty in the page cache. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * The caller must hold folio_memcg_lock(). It is the caller's * responsibility to prevent the folio from being truncated while * this function is in progress, although it may have been truncated * before this function is called. Most callers have the folio locked. * A few have the folio blocked from truncation through other means (e.g. * zap_vma_pages() has it mapped and is holding the page table lock). * When called from mark_buffer_dirty(), the filesystem should hold a * reference to the buffer_head that is being marked dirty, which causes * try_to_free_buffers() to fail. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (folio->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); folio_account_dirtied(folio, mapping); __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } /** * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. * @mapping: Address space this folio belongs to. * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * * This is also sometimes used by filesystems which use buffer_heads when * a single buffer is being dirtied: we want to set the folio dirty in * that case, but not all the buffers. This is a "bottom-up" dirtying, * whereas block_dirty_folio() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will * simply hold the folio lock, but e.g. zap_pte_range() calls with the * folio mapped and the pte lock held, which also locks out truncation. */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { folio_memcg_lock(folio); if (folio_test_set_dirty(folio)) { folio_memcg_unlock(folio); return false; } __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); folio_memcg_unlock(folio); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return true; } EXPORT_SYMBOL(filemap_dirty_folio); /** * folio_redirty_for_writepage - Decline to write a dirty folio. * @wbc: The writeback control. * @folio: The folio. * * When a writepage implementation decides that it doesn't want to write * @folio for some reason, it should call this function, unlock @folio and * return 0. * * Return: True if we redirtied the folio. False if someone else dirtied * it first. */ bool folio_redirty_for_writepage(struct writeback_control *wbc, struct folio *folio) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); bool ret; wbc->pages_skipped += nr; ret = filemap_dirty_folio(mapping, folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied -= nr; node_stat_mod_folio(folio, NR_DIRTIED, -nr); wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } return ret; } EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * * The folio may not be truncated while this function is running. * Holding the folio lock is sufficient to prevent truncation, but some * callers cannot acquire a sleeping lock. These callers instead hold * the page table lock for a page table which contains at least one page * in this folio. Truncation will block on the page table lock as it * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ bool folio_mark_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (likely(mapping)) { /* * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's * a trivial problem. */ if (folio_test_reclaim(folio)) folio_clear_reclaim(folio); return mapping->a_ops->dirty_folio(mapping, folio); } return noop_dirty_folio(mapping, folio); } EXPORT_SYMBOL(folio_mark_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __folio_cancel_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); folio_memcg_unlock(folio); } else { folio_clear_dirty(folio); } } EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a folio's dirty flag, while caring for dirty memory accounting. * Returns true if the folio was previously dirty. * * This is for preparing to put the folio under writeout. We leave * the folio tagged as dirty in the xarray so that a concurrent * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. * The ->writepage implementation will run either folio_start_writeback() * or folio_mark_dirty(), at which stage we bring the folio's dirty flag * and xarray dirty tag back into sync. * * This incoherency between the folio's dirty flag and xarray tag is * unfortunate, but it only exists while the folio is locked. */ bool folio_clear_dirty_for_io(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); bool ret = false; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole folio dirty if it was * dirty in a pagetable. Only to then * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return folio_test_clear_dirty(folio); } EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { atomic_inc(&wb->writeback_inodes); } static void wb_inode_writeback_end(struct bdi_writeback *wb) { unsigned long flags; atomic_dec(&wb->writeback_inodes); /* * Make sure estimate of writeback throughput gets updated after * writeback completed. We delay the update by BANDWIDTH_INTERVAL * (which is the interval other bandwidth updates use for batching) so * that if multiple inodes end writeback at a similar time, they get * batched into one bandwidth update. */ spin_lock_irqsave(&wb->work_lock, flags); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); spin_unlock_irqrestore(&wb->work_lock, flags); } bool __folio_end_writeback(struct folio *folio) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); bool ret; folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, -nr); __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); folio_memcg_unlock(folio); return ret; } void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); int access_ret; VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); folio_test_set_writeback(folio); on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* * We can come through here when swapping anonymous * folios, so we don't necessarily have an inode to * track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { folio_test_set_writeback(folio); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); folio_memcg_unlock(folio); access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); } EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); /** * folio_wait_writeback_killable - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete or a fatal signal to arrive. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * folio_wait_stable() - wait for writeback to finish, if necessary. * @folio: The folio to wait on. * * This function determines if the given folio is related to a backing * device that requires folio contents to be held stable during writeback. * If so, then it will wait for any pending writeback to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_stable(struct folio *folio) { if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); |
| 3 3 3 3 3 4 5 5 5 4 1 1 2 2 2 2 9 5 5 2 2 1 1 1 1 12 4 3 4 1 3 4 4 3 2 1 1 2 2 2 4 1 10 1 9 3 4 3 1 4 1 4 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC: KVM DEVICE API * * Copyright (C) 2015 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <linux/uaccess.h> #include <asm/kvm_mmu.h> #include <asm/cputype.h> #include "vgic.h" /* common helpers */ int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr, phys_addr_t addr, phys_addr_t alignment, phys_addr_t size) { if (!IS_VGIC_ADDR_UNDEF(ioaddr)) return -EEXIST; if (!IS_ALIGNED(addr, alignment) || !IS_ALIGNED(size, alignment)) return -EINVAL; if (addr + size < addr) return -EINVAL; if (addr & ~kvm_phys_mask(&kvm->arch.mmu) || (addr + size) > kvm_phys_size(&kvm->arch.mmu)) return -E2BIG; return 0; } static int vgic_check_type(struct kvm *kvm, int type_needed) { if (kvm->arch.vgic.vgic_model != type_needed) return -ENODEV; else return 0; } int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { struct vgic_dist *vgic = &kvm->arch.vgic; int r; mutex_lock(&kvm->arch.config_lock); switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_dist_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_DIST_SIZE); if (!r) vgic->vgic_dist_base = dev_addr->addr; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_cpu_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_CPU_SIZE); if (!r) vgic->vgic_cpu_base = dev_addr->addr; break; default: r = -ENODEV; } mutex_unlock(&kvm->arch.config_lock); return r; } /** * kvm_vgic_addr - set or get vgic VM base addresses * @kvm: pointer to the vm struct * @attr: pointer to the attribute being retrieved/updated * @write: if true set the address in the VM address space, if false read the * address * * Set or get the vgic base addresses for the distributor and the virtual CPU * interface in the VM physical address space. These addresses are properties * of the emulated core/SoC and therefore user space initially knows this * information. * Check them for sanity (alignment, double assignment). We can't check for * overlapping regions in case of a virtual GICv3 here, since we don't know * the number of VCPUs yet, so we defer this check to map_resources(). */ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool write) { u64 __user *uaddr = (u64 __user *)attr->addr; struct vgic_dist *vgic = &kvm->arch.vgic; phys_addr_t *addr_ptr, alignment, size; u64 undef_value = VGIC_ADDR_UNDEF; u64 addr; int r; /* Reading a redistributor region addr implies getting the index */ if (write || attr->attr == KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION) if (get_user(addr, uaddr)) return -EFAULT; /* * Since we can't hold config_lock while registering the redistributor * iodevs, take the slots_lock immediately. */ mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_4K; size = KVM_VGIC_V2_DIST_SIZE; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_cpu_base; alignment = SZ_4K; size = KVM_VGIC_V2_CPU_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_64K; size = KVM_VGIC_V3_DIST_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_REDIST: { struct vgic_redist_region *rdreg; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; if (write) { r = vgic_v3_set_redist_base(kvm, 0, addr, 0); goto out; } rdreg = list_first_entry_or_null(&vgic->rd_regions, struct vgic_redist_region, list); if (!rdreg) addr_ptr = &undef_value; else addr_ptr = &rdreg->base; break; } case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: { struct vgic_redist_region *rdreg; u8 index; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; index = addr & KVM_VGIC_V3_RDIST_INDEX_MASK; if (write) { gpa_t base = addr & KVM_VGIC_V3_RDIST_BASE_MASK; u32 count = FIELD_GET(KVM_VGIC_V3_RDIST_COUNT_MASK, addr); u8 flags = FIELD_GET(KVM_VGIC_V3_RDIST_FLAGS_MASK, addr); if (!count || flags) r = -EINVAL; else r = vgic_v3_set_redist_base(kvm, index, base, count); goto out; } rdreg = vgic_v3_rdist_region_from_index(kvm, index); if (!rdreg) { r = -ENOENT; goto out; } addr = index; addr |= rdreg->base; addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; goto out; } default: r = -ENODEV; } if (r) goto out; mutex_lock(&kvm->arch.config_lock); if (write) { r = vgic_check_iorange(kvm, *addr_ptr, addr, alignment, size); if (!r) *addr_ptr = addr; } else { addr = *addr_ptr; } mutex_unlock(&kvm->arch.config_lock); out: mutex_unlock(&kvm->slots_lock); if (!r && !write) r = put_user(addr, uaddr); return r; } static int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, true); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; u32 val; int ret = 0; if (get_user(val, uaddr)) return -EFAULT; /* * We require: * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs * - at most 1024 interrupts * - a multiple of 32 interrupts */ if (val < (VGIC_NR_PRIVATE_IRQS + 32) || val > VGIC_MAX_RESERVED || (val & 31)) return -EINVAL; mutex_lock(&dev->kvm->arch.config_lock); if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) ret = -EBUSY; else dev->kvm->arch.vgic.nr_spis = val - VGIC_NR_PRIVATE_IRQS; mutex_unlock(&dev->kvm->arch.config_lock); return ret; } case KVM_DEV_ARM_VGIC_GRP_CTRL: { switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: mutex_lock(&dev->kvm->arch.config_lock); r = vgic_init(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); return r; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: /* * OK, this one isn't common at all, but we * want to handle all control group attributes * in a single place. */ if (vgic_check_type(dev->kvm, KVM_DEV_TYPE_ARM_VGIC_V3)) return -ENXIO; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); r = vgic_v3_save_pending_tables(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return r; } break; } } return -ENXIO; } static int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = -ENXIO; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, false); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; r = put_user(dev->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS, uaddr); break; } } return r; } static int vgic_create(struct kvm_device *dev, u32 type) { return kvm_vgic_create(dev->kvm, type); } static void vgic_destroy(struct kvm_device *dev) { kfree(dev); } int kvm_register_vgic_device(unsigned long type) { int ret = -ENODEV; switch (type) { case KVM_DEV_TYPE_ARM_VGIC_V2: ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2); break; case KVM_DEV_TYPE_ARM_VGIC_V3: ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops, KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) break; ret = kvm_vgic_register_its_device(); break; } return ret; } int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); if (!reg_attr->vcpu) return -EINVAL; return 0; } /** * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v2_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; int ret; u32 val; ret = vgic_v2_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; if (is_write) if (get_user(val, uaddr)) return -EFAULT; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); ret = vgic_init(dev->kvm); if (ret) goto out; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, &val); break; default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && !is_write) ret = put_user(val, uaddr); return ret; } static int vgic_v2_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v2_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v2_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: case KVM_VGIC_V2_ADDR_TYPE_CPU: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v2_ops = { .name = "kvm-arm-vgic-v2", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v2_set_attr, .get_attr = vgic_v2_get_attr, .has_attr = vgic_v2_has_attr, }; int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { unsigned long vgic_mpidr, mpidr_reg; /* * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group, * attr might not hold MPIDR. Hence assume vcpu0. */ if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) { vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >> KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT; mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr); reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg); } else { reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0); } if (!reg_attr->vcpu) return -EINVAL; reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; return 0; } /* * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v3_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; bool uaccess; u32 val; int ret; ret = vgic_v3_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: /* Sysregs uaccess is performed by the sysreg handling code */ uaccess = false; break; default: uaccess = true; } if (uaccess && is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; if (get_user(val, uaddr)) return -EFAULT; } mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (unlikely(!vgic_initialized(dev->kvm))) { ret = -EBUSY; goto out; } switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: ret = vgic_v3_cpu_sysregs_uaccess(vcpu, attr, is_write); break; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { unsigned int info, intid; info = (attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT; if (info == VGIC_LEVEL_INFO_LINE_LEVEL) { intid = attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK; ret = vgic_v3_line_level_info_uaccess(vcpu, is_write, intid, &val); } else { ret = -EINVAL; } break; } default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && uaccess && !is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; ret = put_user(val, uaddr); } return ret; } static int vgic_v3_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v3_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v3_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V3_ADDR_TYPE_DIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: return vgic_v3_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) == VGIC_LEVEL_INFO_LINE_LEVEL) return 0; break; } case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v3_ops = { .name = "kvm-arm-vgic-v3", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v3_set_attr, .get_attr = vgic_v3_get_attr, .has_attr = vgic_v3_has_attr, }; |
| 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 | // SPDX-License-Identifier: GPL-2.0-only /* * ARMv8 single-step debug support and mdscr context switching. * * Copyright (C) 2012 ARM Limited * * Author: Will Deacon <will.deacon@arm.com> */ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/ptrace.h> #include <linux/kprobes.h> #include <linux/stat.h> #include <linux/uaccess.h> #include <linux/sched/task_stack.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/system_misc.h> #include <asm/traps.h> /* Determine debug architecture. */ u8 debug_monitors_arch(void) { return cpuid_feature_extract_unsigned_field(read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1), ID_AA64DFR0_EL1_DebugVer_SHIFT); } /* * MDSCR access routines. */ static void mdscr_write(u32 mdscr) { unsigned long flags; flags = local_daif_save(); write_sysreg(mdscr, mdscr_el1); local_daif_restore(flags); } NOKPROBE_SYMBOL(mdscr_write); static u32 mdscr_read(void) { return read_sysreg(mdscr_el1); } NOKPROBE_SYMBOL(mdscr_read); /* * Allow root to disable self-hosted debug from userspace. * This is useful if you want to connect an external JTAG debugger. */ static bool debug_enabled = true; static int create_debug_debugfs_entry(void) { debugfs_create_bool("debug_enabled", 0644, NULL, &debug_enabled); return 0; } fs_initcall(create_debug_debugfs_entry); static int __init early_debug_disable(char *buf) { debug_enabled = false; return 0; } early_param("nodebugmon", early_debug_disable); /* * Keep track of debug users on each core. * The ref counts are per-cpu so we use a local_t type. */ static DEFINE_PER_CPU(int, mde_ref_count); static DEFINE_PER_CPU(int, kde_ref_count); void enable_debug_monitors(enum dbg_active_el el) { u32 mdscr, enable = 0; WARN_ON(preemptible()); if (this_cpu_inc_return(mde_ref_count) == 1) enable = DBG_MDSCR_MDE; if (el == DBG_ACTIVE_EL1 && this_cpu_inc_return(kde_ref_count) == 1) enable |= DBG_MDSCR_KDE; if (enable && debug_enabled) { mdscr = mdscr_read(); mdscr |= enable; mdscr_write(mdscr); } } NOKPROBE_SYMBOL(enable_debug_monitors); void disable_debug_monitors(enum dbg_active_el el) { u32 mdscr, disable = 0; WARN_ON(preemptible()); if (this_cpu_dec_return(mde_ref_count) == 0) disable = ~DBG_MDSCR_MDE; if (el == DBG_ACTIVE_EL1 && this_cpu_dec_return(kde_ref_count) == 0) disable &= ~DBG_MDSCR_KDE; if (disable) { mdscr = mdscr_read(); mdscr &= disable; mdscr_write(mdscr); } } NOKPROBE_SYMBOL(disable_debug_monitors); /* * OS lock clearing. */ static int clear_os_lock(unsigned int cpu) { write_sysreg(0, osdlr_el1); write_sysreg(0, oslar_el1); isb(); return 0; } static int __init debug_monitors_init(void) { return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, "arm64/debug_monitors:starting", clear_os_lock, NULL); } postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } NOKPROBE_SYMBOL(set_user_regs_spsr_ss); static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); #define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) #define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) static DEFINE_SPINLOCK(debug_hook_lock); static LIST_HEAD(user_step_hook); static LIST_HEAD(kernel_step_hook); static void register_debug_hook(struct list_head *node, struct list_head *list) { spin_lock(&debug_hook_lock); list_add_rcu(node, list); spin_unlock(&debug_hook_lock); } static void unregister_debug_hook(struct list_head *node) { spin_lock(&debug_hook_lock); list_del_rcu(node); spin_unlock(&debug_hook_lock); synchronize_rcu(); } void register_user_step_hook(struct step_hook *hook) { register_debug_hook(&hook->node, &user_step_hook); } void unregister_user_step_hook(struct step_hook *hook) { unregister_debug_hook(&hook->node); } void register_kernel_step_hook(struct step_hook *hook) { register_debug_hook(&hook->node, &kernel_step_hook); } void unregister_kernel_step_hook(struct step_hook *hook) { unregister_debug_hook(&hook->node); } /* * Call registered single step handlers * There is no Syndrome info to check for determining the handler. * So we call all the registered handlers, until the right handler is * found which returns zero. */ static int call_step_hook(struct pt_regs *regs, unsigned long esr) { struct step_hook *hook; struct list_head *list; int retval = DBG_HOOK_ERROR; list = user_mode(regs) ? &user_step_hook : &kernel_step_hook; /* * Since single-step exception disables interrupt, this function is * entirely not preemptible, and we can use rcu list safely here. */ list_for_each_entry_rcu(hook, list, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } return retval; } NOKPROBE_SYMBOL(call_step_hook); static void send_user_sigtrap(int si_code) { struct pt_regs *regs = current_pt_regs(); if (WARN_ON(!user_mode(regs))) return; if (interrupts_enabled(regs)) local_irq_enable(); arm64_force_sig_fault(SIGTRAP, si_code, instruction_pointer(regs), "User debug trap"); } static int single_step_handler(unsigned long unused, unsigned long esr, struct pt_regs *regs) { bool handler_found = false; /* * If we are stepping a pending breakpoint, call the hw_breakpoint * handler first. */ if (!reinstall_suspended_bps(regs)) return 0; if (!handler_found && call_step_hook(regs, esr) == DBG_HOOK_HANDLED) handler_found = true; if (!handler_found && user_mode(regs)) { send_user_sigtrap(TRAP_TRACE); /* * ptrace will disable single step unless explicitly * asked to re-enable it. For other clients, it makes * sense to leave it enabled (i.e. rewind the controls * to the active-not-pending state). */ user_rewind_single_step(current); } else if (!handler_found) { pr_warn("Unexpected kernel single-step exception at EL1\n"); /* * Re-enable stepping since we know that we will be * returning to regs. */ set_regs_spsr_ss(regs); } return 0; } NOKPROBE_SYMBOL(single_step_handler); static LIST_HEAD(user_break_hook); static LIST_HEAD(kernel_break_hook); void register_user_break_hook(struct break_hook *hook) { register_debug_hook(&hook->node, &user_break_hook); } void unregister_user_break_hook(struct break_hook *hook) { unregister_debug_hook(&hook->node); } void register_kernel_break_hook(struct break_hook *hook) { register_debug_hook(&hook->node, &kernel_break_hook); } void unregister_kernel_break_hook(struct break_hook *hook) { unregister_debug_hook(&hook->node); } static int call_break_hook(struct pt_regs *regs, unsigned long esr) { struct break_hook *hook; struct list_head *list; int (*fn)(struct pt_regs *regs, unsigned long esr) = NULL; list = user_mode(regs) ? &user_break_hook : &kernel_break_hook; /* * Since brk exception disables interrupt, this function is * entirely not preemptible, and we can use rcu list safely here. */ list_for_each_entry_rcu(hook, list, node) { if ((esr_brk_comment(esr) & ~hook->mask) == hook->imm) fn = hook->fn; } return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } NOKPROBE_SYMBOL(call_break_hook); static int brk_handler(unsigned long unused, unsigned long esr, struct pt_regs *regs) { if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED) return 0; if (user_mode(regs)) { send_user_sigtrap(TRAP_BRKPT); } else { pr_warn("Unexpected kernel BRK exception at EL1\n"); return -EFAULT; } return 0; } NOKPROBE_SYMBOL(brk_handler); int aarch32_break_handler(struct pt_regs *regs) { u32 arm_instr; u16 thumb_instr; bool bp = false; void __user *pc = (void __user *)instruction_pointer(regs); if (!compat_user_mode(regs)) return -EFAULT; if (compat_thumb_mode(regs)) { /* get 16-bit Thumb instruction */ __le16 instr; get_user(instr, (__le16 __user *)pc); thumb_instr = le16_to_cpu(instr); if (thumb_instr == AARCH32_BREAK_THUMB2_LO) { /* get second half of 32-bit Thumb-2 instruction */ get_user(instr, (__le16 __user *)(pc + 2)); thumb_instr = le16_to_cpu(instr); bp = thumb_instr == AARCH32_BREAK_THUMB2_HI; } else { bp = thumb_instr == AARCH32_BREAK_THUMB; } } else { /* 32-bit ARM instruction */ __le32 instr; get_user(instr, (__le32 __user *)pc); arm_instr = le32_to_cpu(instr); bp = (arm_instr & ~0xf0000000) == AARCH32_BREAK_ARM; } if (!bp) return -EFAULT; send_user_sigtrap(TRAP_BRKPT); return 0; } NOKPROBE_SYMBOL(aarch32_break_handler); void __init debug_traps_init(void) { hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP, TRAP_TRACE, "single-step handler"); hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP, TRAP_BRKPT, "BRK handler"); } /* Re-enable single step for syscall restarting. */ void user_rewind_single_step(struct task_struct *task) { /* * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } void user_regs_reset_single_step(struct user_pt_regs *regs, struct task_struct *task) { if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_user_regs_spsr_ss(regs); else clear_user_regs_spsr_ss(regs); } /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { WARN_ON(!irqs_disabled()); set_regs_spsr_ss(regs); mdscr_write(mdscr_read() | DBG_MDSCR_SS); enable_debug_monitors(DBG_ACTIVE_EL1); } NOKPROBE_SYMBOL(kernel_enable_single_step); void kernel_disable_single_step(void) { WARN_ON(!irqs_disabled()); mdscr_write(mdscr_read() & ~DBG_MDSCR_SS); disable_debug_monitors(DBG_ACTIVE_EL1); } NOKPROBE_SYMBOL(kernel_disable_single_step); int kernel_active_single_step(void) { WARN_ON(!irqs_disabled()); return mdscr_read() & DBG_MDSCR_SS; } NOKPROBE_SYMBOL(kernel_active_single_step); void kernel_rewind_single_step(struct pt_regs *regs) { set_regs_spsr_ss(regs); } /* ptrace API */ void user_enable_single_step(struct task_struct *task) { struct thread_info *ti = task_thread_info(task); if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_enable_single_step); void user_disable_single_step(struct task_struct *task) { clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); } NOKPROBE_SYMBOL(user_disable_single_step); |
| 234 234 234 233 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif /* * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ if (this_cpu_read(printk_context) || in_nmi()) return vprintk_deferred(fmt, args); /* No obstacles. */ return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 59 78 59 42 42 84 84 86 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> #include <uapi/linux/lsm.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @targ_ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { int error; error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(vfsuid_t rootvfsuid) { struct user_namespace *ns; kuid_t kroot; if (!vfsuid_valid(rootvfsuid)) return false; kroot = vfsuid_into_kuid(rootvfsuid); for (ns = current_user_ns();; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { int size; kuid_t kroot; vfsuid_t vfsroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf, sizeof(struct vfs_ns_cap_data), GFP_NOFS); dput(dentry); /* gcc11 complains if we don't check for !tmpbuf */ if (size < 0 || !tmpbuf) goto out_free; fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header(size, cap)) { root = 0; } else if (is_v3header(size, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ vfsroot = make_vfsuid(idmap, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), vfsuid_into_kuid(vfsroot)); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(vfsroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller */ static vfsuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return VFSUIDT_INIT(make_kuid(task_ns, rootid)); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @idmap: idmap of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; vfsuid_t vfsrootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; vfsrootid = rootid_from_xattr(*ivalue, size, task_ns); if (!vfsuid_valid(vfsrootid)) return -EINVAL; rootid = from_vfsuid(idmap, fs_ns, vfsrootid); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.val = (new->cap_bset.val & caps->permitted.val) | (new->cap_inheritable.val & caps->inheritable.val); if (caps->permitted.val & ~new->cap_permitted.val) /* insufficient to execute correctly */ ret = -EPERM; /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @idmap: idmap of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; vfsuid_t rootvfsuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid); if (!vfsuid_valid(rootvfsuid)) return -ENODATA; /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!rootid_owns_currentns(rootvfsuid)) return -ENODATA; cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted); cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable); /* * Rev1 had just a single 32-bit word, later expanded * to a second one for the high bits */ if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) { cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32; cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32; } cpu_caps->permitted.val &= CAP_VALID_MASK; cpu_caps->inheritable.val &= CAP_VALID_MASK; cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid); return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, const struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_idmap(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilities to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Determine if scheduler policy change is permitted * @p: The task to affect * * Determine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Determine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Determine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Determine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Determine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static const struct lsm_id capability_lsmid = { .name = "capability", .id = LSM_ID_CAPABILITY, }; static struct security_hook_list capability_hooks[] __ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), &capability_lsmid); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 207 220 90 41 42 41 42 3 63 101 106 81 106 106 190 99 102 100 176 67 177 177 177 177 102 177 22 124 186 187 207 207 219 220 220 220 220 220 220 220 220 102 19 19 7 6 80 32 32 82 39 3 85 63 101 177 80 7 7 6 6 6 6 7 10 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PGTABLE_H #define __ASM_PGTABLE_H #include <asm/bug.h> #include <asm/proc-fns.h> #include <asm/memory.h> #include <asm/mte.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable-prot.h> #include <asm/tlbflush.h> /* * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) #if VA_BITS == VA_BITS_MIN #define VMALLOC_END (VMEMMAP_START - SZ_8M) #else #define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) #define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) #endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #ifndef __ASSEMBLY__ #include <asm/cmpxchg.h> #include <asm/fixmap.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <linux/page_table_check.h> #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE /* Set stride and tlb_level in flush_*_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2) #define flush_pud_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page * fault on one CPU which has been handled concurrently by another CPU * does not need to perform additional invalidation. */ #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e)) /* * Macros to convert between a physical address and its placement in a * page table entry, taking care of 52-bit addresses. */ #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else #define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif #define pte_pfn(pte) (__pte_to_phys(pte) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) \ __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pte_none(pte) (!pte_val(pte)) #define __pte_clear(mm, addr, ptep) \ __set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) /* * The following only work if pte_present(). Undefined behaviour otherwise. */ #define pte_present(pte) (pte_valid(pte) || pte_present_invalid(pte)) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_rdonly(pte) (!!(pte_val(pte) & PTE_RDONLY)) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) #define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) #define pte_tagged(pte) ((pte_val(pte) & PTE_ATTRINDX_MASK) == \ PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pte_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pmd_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pte_hw_dirty(pte) (pte_write(pte) && !pte_rdonly(pte)) #define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_present_invalid(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID) /* * Execute-only user mappings do not have the PTE_USER bit set. All valid * kernel mappings have the PTE_UXN bit set. */ #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) /* * Returns true if the pte is valid and has the contiguous bit set. */ #define pte_valid_cont(pte) (pte_valid(pte) && pte_cont(pte)) /* * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. * Note that we can't make any assumptions based on the state of the access * flag, since __ptep_clear_flush_young() elides a DSB when invalidating the * TLB. */ #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (PTE_USER * bit set, subject to the write permission check). For execute-only * mappings, like PROT_EXEC with EPAN (both PTE_USER and PTE_UXN bits * not set) must return false. PROT_NONE mappings do not have the * PTE_VALID bit set. */ #define pte_access_permitted(pte, write) \ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte))) #define pmd_access_permitted(pmd, write) \ (pte_access_permitted(pmd_pte(pmd), (write))) #define pud_access_permitted(pud, write) \ (pte_access_permitted(pud_pte(pud), (write))) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) &= ~pgprot_val(prot); return pte; } static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) |= pgprot_val(prot); return pte; } static inline pmd_t clear_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) &= ~pgprot_val(prot); return pmd; } static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) |= pgprot_val(prot); return pmd; } static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkclean(pte_t pte) { pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkdirty(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); if (pte_write(pte)) pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_wrprotect(pte_t pte) { /* * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY * clear), set the PTE_DIRTY bit. */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkyoung(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkspecial(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } static inline pte_t pte_mkcont(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_CONT)); return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); } static inline pte_t pte_mknoncont(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_CONT)); } static inline pte_t pte_mkpresent(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } static inline pte_t pte_mkinvalid(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID)); pte = clear_pte_bit(pte, __pgprot(PTE_VALID)); return pte; } static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); } static inline pte_t pte_mkdevmap(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_UFFD_WP); } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP))); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void __set_pte(pte_t *ptep, pte_t pte) { __set_pte_nosync(ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ if (pte_valid_not_user(pte)) { dsb(ishst); isb(); } } static inline pte_t __ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } extern void __sync_icache_dcache(pte_t pteval); bool pgattr_change_is_safe(u64 old, u64 new); /* * PTE bits configuration in the presence of hardware Dirty Bit Management * (PTE_WRITE == PTE_DBM): * * Dirty Writable | PTE_RDONLY PTE_WRITE PTE_DIRTY (sw) * 0 0 | 1 0 0 * 0 1 | 1 1 0 * 1 0 | 1 0 1 * 1 1 | 0 1 x * * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via * the page fault mechanism. Checking the dirty status of a pte becomes: * * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, pte_t pte) { pte_t old_pte; if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; old_pte = __ptep_get(ptep); if (!pte_valid(old_pte) || !pte_valid(pte)) return; if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1) return; /* * Check for potential race with hardware updates of the pte * (__ptep_set_access_flags safely changes valid ptes without going * through an invalid entry). */ VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(!pgattr_change_is_safe(pte_val(old_pte), pte_val(pte)), "%s: unsafe attribute change: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); } static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) { if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte); /* * If the PTE would provide user space access to the tags associated * with it then ensure that the MTE tags are synchronised. Although * pte_access_permitted() returns false for exec only mappings, they * don't expose tags (instruction fetches don't check tags). */ if (system_supports_mte() && pte_access_permitted(pte, false) && !pte_special(pte) && pte_tagged(pte)) mte_sync_tags(pte, nr_pages); } /* * Select all bits except the pfn */ static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pfn = pte_pfn(pte); return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); } #define pte_advance_pfn pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte)); } static inline void __set_ptes(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); __sync_cache_and_tags(pte, nr); for (;;) { __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_advance_pfn(pte, 1); } } /* * Huge pte definitions. */ #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) /* * Hugetlb definitions. */ #define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) static inline pte_t pgd_pte(pgd_t pgd) { return __pte(pgd_val(pgd)); } static inline pte_t p4d_pte(p4d_t p4d) { return __pte(p4d_val(p4d)); } static inline pte_t pud_pte(pud_t pud) { return __pte(pud_val(pud)); } static inline pud_t pte_pud(pte_t pte) { return __pud(pte_val(pte)); } static inline pmd_t pud_pmd(pud_t pud) { return __pmd(pud_val(pud)); } static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); } static inline pmd_t pte_pmd(pte_t pte) { return __pmd(pte_val(pte)); } static inline pgprot_t mk_pud_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT); } static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & PTE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } static inline int pte_swp_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_SWP_UFFD_WP); } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { /* * pte_present_invalid() tells us that the pte is invalid from HW * perspective but present from SW perspective, so the fields are to be * interpretted as per the HW layout. The second 2 checks are the unique * encoding that we use for PROT_NONE. It is insufficient to only use * the first check because we share the same encoding scheme with pmds * which support pmd_mkinvalid(), so can be present-invalid without * being PROT_NONE. */ return pte_present_invalid(pte) && !pte_user(pte) && !pte_user_exec(pte); } static inline int pmd_protnone(pmd_t pmd) { return pte_protnone(pmd_pte(pmd)); } #endif #define pmd_present(pmd) pte_present(pmd_pte(pmd)) /* * THP definitions. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) #define pmd_user(pmd) pte_user(pmd_pte(pmd)) #define pmd_user_exec(pmd) pte_user_exec(pmd_pte(pmd)) #define pmd_cont(pmd) pte_cont(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkinvalid(pmd) pte_pmd(pte_mkinvalid(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define pmd_uffd_wp(pmd) pte_uffd_wp(pmd_pte(pmd)) #define pmd_mkuffd_wp(pmd) pte_pmd(pte_mkuffd_wp(pmd_pte(pmd))) #define pmd_clear_uffd_wp(pmd) pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd))) #define pmd_swp_uffd_wp(pmd) pte_swp_uffd_wp(pmd_pte(pmd)) #define pmd_swp_mkuffd_wp(pmd) pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd))) #define pmd_swp_clear_uffd_wp(pmd) \ pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) #endif static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); } #define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd)) #define __phys_to_pmd_val(phys) __phys_to_pte_val(phys) #define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT) #define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) #define pud_young(pud) pte_young(pud_pte(pud)) #define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) #define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT)) #define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud)) #define __phys_to_pud_val(phys) __phys_to_pte_val(phys) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) static inline void __set_pte_at(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { __sync_cache_and_tags(pte, nr); __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd), PMD_SIZE >> PAGE_SHIFT); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud), PUD_SIZE >> PAGE_SHIFT); } #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) #define __pgd_to_phys(pgd) __pte_to_phys(pgd_pte(pgd)) #define __phys_to_pgd_val(phys) __phys_to_pte_val(phys) #define __pgprot_modify(prot,mask,bits) \ __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) /* * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define pgprot_device(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) #define pgprot_tagged(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pgprot_mhp pgprot_tagged /* * DMA allocations for non-coherent devices use what the Arm architecture calls * "Normal non-cacheable" memory, which permits speculation, unaligned accesses * and merging of writes. This is different from "Device-nGnR[nE]" memory which * is intended for MMIO and thus forbids speculation, preserves access size, * requires strict alignment and can also force write responses to come from the * endpoint. */ #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, \ PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) #define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) #define pte_leaf_size(pte) (pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 static inline bool pud_sect(pud_t pud) { return false; } static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) #define pud_table(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_TABLE) #endif extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; extern pgd_t swapper_pg_dir[]; extern pgd_t idmap_pg_dir[]; extern pgd_t tramp_pg_dir[]; extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); static inline bool in_swapper_pgdir(void *addr) { return ((unsigned long)addr & PAGE_MASK) == ((unsigned long)swapper_pg_dir & PAGE_MASK); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { #ifdef __PAGETABLE_PMD_FOLDED if (in_swapper_pgdir(pmdp)) { set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd))); return; } #endif /* __PAGETABLE_PMD_FOLDED */ WRITE_ONCE(*pmdp, pmd); if (pmd_valid(pmd)) { dsb(ishst); isb(); } } static inline void pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, __pmd(0)); } static inline phys_addr_t pmd_page_paddr(pmd_t pmd) { return __pmd_to_phys(pmd); } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_page_paddr(pmd)); } /* Find an entry in the third-level page table. */ #define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr)) #define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr)) #define pte_clear_fixmap() clear_fixmap(FIX_PTE) #define pmd_page(pmd) phys_to_page(__pmd_to_phys(pmd)) /* use ONLY for statically allocated translation tables */ #define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr)))) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ #define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot) #if CONFIG_PGTABLE_LEVELS > 2 #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) #ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #else #define pud_leaf(pud) false #endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline bool pgtable_l4_enabled(void); static inline void set_pud(pud_t *pudp, pud_t pud) { if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } WRITE_ONCE(*pudp, pud); if (pud_valid(pud)) { dsb(ishst); isb(); } } static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); } static inline phys_addr_t pud_page_paddr(pud_t pud) { return __pud_to_phys(pud); } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_page_paddr(pud)); } /* Find an entry in the second-level page table. */ #define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) #define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr)) #define pmd_clear_fixmap() clear_fixmap(FIX_PMD) #define pud_page(pud) phys_to_page(__pud_to_phys(pud)) /* use ONLY for statically allocated translation tables */ #define pmd_offset_kimg(dir,addr) ((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr)))) #else #define pud_valid(pud) false #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) #define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL #define pmd_set_fixmap_offset(pudp, addr) ((pmd_t *)pudp) #define pmd_clear_fixmap() #define pmd_offset_kimg(dir,addr) ((pmd_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static __always_inline bool pgtable_l4_enabled(void) { if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) return true; if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_pud_folded(const struct mm_struct *mm) { return !pgtable_l4_enabled(); } #define mm_pud_folded mm_pud_folded #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) #define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { if (in_swapper_pgdir(p4dp)) { set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d))); return; } WRITE_ONCE(*p4dp, p4d); dsb(ishst); isb(); } static inline void p4d_clear(p4d_t *p4dp) { if (pgtable_l4_enabled()) set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) { return __p4d_to_phys(p4d); } #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) { return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) { BUG_ON(!pgtable_l4_enabled()); return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); } static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); } #define pud_offset_lockless pud_offset_lockless static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) { return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); } #define pud_offset pud_offset static inline pud_t *pud_set_fixmap(unsigned long addr) { if (!pgtable_l4_enabled()) return NULL; return (pud_t *)set_fixmap_offset(FIX_PUD, addr); } static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return pud_set_fixmap(pud_offset_phys(p4dp, addr)); } static inline void pud_clear_fixmap(void) { if (pgtable_l4_enabled()) clear_fixmap(FIX_PUD); } /* use ONLY for statically allocated translation tables */ static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); } #define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else static inline bool pgtable_l4_enabled(void) { return false; } #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ #define pud_set_fixmap(addr) NULL #define pud_set_fixmap_offset(pgdp, addr) ((pud_t *)pgdp) #define pud_clear_fixmap() #define pud_offset_kimg(dir,addr) ((pud_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static __always_inline bool pgtable_l5_enabled(void) { if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_p4d_folded(const struct mm_struct *mm) { return !pgtable_l5_enabled(); } #define mm_p4d_folded mm_p4d_folded #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) #define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { if (in_swapper_pgdir(pgdp)) { set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); return; } WRITE_ONCE(*pgdp, pgd); dsb(ishst); isb(); } static inline void pgd_clear(pgd_t *pgdp) { if (pgtable_l5_enabled()) set_pgd(pgdp, __pgd(0)); } static inline phys_addr_t pgd_page_paddr(pgd_t pgd) { return __pgd_to_phys(pgd); } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) { return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); } static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) { BUG_ON(!pgtable_l5_enabled()); return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); } static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); } #define p4d_offset_lockless p4d_offset_lockless static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) { return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); } static inline p4d_t *p4d_set_fixmap(unsigned long addr) { if (!pgtable_l5_enabled()) return NULL; return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); } static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); } static inline void p4d_clear_fixmap(void) { if (pgtable_l5_enabled()) clear_fixmap(FIX_P4D); } /* use ONLY for statically allocated translation tables */ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); } #define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) #else static inline bool pgtable_l5_enabled(void) { return false; } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) /* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ #define p4d_set_fixmap(addr) NULL #define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) #define p4d_clear_fixmap() #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) #define pgd_set_fixmap(addr) ((pgd_t *)set_fixmap_offset(FIX_PGD, addr)) #define pgd_clear_fixmap() clear_fixmap(FIX_PGD) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { /* * Normal and Normal-Tagged are two different memory types and indices * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK. */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | PTE_GP | PTE_ATTRINDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); /* * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware * dirtiness again. */ if (pte_sw_dirty(pte)) pte = pte_mkdirty(pte); return pte; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); } extern int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { return __ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return pte_valid(pte) && (pte_user(pte) || pte_user_exec(pte)); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_valid(pmd) && !pmd_table(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_valid(pud) && !pud_table(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif /* * Atomic pte/pmd modifications. */ static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; pte = __ptep_get(ptep); do { old_pte = pte; pte = pte_mkold(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); return pte_young(pte); } static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { int young = __ptep_test_and_clear_young(vma, address, ptep); if (young) { /* * We can elide the trailing DSB here since the worst that can * happen is that a CPU continues to use the young entry in its * TLB and we mistakenly reclaim the associated page. The * window for such an event is bounded by the next * context-switch, which provides a DSB to complete the TLB * invalidation. */ flush_tlb_page_nosync(vma, address); } return young; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); page_table_check_pte_clear(mm, pte); return pte; } static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { __ptep_get_and_clear(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = __ptep_get_and_clear(mm, addr, ptep); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = __ptep_get_and_clear(mm, addr, ptep); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); page_table_check_pmd_clear(mm, pmd); return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep, pte_t pte) { pte_t old_pte; do { old_pte = pte; pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } /* * __ptep_set_wrprotect - mark read-only while trasferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { ___ptep_set_wrprotect(mm, address, ptep, __ptep_get(ptep)); } static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, pte_t *ptep, unsigned int nr) { unsigned int i; for (i = 0; i < nr; i++, address += PAGE_SIZE, ptep++) __ptep_set_wrprotect(mm, address, ptep); } static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, cydp_t flags) { pte_t old_pte; do { old_pte = pte; if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { pte = __ptep_get(ptep); if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) __set_pte(ptep, pte_mkclean(pte_mkold(pte))); else __clear_young_dirty_pte(vma, addr, ptep, pte, flags); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { __ptep_set_wrprotect(mm, address, (pte_t *)pmdp); } #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) * bits 2: remember PG_anon_exclusive * bit 3: remember uffd-wp state * bits 6-10: swap type * bit 11: PTE_PRESENT_INVALID (must be zero) * bits 12-61: swap offset */ #define __SWP_TYPE_SHIFT 6 #define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT 12 #define __SWP_OFFSET_BITS 50 #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) #define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK) #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(swp) ((pte_t) { (swp).val }) #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) #define __swp_entry_to_pmd(swp) __pmd((swp).val) #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ /* * Ensure that there are not more swap files than can be encoded in the kernel * PTEs. */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { if (system_supports_mte()) mte_invalidate_tags(type, offset); } static inline void arch_swap_invalidate_area(int type) { if (system_supports_mte()) mte_invalidate_tags_area(type); } #define __HAVE_ARCH_SWAP_RESTORE extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ /* * On AArch64, the cache coherency is handled via the __set_ptes() function. */ static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * We don't do anything here, so there's a very small chance of * us retaking a user fault which we just fixed up. The alternative * is doing a dsb(ishst), but that penalises the fastpath. */ } #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else #define phys_to_ttbr(addr) (addr) #endif /* * On arm64 without hardware Access Flag, copying from user will fail because * the pte is old and cannot be marked young. So we always end up with zeroed * page after fork() + CoW for pfn mappings. We don't always have a * hardware-managed access flag on arm64. */ #define arch_has_hw_pte_young cpu_has_hw_af /* * Experimentally, it's cheap to set the access flag in hardware and we * benefit from prefaulting mappings as 'old' to start with. */ #define arch_wants_old_prefaulted_pte cpu_has_hw_af static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION #define ptep_modify_prot_start ptep_modify_prot_start extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define ptep_modify_prot_commit ptep_modify_prot_commit extern void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t new_pte); #ifdef CONFIG_ARM64_CONTPTE /* * The contpte APIs are used to transparently manage the contiguous bit in ptes * where it is possible and makes sense to do so. The PTE_CONT bit is considered * a private implementation detail of the public ptep API (see below). */ extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte); extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep); extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr); extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr); extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * Only bother trying if both the virtual and physical addresses are * aligned and correspond to the last entry in a contig range. The core * code mostly modifies ranges from low to high, so this is the likely * the last modification in the contig range, so a good time to fold. * We can't fold special mappings, because there is no associated folio. */ const unsigned long contmask = CONT_PTES - 1; bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask; if (unlikely(valign)) { bool palign = (pte_pfn(pte) & contmask) == contmask; if (unlikely(palign && pte_valid(pte) && !pte_cont(pte) && !pte_special(pte))) __contpte_try_fold(mm, addr, ptep, pte); } } static __always_inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (unlikely(pte_valid_cont(pte))) __contpte_try_unfold(mm, addr, ptep, pte); } #define pte_batch_hint pte_batch_hint static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { if (!pte_valid_cont(pte)) return 1; return CONT_PTES - (((unsigned long)ptep >> 3) & (CONT_PTES - 1)); } /* * The below functions constitute the public API that arm64 presents to the * core-mm to manipulate PTE entries within their page tables (or at least this * is the subset of the API that arm64 needs to implement). These public * versions will automatically and transparently apply the contiguous bit where * it makes sense to do so. Therefore any users that are contig-aware (e.g. * hugetlb, kernel mapper) should NOT use these APIs, but instead use the * private versions, which are prefixed with double underscore. All of these * APIs except for ptep_get_lockless() are expected to be called with the PTL * held. Although the contiguous bit is considered private to the * implementation, it is deliberately allowed to leak through the getters (e.g. * ptep_get()), back to core code. This is required so that pte_leaf_size() can * provide an accurate size for perf_get_pgtable_size(). But this leakage means * its possible a pte will be passed to a setter with the contiguous bit set, so * we explicitly clear the contiguous bit in those cases to prevent accidentally * setting it in the pgtable. */ #define ptep_get ptep_get static inline pte_t ptep_get(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get(ptep, pte); } #define ptep_get_lockless ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get_lockless(ptep); } static inline void set_pte(pte_t *ptep, pte_t pte) { /* * We don't have the mm or vaddr so cannot unfold contig entries (since * it requires tlb maintenance). set_pte() is not used in core code, so * this should never even be called. Regardless do our best to service * any call and emit a warning if there is any attempt to set a pte on * top of an existing contig range. */ pte_t orig_pte = __ptep_get(ptep); WARN_ON_ONCE(pte_valid_cont(orig_pte)); __set_pte(ptep, pte_mknoncont(pte)); } #define set_ptes set_ptes static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { pte = pte_mknoncont(pte); if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __set_ptes(mm, addr, ptep, pte, 1); contpte_try_fold(mm, addr, ptep, pte); } else { contpte_set_ptes(mm, addr, ptep, pte, nr); } } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __pte_clear(mm, addr, ptep); } #define clear_full_ptes clear_full_ptes static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __clear_full_ptes(mm, addr, ptep, nr, full); } else { contpte_clear_full_ptes(mm, addr, ptep, nr, full); } } #define get_and_clear_full_ptes get_and_clear_full_ptes static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte; if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); pte = __get_and_clear_full_ptes(mm, addr, ptep, nr, full); } else { pte = contpte_get_and_clear_full_ptes(mm, addr, ptep, nr, full); } return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); return __ptep_get_and_clear(mm, addr, ptep); } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_test_and_clear_young(vma, addr, ptep); return contpte_ptep_test_and_clear_young(vma, addr, ptep); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_clear_flush_young(vma, addr, ptep); return contpte_ptep_clear_flush_young(vma, addr, ptep); } #define wrprotect_ptes wrprotect_ptes static __always_inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1)) { /* * Optimization: wrprotect_ptes() can only be called for present * ptes so we only need to check contig bit as condition for * unfold, and we can remove the contig bit from the pte we read * to avoid re-reading. This speeds up fork() which is sensitive * for order-0 folios. Equivalent to contpte_try_unfold(). */ pte_t orig_pte = __ptep_get(ptep); if (unlikely(pte_cont(orig_pte))) { __contpte_try_unfold(mm, addr, ptep, orig_pte); orig_pte = pte_mknoncont(orig_pte); } ___ptep_set_wrprotect(mm, addr, ptep, orig_pte); } else { contpte_wrprotect_ptes(mm, addr, ptep, nr); } } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { wrprotect_ptes(mm, addr, ptep, 1); } #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS static inline int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) { pte_t orig_pte = __ptep_get(ptep); entry = pte_mknoncont(entry); if (likely(!pte_valid_cont(orig_pte))) return __ptep_set_access_flags(vma, addr, ptep, entry, dirty); return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } #define clear_young_dirty_ptes clear_young_dirty_ptes static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); else contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); } #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get #define set_pte __set_pte #define set_ptes __set_ptes #define pte_clear __pte_clear #define clear_full_ptes __clear_full_ptes #define get_and_clear_full_ptes __get_and_clear_full_ptes #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define ptep_get_and_clear __ptep_get_and_clear #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young __ptep_test_and_clear_young #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young __ptep_clear_flush_young #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define ptep_set_wrprotect __ptep_set_wrprotect #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags #define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ |
| 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _LINUX_RSEQ_H #define _LINUX_RSEQ_H #ifdef CONFIG_RSEQ #include <linux/preempt.h> #include <linux/sched.h> /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. */ enum rseq_event_mask_bits { RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, }; enum rseq_event_mask { RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), }; static inline void rseq_set_notify_resume(struct task_struct *t) { if (t->rseq) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { if (current->rseq) __rseq_handle_notify_resume(ksig, regs); } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ static inline void rseq_preempt(struct task_struct *t) { __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* rseq_migrate() requires preemption to be disabled. */ static inline void rseq_migrate(struct task_struct *t) { __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } } static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } #else static inline void rseq_set_notify_resume(struct task_struct *t) { } static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) { } static inline void rseq_migrate(struct task_struct *t) { } static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { } static inline void rseq_execve(struct task_struct *t) { } #endif #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); #else static inline void rseq_syscall(struct pt_regs *regs) { } #endif #endif /* _LINUX_RSEQ_H */ |
| 11 11 7 11 11 11 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/tlb.h * * Copyright (C) 2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_TLB_H #define __ASM_TLB_H #include <linux/pagemap.h> #include <linux/swap.h> static inline void __tlb_remove_table(void *_table) { free_page_and_swap_cache((struct page *)_table); } #define tlb_flush tlb_flush static void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> /* * get the tlbi levels in arm64. Default value is TLBI_TTL_UNKNOWN if more than * one of cleared_* is set or neither is set - this elides the level hinting to * the hardware. */ static inline int tlb_get_level(struct mmu_gather *tlb) { /* The TTL field is only valid for the leaf entry. */ if (tlb->freed_tables) return TLBI_TTL_UNKNOWN; if (tlb->cleared_ptes && !(tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds)) return 3; if (tlb->cleared_pmds && !(tlb->cleared_ptes || tlb->cleared_puds || tlb->cleared_p4ds)) return 2; if (tlb->cleared_puds && !(tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_p4ds)) return 1; if (tlb->cleared_p4ds && !(tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds)) return 0; return TLBI_TTL_UNKNOWN; } static inline void tlb_flush(struct mmu_gather *tlb) { struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); bool last_level = !tlb->freed_tables; unsigned long stride = tlb_get_unmap_size(tlb); int tlb_level = tlb_get_level(tlb); /* * If we're tearing down the address space then we only care about * invalidating the walk-cache, since the ASID allocator won't * reallocate our ASID without invalidating the entire TLB. */ if (tlb->fullmm) { if (!last_level) flush_tlb_mm(tlb->mm); return; } __flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level, tlb_level); } static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { struct ptdesc *ptdesc = page_ptdesc(pte); pagetable_pte_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); pagetable_pmd_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #endif #if CONFIG_PGTABLE_LEVELS > 3 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { struct ptdesc *ptdesc = virt_to_ptdesc(pudp); if (!pgtable_l4_enabled()) return; pagetable_pud_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } #endif #endif |
| 92 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG_KMEM) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_alloc_contig_migrate_range_info, TP_PROTO(unsigned long start, unsigned long end, unsigned long nr_migrated, unsigned long nr_reclaimed, unsigned long nr_mapped, int migratetype), TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned long, nr_migrated) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_mapped) __field(int, migratetype) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->nr_migrated = nr_migrated; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_mapped = nr_mapped; __entry->migratetype = migratetype; ), TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", __entry->start, __entry->end, __entry->migratetype, __entry->nr_migrated, __entry->nr_reclaimed, __entry->nr_mapped) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 9 9 8 8 2 4 2 1 1 6 8 8 7 7 8 8 5 4 6 5 5 5 5 5 4 5 5 5 5 5 3 5 5 2 6 3 6 3 2 1 2 2 1 1 1 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started * reading in order to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(was_full)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_version != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_version = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_version = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 38 37 32 32 24 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ raw_spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; raw_spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_raw_lock); int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ raw_spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; raw_spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave); |
| 37 37 37 37 36 36 36 36 36 27 1 36 37 42 42 42 42 41 42 42 19 19 19 19 19 19 19 42 42 42 42 42 42 42 42 42 42 19 19 42 42 42 42 42 42 42 42 41 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 | /* * hugetlbpage-backed filesystem. Based on ramfs. * * Nadia Yvette Chambers, 2002 * * Copyright (C) 2002 Linus Torvalds. * License: GPL */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/thread_info.h> #include <asm/current.h> #include <linux/falloc.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/kernel.h> #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/string.h> #include <linux/capability.h> #include <linux/ctype.h> #include <linux/backing-dev.h> #include <linux/hugetlb.h> #include <linux/pagevec.h> #include <linux/fs_parser.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/dnotify.h> #include <linux/statfs.h> #include <linux/security.h> #include <linux/magic.h> #include <linux/migrate.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <linux/sched/mm.h> static const struct address_space_operations hugetlbfs_aops; static const struct file_operations hugetlbfs_file_operations; static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; struct hugetlbfs_fs_context { struct hstate *hstate; unsigned long long max_size_opt; unsigned long long min_size_opt; long max_hpages; long nr_inodes; long min_hpages; enum hugetlbfs_size_type max_val_type; enum hugetlbfs_size_type min_val_type; kuid_t uid; kgid_t gid; umode_t mode; }; int sysctl_hugetlb_shm_group; enum hugetlb_param { Opt_gid, Opt_min_size, Opt_mode, Opt_nr_inodes, Opt_pagesize, Opt_size, Opt_uid, }; static const struct fs_parameter_spec hugetlb_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_string("min_size", Opt_min_size), fsparam_u32oct("mode", Opt_mode), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("pagesize", Opt_pagesize), fsparam_string("size", Opt_size), fsparam_u32 ("uid", Opt_uid), {} }; /* * Mask used when checking the page offset value passed in via system * calls. This value will be converted to a loff_t which is signed. * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the * value. The extra bit (- 1 in the shift value) is to take the sign * bit into account. */ #define PGOFF_LOFFT_MAX \ (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has * already been checked by prepare_hugepage_range. If you add * any error returns here, do so after setting VM_HUGETLB, so * is_vm_hugetlb_page tests below unmap_region go the right * way when do_mmap unwinds (may be important on powerpc * and ia64). */ vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND); vma->vm_ops = &hugetlb_vm_ops; ret = seal_check_write(info->seals, vma); if (ret) return ret; /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can * only happen on architectures where sizeof(loff_t) == * sizeof(unsigned long). So, only check in those instances. */ if (sizeof(unsigned long) == sizeof(loff_t)) { if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL; } /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* check for overflow */ if (len < vma_len) return -EINVAL; inode_lock(inode); file_accessed(file); ret = -ENOMEM; vm_flags = vma->vm_flags; /* * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip * reserving here. Note: only for SHM hugetlbfs file, the inode * flag S_PRIVATE is set. */ if (inode->i_flags & S_PRIVATE) vm_flags |= VM_NORESERVE; if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, vm_flags)) goto out; ret = 0; if (vma->vm_flags & VM_WRITE && inode->i_size < len) i_size_write(inode, len); out: inode_unlock(inode); return ret; } /* * Called under mmap_write_lock(mm). */ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); struct vm_unmapped_area_info info = {}; info.length = len; info.low_limit = current->mm->mmap_base; info.high_limit = arch_get_mmap_end(addr, len, flags); info.align_mask = PAGE_MASK & ~huge_page_mask(h); return vm_unmapped_area(&info); } static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); struct vm_unmapped_area_info info = {}; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (unlikely(offset_in_page(addr))) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; info.high_limit = arch_get_mmap_end(addr, len, flags); addr = vm_unmapped_area(&info); } return addr; } unsigned long generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } /* * Use MMF_TOPDOWN flag as a hint to use topdown routine. * If architectures have special needs, they should define their own * version of hugetlb_get_unmapped_area. */ if (test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_topdown(file, addr, len, pgoff, flags); return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); } #ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA static unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags); } #endif /* * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset. * Returns the maximum number of bytes one can read without touching the 1st raw * HWPOISON subpage. * * The implementation borrows the iteration logic from copy_page_to_iter*. */ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes) { size_t n = 0; size_t res = 0; /* First subpage to start the loop. */ page = nth_page(page, offset / PAGE_SIZE); offset %= PAGE_SIZE; while (1) { if (is_raw_hwpoison_page_in_hugepage(page)) break; /* Safe to read n bytes without touching HWPOISON subpage. */ n = min(bytes, (size_t)PAGE_SIZE - offset); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page = nth_page(page, 1); offset = 0; } } return res; } /* * Support for read() - Find the page attached to f_mapping and copy out the * data. This provides functionality similar to filemap_read(). */ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct hstate *h = hstate_file(file); struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; unsigned long index = iocb->ki_pos >> huge_page_shift(h); unsigned long offset = iocb->ki_pos & ~huge_page_mask(h); unsigned long end_index; loff_t isize; ssize_t retval = 0; while (iov_iter_count(to)) { struct folio *folio; size_t nr, copied, want; /* nr is the maximum number of bytes to copy from this page */ nr = huge_page_size(h); isize = i_size_read(inode); if (!isize) break; end_index = (isize - 1) >> huge_page_shift(h); if (index > end_index) break; if (index == end_index) { nr = ((isize - 1) & ~huge_page_mask(h)) + 1; if (nr <= offset) break; } nr = nr - offset; /* Find the folio */ folio = filemap_lock_hugetlb_folio(h, mapping, index); if (IS_ERR(folio)) { /* * We have a HOLE, zero out the user-buffer for the * length of the hole or request. */ copied = iov_iter_zero(nr, to); } else { folio_unlock(folio); if (!folio_test_hwpoison(folio)) want = nr; else { /* * Adjust how many bytes safe to read without * touching the 1st raw HWPOISON subpage after * offset. */ want = adjust_range_hwpoison(&folio->page, offset, nr); if (want == 0) { folio_put(folio); retval = -EIO; break; } } /* * We have the folio, copy it to user space buffer. */ copied = copy_folio_to_iter(folio, offset, want, to); folio_put(folio); } offset += copied; retval += copied; if (copied != nr && iov_iter_count(to)) { if (!retval) retval = -EFAULT; break; } index += offset >> huge_page_shift(h); offset &= ~huge_page_mask(h); } iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset; return retval; } static int hugetlbfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata) { return -EINVAL; } static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { BUG(); return -EINVAL; } static void hugetlb_delete_from_page_cache(struct folio *folio) { folio_clear_dirty(folio); folio_clear_uptodate(folio); filemap_remove_folio(folio); } /* * Called with i_mmap_rwsem held for inode based vma maps. This makes * sure vma (and vm_mm) will not go away. We also hold the hugetlb fault * mutex for the page in the mapping. So, we can not race with page being * faulted into the vma. */ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { pte_t *ptep, pte; ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma))); if (!ptep) return false; pte = huge_ptep_get(ptep); if (huge_pte_none(pte) || !pte_present(pte)) return false; if (pte_page(pte) == page) return true; return false; } /* * Can vma_offset_start/vma_offset_end overflow on 32-bit arches? * No, because the interval tree returns us only those vmas * which overlap the truncated area starting at pgoff, * and no vma on a 32-bit arch can span beyond the 4GB. */ static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start) { unsigned long offset = 0; if (vma->vm_pgoff < start) offset = (start - vma->vm_pgoff) << PAGE_SHIFT; return vma->vm_start + offset; } static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end) { unsigned long t_end; if (!end) return vma->vm_end; t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start; if (t_end > vma->vm_end) t_end = vma->vm_end; return t_end; } /* * Called with hugetlb fault mutex held. Therefore, no more mappings to * this folio can be created while executing the routine. */ static void hugetlb_unmap_file_folio(struct hstate *h, struct address_space *mapping, struct folio *folio, pgoff_t index) { struct rb_root_cached *root = &mapping->i_mmap; struct hugetlb_vma_lock *vma_lock; struct page *page = &folio->page; struct vm_area_struct *vma; unsigned long v_start; unsigned long v_end; pgoff_t start, end; start = index * pages_per_huge_page(h); end = (index + 1) * pages_per_huge_page(h); i_mmap_lock_write(mapping); retry: vma_lock = NULL; vma_interval_tree_foreach(vma, root, start, end - 1) { v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); if (!hugetlb_vma_maps_page(vma, v_start, page)) continue; if (!hugetlb_vma_trylock_write(vma)) { vma_lock = vma->vm_private_data; /* * If we can not get vma lock, we need to drop * immap_sema and take locks in order. First, * take a ref on the vma_lock structure so that * we can be guaranteed it will not go away when * dropping immap_sema. */ kref_get(&vma_lock->refs); break; } unmap_hugepage_range(vma, v_start, v_end, NULL, ZAP_FLAG_DROP_MARKER); hugetlb_vma_unlock_write(vma); } i_mmap_unlock_write(mapping); if (vma_lock) { /* * Wait on vma_lock. We know it is still valid as we have * a reference. We must 'open code' vma locking as we do * not know if vma_lock is still attached to vma. */ down_write(&vma_lock->rw_sema); i_mmap_lock_write(mapping); vma = vma_lock->vma; if (!vma) { /* * If lock is no longer attached to vma, then just * unlock, drop our reference and retry looking for * other vmas. */ up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); goto retry; } /* * vma_lock is still attached to vma. Check to see if vma * still maps page and if so, unmap. */ v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); if (hugetlb_vma_maps_page(vma, v_start, page)) unmap_hugepage_range(vma, v_start, v_end, NULL, ZAP_FLAG_DROP_MARKER); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); hugetlb_vma_unlock_write(vma); goto retry; } } static void hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, zap_flags_t zap_flags) { struct vm_area_struct *vma; /* * end == 0 indicates that the entire range after start should be * unmapped. Note, end is exclusive, whereas the interval tree takes * an inclusive "last". */ vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) { unsigned long v_start; unsigned long v_end; if (!hugetlb_vma_trylock_write(vma)) continue; v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags); /* * Note that vma lock only exists for shared/non-private * vmas. Therefore, lock is not held when calling * unmap_hugepage_range for private vmas. */ hugetlb_vma_unlock_write(vma); } } /* * Called with hugetlb fault mutex held. * Returns true if page was actually removed, false otherwise. */ static bool remove_inode_single_folio(struct hstate *h, struct inode *inode, struct address_space *mapping, struct folio *folio, pgoff_t index, bool truncate_op) { bool ret = false; /* * If folio is mapped, it was faulted in after being * unmapped in caller. Unmap (again) while holding * the fault mutex. The mutex will prevent faults * until we finish removing the folio. */ if (unlikely(folio_mapped(folio))) hugetlb_unmap_file_folio(h, mapping, folio, index); folio_lock(folio); /* * We must remove the folio from page cache before removing * the region/ reserve map (hugetlb_unreserve_pages). In * rare out of memory conditions, removal of the region/reserve * map could fail. Correspondingly, the subpool and global * reserve usage count can need to be adjusted. */ VM_BUG_ON_FOLIO(folio_test_hugetlb_restore_reserve(folio), folio); hugetlb_delete_from_page_cache(folio); ret = true; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); } folio_unlock(folio); return ret; } /* * remove_inode_hugepages handles two distinct cases: truncation and hole * punch. There are subtle differences in operation for each case. * * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserve * maps and global counts. Page faults can race with truncation. * During faults, hugetlb_no_page() checks i_size before page allocation, * and again after obtaining page table lock. It will 'back out' * allocations in the truncated range. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserve map * deleted. The region/reserve map for ranges without associated * pages are not modified. Page faults can race with hole punch. * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, loff_t lend) { struct hstate *h = hstate_inode(inode); struct address_space *mapping = &inode->i_data; const pgoff_t end = lend >> PAGE_SHIFT; struct folio_batch fbatch; pgoff_t next, index; int i, freed = 0; bool truncate_op = (lend == LLONG_MAX); folio_batch_init(&fbatch); next = lstart >> PAGE_SHIFT; while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) { for (i = 0; i < folio_batch_count(&fbatch); ++i) { struct folio *folio = fbatch.folios[i]; u32 hash = 0; index = folio->index >> huge_page_order(h); hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Remove folio that was part of folio_batch. */ if (remove_inode_single_folio(h, inode, mapping, folio, index, truncate_op)) freed++; mutex_unlock(&hugetlb_fault_mutex_table[hash]); } folio_batch_release(&fbatch); cond_resched(); } if (truncate_op) (void)hugetlb_unreserve_pages(inode, lstart >> huge_page_shift(h), LONG_MAX, freed); } static void hugetlbfs_evict_inode(struct inode *inode) { struct resv_map *resv_map; remove_inode_hugepages(inode, 0, LLONG_MAX); /* * Get the resv_map from the address space embedded in the inode. * This is the address space which points to any resv_map allocated * at inode creation time. If this is a device special inode, * i_mapping may not point to the original address space. */ resv_map = (struct resv_map *)(&inode->i_data)->i_private_data; /* Only regular and link inodes have associated reserve maps */ if (resv_map) resv_map_release(&resv_map->refs); clear_inode(inode); } static void hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); BUG_ON(offset & ~huge_page_mask(h)); pgoff = offset >> PAGE_SHIFT; i_size_write(inode, offset); i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0, ZAP_FLAG_DROP_MARKER); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); } static void hugetlbfs_zero_partial_page(struct hstate *h, struct address_space *mapping, loff_t start, loff_t end) { pgoff_t idx = start >> huge_page_shift(h); struct folio *folio; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) return; start = start & ~huge_page_mask(h); end = end & ~huge_page_mask(h); if (!end) end = huge_page_size(h); folio_zero_segment(folio, (size_t)start, (size_t)end); folio_unlock(folio); folio_put(folio); } static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) { struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); loff_t hpage_size = huge_page_size(h); loff_t hole_start, hole_end; /* * hole_start and hole_end indicate the full pages within the hole. */ hole_start = round_up(offset, hpage_size); hole_end = round_down(offset + len, hpage_size); inode_lock(inode); /* protected by i_rwsem */ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } i_mmap_lock_write(mapping); /* If range starts before first full page, zero partial page. */ if (offset < hole_start) hugetlbfs_zero_partial_page(h, mapping, offset, min(offset + len, hole_start)); /* Unmap users of full pages in the hole. */ if (hole_end > hole_start) { if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT, 0); } /* If range extends beyond last full page, zero partial page. */ if ((offset + len) > hole_end && (offset + len) > hole_start) hugetlbfs_zero_partial_page(h, mapping, hole_end, offset + len); i_mmap_unlock_write(mapping); /* Remove full pages from the file. */ if (hole_end > hole_start) remove_inode_hugepages(inode, hole_start, hole_end); inode_unlock(inode); return 0; } static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); struct vm_area_struct pseudo_vma; struct mm_struct *mm = current->mm; loff_t hpage_size = huge_page_size(h); unsigned long hpage_shift = huge_page_shift(h); pgoff_t start, index, end; int error; u32 hash; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) return hugetlbfs_punch_hole(inode, offset, len); /* * Default preallocate case. * For this range, start is rounded down and end is rounded up * as well as being converted to page offsets. */ start = offset >> hpage_shift; end = (offset + len + hpage_size - 1) >> hpage_shift; inode_lock(inode); /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ error = inode_newsize_ok(inode, offset + len); if (error) goto out; if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { error = -EPERM; goto out; } /* * Initialize a pseudo vma as this is required by the huge page * allocation routines. */ vma_init(&pseudo_vma, mm); vm_flags_init(&pseudo_vma, VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; for (index = start; index < end; index++) { /* * This is supposed to be the vaddr where the page is being * faulted in, but we have no vaddr here. */ struct folio *folio; unsigned long addr; cond_resched(); /* * fallocate(2) manpage permits EINTR; we may have been * interrupted because we are using up too much memory. */ if (signal_pending(current)) { error = -EINTR; break; } /* addr is the offset within the file (zero based) */ addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ folio = filemap_get_folio(mapping, index << huge_page_order(h)); if (!IS_ERR(folio)) { folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); continue; } /* * Allocate folio without setting the avoid_reserve argument. * There certainly are no reserves associated with the * pseudo_vma. However, there could be shared mappings with * reserves for the file at the inode level. If we fallocate * folios in these areas, we need to consume the reserves * to keep reservation accounting consistent. */ folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0); if (IS_ERR(folio)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); error = PTR_ERR(folio); goto out; } clear_huge_page(&folio->page, addr, pages_per_huge_page(h)); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { restore_reserve_on_error(h, &pseudo_vma, addr, folio); folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; } mutex_unlock(&hugetlb_fault_mutex_table[hash]); folio_set_hugetlb_migratable(folio); /* * folio_unlock because locked by hugetlb_add_to_page_cache() * folio_put() due to reference from alloc_hugetlb_folio() */ folio_unlock(folio); folio_put(folio); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode_set_ctime_current(inode); out: inode_unlock(inode); return error; } static int hugetlbfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hstate *h = hstate_inode(inode); int error; unsigned int ia_valid = attr->ia_valid; struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); error = setattr_prepare(idmap, dentry, attr); if (error) return error; if (ia_valid & ATTR_SIZE) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; if (newsize & ~huge_page_mask(h)) return -EINVAL; /* protected by i_rwsem */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; hugetlb_vmtruncate(inode, newsize); } setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); return 0; } static struct inode *hugetlbfs_get_root(struct super_block *sb, struct hugetlbfs_fs_context *ctx) { struct inode *inode; inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = S_IFDIR | ctx->mode; inode->i_uid = ctx->uid; inode->i_gid = ctx->gid; simple_inode_init_ts(inode); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); lockdep_annotate_inode_mutex_key(inode); } return inode; } /* * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never * be taken from reclaim -- unlike regular filesystems. This needs an * annotation because huge_pmd_share() does an allocation under hugetlb's * i_mmap_rwsem. */ static struct lock_class_key hugetlbfs_i_mmap_rwsem_key; static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct mnt_idmap *idmap, struct inode *dir, umode_t mode, dev_t dev) { struct inode *inode; struct resv_map *resv_map = NULL; /* * Reserve maps are only needed for inodes that can have associated * page allocations. */ if (S_ISREG(mode) || S_ISLNK(mode)) { resv_map = resv_map_alloc(); if (!resv_map) return NULL; } inode = new_inode(sb); if (inode) { struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); inode->i_ino = get_next_ino(); inode_init_owner(idmap, inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; simple_inode_init_ts(inode); inode->i_mapping->i_private_data = resv_map; info->seals = F_SEAL_SEAL; switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_op = &hugetlbfs_inode_operations; inode->i_fop = &hugetlbfs_file_operations; break; case S_IFDIR: inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); break; } lockdep_annotate_inode_mutex_key(inode); } else { if (resv_map) kref_put(&resv_map->refs, resv_map_release); } return inode; } /* * File creation. Allocate an inode, and we're done.. */ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_instantiate(dentry, inode); dget(dentry);/* Extra count - pin the dentry in core */ return 0; } static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int retval = hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } static int hugetlbfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_tmpfile(file, inode); return finish_open_simple(file, 0); } static int hugetlbfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { const umode_t mode = S_IFLNK|S_IRWXUGO; struct inode *inode; int error = -ENOSPC; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0); if (inode) { int l = strlen(symname)+1; error = page_symlink(inode, symname, l); if (!error) { d_instantiate(dentry, inode); dget(dentry); } else iput(inode); } inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return error; } #ifdef CONFIG_MIGRATION static int hugetlbfs_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { int rc; rc = migrate_huge_page_move_mapping(mapping, dst, src); if (rc != MIGRATEPAGE_SUCCESS) return rc; if (hugetlb_folio_subpool(src)) { hugetlb_set_folio_subpool(dst, hugetlb_folio_subpool(src)); hugetlb_set_folio_subpool(src, NULL); } if (mode != MIGRATE_SYNC_NO_COPY) folio_migrate_copy(dst, src); else folio_migrate_flags(dst, src); return MIGRATEPAGE_SUCCESS; } #else #define hugetlbfs_migrate_folio NULL #endif static int hugetlbfs_error_remove_folio(struct address_space *mapping, struct folio *folio) { return 0; } /* * Display the mount options in /proc/mounts. */ static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); struct hugepage_subpool *spool = sbinfo->spool; unsigned long hpage_size = huge_page_size(sbinfo->hstate); unsigned hpage_shift = huge_page_shift(sbinfo->hstate); char mod; if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, sbinfo->uid)); if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); if (sbinfo->mode != 0755) seq_printf(m, ",mode=%o", sbinfo->mode); if (sbinfo->max_inodes != -1) seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); hpage_size /= 1024; mod = 'K'; if (hpage_size >= 1024) { hpage_size /= 1024; mod = 'M'; } seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); if (spool) { if (spool->max_hpages != -1) seq_printf(m, ",size=%llu", (unsigned long long)spool->max_hpages << hpage_shift); if (spool->min_hpages != -1) seq_printf(m, ",min_size=%llu", (unsigned long long)spool->min_hpages << hpage_shift); } return 0; } static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); struct hstate *h = hstate_inode(d_inode(dentry)); u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = HUGETLBFS_MAGIC; buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); /* If no limits set, just report 0 or -1 for max/free/used * blocks, like simple_statfs() */ if (sbinfo->spool) { long free_pages; spin_lock_irq(&sbinfo->spool->lock); buf->f_blocks = sbinfo->spool->max_hpages; free_pages = sbinfo->spool->max_hpages - sbinfo->spool->used_hpages; buf->f_bavail = buf->f_bfree = free_pages; spin_unlock_irq(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } spin_unlock(&sbinfo->stat_lock); } buf->f_namelen = NAME_MAX; return 0; } static void hugetlbfs_put_super(struct super_block *sb) { struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb); if (sbi) { sb->s_fs_info = NULL; if (sbi->spool) hugepage_put_subpool(sbi->spool); kfree(sbi); } } static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo) { if (sbinfo->free_inodes >= 0) { spin_lock(&sbinfo->stat_lock); if (unlikely(!sbinfo->free_inodes)) { spin_unlock(&sbinfo->stat_lock); return 0; } sbinfo->free_inodes--; spin_unlock(&sbinfo->stat_lock); } return 1; } static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo) { if (sbinfo->free_inodes >= 0) { spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } static struct kmem_cache *hugetlbfs_inode_cachep; static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb); struct hugetlbfs_inode_info *p; if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo))) return NULL; p = alloc_inode_sb(sb, hugetlbfs_inode_cachep, GFP_KERNEL); if (unlikely(!p)) { hugetlbfs_inc_free_inodes(sbinfo); return NULL; } return &p->vfs_inode; } static void hugetlbfs_free_inode(struct inode *inode) { kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode)); } static void hugetlbfs_destroy_inode(struct inode *inode) { hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb)); } static const struct address_space_operations hugetlbfs_aops = { .write_begin = hugetlbfs_write_begin, .write_end = hugetlbfs_write_end, .dirty_folio = noop_dirty_folio, .migrate_folio = hugetlbfs_migrate_folio, .error_remove_folio = hugetlbfs_error_remove_folio, }; static void init_once(void *foo) { struct hugetlbfs_inode_info *ei = foo; inode_init_once(&ei->vfs_inode); } static const struct file_operations hugetlbfs_file_operations = { .read_iter = hugetlbfs_read_iter, .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, .llseek = default_llseek, .fallocate = hugetlbfs_fallocate, .fop_flags = FOP_HUGE_PAGES, }; static const struct inode_operations hugetlbfs_dir_inode_operations = { .create = hugetlbfs_create, .lookup = simple_lookup, .link = simple_link, .unlink = simple_unlink, .symlink = hugetlbfs_symlink, .mkdir = hugetlbfs_mkdir, .rmdir = simple_rmdir, .mknod = hugetlbfs_mknod, .rename = simple_rename, .setattr = hugetlbfs_setattr, .tmpfile = hugetlbfs_tmpfile, }; static const struct inode_operations hugetlbfs_inode_operations = { .setattr = hugetlbfs_setattr, }; static const struct super_operations hugetlbfs_ops = { .alloc_inode = hugetlbfs_alloc_inode, .free_inode = hugetlbfs_free_inode, .destroy_inode = hugetlbfs_destroy_inode, .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, .show_options = hugetlbfs_show_options, }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; if (val_type == SIZE_PERCENT) { size_opt <<= huge_page_shift(h); size_opt *= h->max_huge_pages; do_div(size_opt, 100); } size_opt >>= huge_page_shift(h); return size_opt; } /* * Parse one mount parameter. */ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; struct hstate *h; char *rest; unsigned long ps; int opt; opt = fs_parse(fc, hugetlb_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: ctx->uid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(ctx->uid)) goto bad_val; return 0; case Opt_gid: ctx->gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(ctx->gid)) goto bad_val; return 0; case Opt_mode: ctx->mode = result.uint_32 & 01777U; return 0; case Opt_size: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->max_size_opt = memparse(param->string, &rest); ctx->max_val_type = SIZE_STD; if (*rest == '%') ctx->max_val_type = SIZE_PERCENT; return 0; case Opt_nr_inodes: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->nr_inodes = memparse(param->string, &rest); return 0; case Opt_pagesize: ps = memparse(param->string, &rest); h = size_to_hstate(ps); if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } ctx->hstate = h; return 0; case Opt_min_size: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->min_size_opt = memparse(param->string, &rest); ctx->min_val_type = SIZE_STD; if (*rest == '%') ctx->min_val_type = SIZE_PERCENT; return 0; default: return -EINVAL; } bad_val: return invalfc(fc, "Bad value '%s' for mount option '%s'\n", param->string, param->key); } /* * Validate the parsed options. */ static int hugetlbfs_validate(struct fs_context *fc) { struct hugetlbfs_fs_context *ctx = fc->fs_private; /* * Use huge page pool size (in hstate) to convert the size * options to number of huge pages. If NO_SIZE, -1 is returned. */ ctx->max_hpages = hugetlbfs_size_to_hpages(ctx->hstate, ctx->max_size_opt, ctx->max_val_type); ctx->min_hpages = hugetlbfs_size_to_hpages(ctx->hstate, ctx->min_size_opt, ctx->min_val_type); /* * If max_size was specified, then min_size must be smaller */ if (ctx->max_val_type > NO_SIZE && ctx->min_hpages > ctx->max_hpages) { pr_err("Minimum size can not be greater than maximum size\n"); return -EINVAL; } return 0; } static int hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct hugetlbfs_sb_info *sbinfo; sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL); if (!sbinfo) return -ENOMEM; sb->s_fs_info = sbinfo; spin_lock_init(&sbinfo->stat_lock); sbinfo->hstate = ctx->hstate; sbinfo->max_inodes = ctx->nr_inodes; sbinfo->free_inodes = ctx->nr_inodes; sbinfo->spool = NULL; sbinfo->uid = ctx->uid; sbinfo->gid = ctx->gid; sbinfo->mode = ctx->mode; /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimum size) are taken * when the subpool is created. */ if (ctx->max_hpages != -1 || ctx->min_hpages != -1) { sbinfo->spool = hugepage_new_subpool(ctx->hstate, ctx->max_hpages, ctx->min_hpages); if (!sbinfo->spool) goto out_free; } sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = huge_page_size(ctx->hstate); sb->s_blocksize_bits = huge_page_shift(ctx->hstate); sb->s_magic = HUGETLBFS_MAGIC; sb->s_op = &hugetlbfs_ops; sb->s_time_gran = 1; /* * Due to the special and limited functionality of hugetlbfs, it does * not work well as a stacking filesystem. */ sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx)); if (!sb->s_root) goto out_free; return 0; out_free: kfree(sbinfo->spool); kfree(sbinfo); return -ENOMEM; } static int hugetlbfs_get_tree(struct fs_context *fc) { int err = hugetlbfs_validate(fc); if (err) return err; return get_tree_nodev(fc, hugetlbfs_fill_super); } static void hugetlbfs_fs_context_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations hugetlbfs_fs_context_ops = { .free = hugetlbfs_fs_context_free, .parse_param = hugetlbfs_parse_param, .get_tree = hugetlbfs_get_tree, }; static int hugetlbfs_init_fs_context(struct fs_context *fc) { struct hugetlbfs_fs_context *ctx; ctx = kzalloc(sizeof(struct hugetlbfs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->max_hpages = -1; /* No limit on size by default */ ctx->nr_inodes = -1; /* No limit on number of inodes by default */ ctx->uid = current_fsuid(); ctx->gid = current_fsgid(); ctx->mode = 0755; ctx->hstate = &default_hstate; ctx->min_hpages = -1; /* No default minimum size */ ctx->max_val_type = NO_SIZE; ctx->min_val_type = NO_SIZE; fc->fs_private = ctx; fc->ops = &hugetlbfs_fs_context_ops; return 0; } static struct file_system_type hugetlbfs_fs_type = { .name = "hugetlbfs", .init_fs_context = hugetlbfs_init_fs_context, .parameters = hugetlb_fs_parameters, .kill_sb = kill_litter_super, .fs_flags = FS_ALLOW_IDMAP, }; static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE]; static int can_do_hugetlb_shm(void) { kgid_t shm_group; shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group); return capable(CAP_IPC_LOCK) || in_group_p(shm_group); } static int get_hstate_idx(int page_size_log) { struct hstate *h = hstate_sizelog(page_size_log); if (!h) return -1; return hstate_index(h); } /* * Note that size should be aligned to proper hugepage size in caller side, * otherwise hugetlb_reserve_pages reserves one less hugepages than intended. */ struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { struct inode *inode; struct vfsmount *mnt; int hstate_idx; struct file *file; hstate_idx = get_hstate_idx(page_size_log); if (hstate_idx < 0) return ERR_PTR(-ENODEV); mnt = hugetlbfs_vfsmount[hstate_idx]; if (!mnt) return ERR_PTR(-ENOENT); if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) { struct ucounts *ucounts = current_ucounts(); if (user_shm_lock(size, ucounts)) { pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n", current->comm, current->pid); user_shm_unlock(size, ucounts); } return ERR_PTR(-EPERM); } file = ERR_PTR(-ENOSPC); /* hugetlbfs_vfsmount[] mounts do not use idmapped mounts. */ inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL, S_IFREG | S_IRWXUGO, 0); if (!inode) goto out; if (creat_flags == HUGETLB_SHMFS_INODE) inode->i_flags |= S_PRIVATE; inode->i_size = size; clear_nlink(inode); if (!hugetlb_reserve_pages(inode, 0, size >> huge_page_shift(hstate_inode(inode)), NULL, acctflag)) file = ERR_PTR(-ENOMEM); else file = alloc_file_pseudo(inode, mnt, name, O_RDWR, &hugetlbfs_file_operations); if (!IS_ERR(file)) return file; iput(inode); out: return file; } static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h) { struct fs_context *fc; struct vfsmount *mnt; fc = fs_context_for_mount(&hugetlbfs_fs_type, SB_KERNMOUNT); if (IS_ERR(fc)) { mnt = ERR_CAST(fc); } else { struct hugetlbfs_fs_context *ctx = fc->fs_private; ctx->hstate = h; mnt = fc_mount(fc); put_fs_context(fc); } if (IS_ERR(mnt)) pr_err("Cannot mount internal hugetlbfs for page size %luK", huge_page_size(h) / SZ_1K); return mnt; } static int __init init_hugetlbfs_fs(void) { struct vfsmount *mnt; struct hstate *h; int error; int i; if (!hugepages_supported()) { pr_info("disabling because there are no supported hugepage sizes\n"); return -ENOTSUPP; } error = -ENOMEM; hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), 0, SLAB_ACCOUNT, init_once); if (hugetlbfs_inode_cachep == NULL) goto out; error = register_filesystem(&hugetlbfs_fs_type); if (error) goto out_free; /* default hstate mount is required */ mnt = mount_one_hugetlbfs(&default_hstate); if (IS_ERR(mnt)) { error = PTR_ERR(mnt); goto out_unreg; } hugetlbfs_vfsmount[default_hstate_idx] = mnt; /* other hstates are optional */ i = 0; for_each_hstate(h) { if (i == default_hstate_idx) { i++; continue; } mnt = mount_one_hugetlbfs(h); if (IS_ERR(mnt)) hugetlbfs_vfsmount[i] = NULL; else hugetlbfs_vfsmount[i] = mnt; i++; } return 0; out_unreg: (void)unregister_filesystem(&hugetlbfs_fs_type); out_free: kmem_cache_destroy(hugetlbfs_inode_cachep); out: return error; } fs_initcall(init_hugetlbfs_fs) |
| 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 | // SPDX-License-Identifier: GPL-2.0-or-later /* * linux/drivers/net/netconsole.c * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * * This file contains the implementation of an IRQ-safe, crash-safe * kernel console implementation that outputs kernel messages to the * network. * * Modification history: * * 2001-09-17 started by Ingo Molnar. * 2003-08-11 2.6 port by Matt Mackall * simplified options * generic card hooks * works non-modular * 2003-09-07 rewritten with netpoll api */ /**************************************************************** * ****************************************************************/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/console.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/netpoll.h> #include <linux/inet.h> #include <linux/configfs.h> #include <linux/etherdevice.h> #include <linux/utsname.h> MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); #define MAX_PARAM_LENGTH 256 #define MAX_USERDATA_ENTRY_LENGTH 256 #define MAX_USERDATA_VALUE_LENGTH 200 /* The number 3 comes from userdata entry format characters (' ', '=', '\n') */ #define MAX_USERDATA_NAME_LENGTH (MAX_USERDATA_ENTRY_LENGTH - \ MAX_USERDATA_VALUE_LENGTH - 3) #define MAX_USERDATA_ITEMS 16 #define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0); MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]"); static bool oops_only; module_param(oops_only, bool, 0600); MODULE_PARM_DESC(oops_only, "Only log oops messages"); #define NETCONSOLE_PARAM_TARGET_PREFIX "cmdline" #ifndef MODULE static int __init option_setup(char *opt) { strscpy(config, opt, MAX_PARAM_LENGTH); return 1; } __setup("netconsole=", option_setup); #endif /* MODULE */ /* Linked list of all configured targets */ static LIST_HEAD(target_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to * avoid unnecessarily enabling ext message formatting. */ static struct console netconsole_ext; /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. * @group: Links us into the configfs subsystem hierarchy. * @userdata_group: Links to the userdata configfs hierarchy * @userdata_complete: Cached, formatted string of append * @userdata_length: String length of userdata_complete * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). * We maintain a strict 1:1 correspondence between this and * whether the corresponding netpoll is active or inactive. * Also, other parameters of a target may be modified at * runtime only when it is disabled (enabled == 0). * @extended: Denotes whether console is extended or not. * @release: Denotes whether kernel release version should be prepended * to the message. Depends on extended console. * @np: The netpoll structure for this target. * Contains the other userspace visible parameters: * dev_name (read-write) * local_port (read-write) * remote_port (read-write) * local_ip (read-write) * remote_ip (read-write) * local_mac (read-only) * remote_mac (read-write) */ struct netconsole_target { struct list_head list; #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_group group; struct config_group userdata_group; char userdata_complete[MAX_USERDATA_ENTRY_LENGTH * MAX_USERDATA_ITEMS]; size_t userdata_length; #endif bool enabled; bool extended; bool release; struct netpoll np; }; #ifdef CONFIG_NETCONSOLE_DYNAMIC static struct configfs_subsystem netconsole_subsys; static DEFINE_MUTEX(dynamic_netconsole_mutex); static int __init dynamic_netconsole_init(void) { config_group_init(&netconsole_subsys.su_group); mutex_init(&netconsole_subsys.su_mutex); return configfs_register_subsystem(&netconsole_subsys); } static void __exit dynamic_netconsole_exit(void) { configfs_unregister_subsystem(&netconsole_subsys); } /* * Targets that were created by parsing the boot/module option string * do not exist in the configfs hierarchy (and have NULL names) and will * never go away, so make these a no-op for them. */ static void netconsole_target_get(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_get(&nt->group); } static void netconsole_target_put(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_put(&nt->group); } #else /* !CONFIG_NETCONSOLE_DYNAMIC */ static int __init dynamic_netconsole_init(void) { return 0; } static void __exit dynamic_netconsole_exit(void) { } /* * No danger of targets going away from under us when dynamic * reconfigurability is off. */ static void netconsole_target_get(struct netconsole_target *nt) { } static void netconsole_target_put(struct netconsole_target *nt) { } static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Allocate and initialize with defaults. * Note that these targets get their config_item fields zeroed-out. */ static struct netconsole_target *alloc_and_init(void) { struct netconsole_target *nt; nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return nt; if (IS_ENABLED(CONFIG_NETCONSOLE_EXTENDED_LOG)) nt->extended = true; if (IS_ENABLED(CONFIG_NETCONSOLE_PREPEND_RELEASE)) nt->release = true; nt->np.name = "netconsole"; strscpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; eth_broadcast_addr(nt->np.remote_mac); return nt; } #ifdef CONFIG_NETCONSOLE_DYNAMIC /* * Our subsystem hierarchy is: * * /sys/kernel/config/netconsole/ * | * <target>/ * | enabled * | release * | dev_name * | local_port * | remote_port * | local_ip * | remote_ip * | local_mac * | remote_mac * | userdata/ * | <key>/ * | value * | ... * | * <target>/... */ static struct netconsole_target *to_target(struct config_item *item) { struct config_group *cfg_group; cfg_group = to_config_group(item); if (!cfg_group) return NULL; return container_of(to_config_group(item), struct netconsole_target, group); } /* Get rid of possible trailing newline, returning the new length */ static void trim_newline(char *s, size_t maxlen) { size_t len; len = strnlen(s, maxlen); if (s[len - 1] == '\n') s[len - 1] = '\0'; } /* * Attribute operations for netconsole_target. */ static ssize_t enabled_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->enabled); } static ssize_t extended_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->extended); } static ssize_t release_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->release); } static ssize_t dev_name_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", to_target(item)->np.dev_name); } static ssize_t local_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.local_port); } static ssize_t remote_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.remote_port); } static ssize_t local_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return sysfs_emit(buf, "%pI6c\n", &nt->np.local_ip.in6); else return sysfs_emit(buf, "%pI4\n", &nt->np.local_ip); } static ssize_t remote_ip_show(struct config_item *item, char *buf) { struct netconsole_target *nt = to_target(item); if (nt->np.ipv6) return sysfs_emit(buf, "%pI6c\n", &nt->np.remote_ip.in6); else return sysfs_emit(buf, "%pI4\n", &nt->np.remote_ip); } static ssize_t local_mac_show(struct config_item *item, char *buf) { struct net_device *dev = to_target(item)->np.dev; static const u8 bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; return sysfs_emit(buf, "%pM\n", dev ? dev->dev_addr : bcast); } static ssize_t remote_mac_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%pM\n", to_target(item)->np.remote_mac); } /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. * The user is expected to set the desired parameters first (which * would enable him to dynamically add new netpoll targets for new * network interfaces as and when they come up). */ static ssize_t enabled_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); unsigned long flags; bool enabled; int err; mutex_lock(&dynamic_netconsole_mutex); err = kstrtobool(buf, &enabled); if (err) goto out_unlock; err = -EINVAL; if ((bool)enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); goto out_unlock; } if (enabled) { /* true */ if (nt->release && !nt->extended) { pr_err("Not enabling netconsole. Release feature requires extended log message"); goto out_unlock; } if (nt->extended && !console_is_registered(&netconsole_ext)) register_console(&netconsole_ext); /* * Skip netpoll_parse_options() -- all the attributes are * already configured via configfs. Just print them out. */ netpoll_print_options(&nt->np); err = netpoll_setup(&nt->np); if (err) goto out_unlock; pr_info("network logging started\n"); } else { /* false */ /* We need to disable the netconsole before cleaning it up * otherwise we might end up in write_msg() with * nt->np.dev == NULL and nt->enabled == true */ spin_lock_irqsave(&target_list_lock, flags); nt->enabled = false; spin_unlock_irqrestore(&target_list_lock, flags); netpoll_cleanup(&nt->np); } nt->enabled = enabled; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return err; } static ssize_t release_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); bool release; int err; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); err = -EINVAL; goto out_unlock; } err = kstrtobool(buf, &release); if (err) goto out_unlock; nt->release = release; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return err; } static ssize_t extended_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); bool extended; int err; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); err = -EINVAL; goto out_unlock; } err = kstrtobool(buf, &extended); if (err) goto out_unlock; nt->extended = extended; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return err; } static ssize_t dev_name_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } strscpy(nt->np.dev_name, buf, IFNAMSIZ); trim_newline(nt->np.dev_name, IFNAMSIZ); mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); } static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); int rv = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } rv = kstrtou16(buf, 10, &nt->np.local_port); if (rv < 0) goto out_unlock; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return rv; } static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); int rv = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } rv = kstrtou16(buf, 10, &nt->np.remote_port); if (rv < 0) goto out_unlock; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return rv; } static ssize_t local_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.local_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) nt->np.local_ip.ip = in_aton(buf); else goto out_unlock; } mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } static ssize_t remote_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (strnchr(buf, count, ':')) { const char *end; if (in6_pton(buf, count, nt->np.remote_ip.in6.s6_addr, -1, &end) > 0) { if (*end && *end != '\n') { pr_err("invalid IPv6 address at: <%c>\n", *end); goto out_unlock; } nt->np.ipv6 = true; } else goto out_unlock; } else { if (!nt->np.ipv6) nt->np.remote_ip.ip = in_aton(buf); else goto out_unlock; } mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); u8 remote_mac[ETH_ALEN]; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); goto out_unlock; } if (!mac_pton(buf, remote_mac)) goto out_unlock; if (buf[3 * ETH_ALEN - 1] && buf[3 * ETH_ALEN - 1] != '\n') goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return -EINVAL; } struct userdatum { struct config_item item; char value[MAX_USERDATA_VALUE_LENGTH]; }; static struct userdatum *to_userdatum(struct config_item *item) { return container_of(item, struct userdatum, item); } struct userdata { struct config_group group; }; static struct userdata *to_userdata(struct config_item *item) { return container_of(to_config_group(item), struct userdata, group); } static struct netconsole_target *userdata_to_target(struct userdata *ud) { struct config_group *netconsole_group; netconsole_group = to_config_group(ud->group.cg_item.ci_parent); return to_target(&netconsole_group->cg_item); } static ssize_t userdatum_value_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", &(to_userdatum(item)->value[0])); } static void update_userdata(struct netconsole_target *nt) { int complete_idx = 0, child_count = 0; struct list_head *entry; /* Clear the current string in case the last userdatum was deleted */ nt->userdata_length = 0; nt->userdata_complete[0] = 0; list_for_each(entry, &nt->userdata_group.cg_children) { struct userdatum *udm_item; struct config_item *item; if (child_count >= MAX_USERDATA_ITEMS) break; child_count++; item = container_of(entry, struct config_item, ci_entry); udm_item = to_userdatum(item); /* Skip userdata with no value set */ if (strnlen(udm_item->value, MAX_USERDATA_VALUE_LENGTH) == 0) continue; /* This doesn't overflow userdata_complete since it will write * one entry length (1/MAX_USERDATA_ITEMS long), entry count is * checked to not exceed MAX items with child_count above */ complete_idx += scnprintf(&nt->userdata_complete[complete_idx], MAX_USERDATA_ENTRY_LENGTH, " %s=%s\n", item->ci_name, udm_item->value); } nt->userdata_length = strnlen(nt->userdata_complete, sizeof(nt->userdata_complete)); } static ssize_t userdatum_value_store(struct config_item *item, const char *buf, size_t count) { struct userdatum *udm = to_userdatum(item); struct netconsole_target *nt; struct userdata *ud; int ret; if (count > MAX_USERDATA_VALUE_LENGTH) return -EMSGSIZE; mutex_lock(&dynamic_netconsole_mutex); ret = strscpy(udm->value, buf, sizeof(udm->value)); if (ret < 0) goto out_unlock; trim_newline(udm->value, sizeof(udm->value)); ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); update_userdata(nt); mutex_unlock(&dynamic_netconsole_mutex); return count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; } CONFIGFS_ATTR(userdatum_, value); static struct configfs_attribute *userdatum_attrs[] = { &userdatum_attr_value, NULL, }; static void userdatum_release(struct config_item *item) { kfree(to_userdatum(item)); } static struct configfs_item_operations userdatum_ops = { .release = userdatum_release, }; static const struct config_item_type userdatum_type = { .ct_item_ops = &userdatum_ops, .ct_attrs = userdatum_attrs, .ct_owner = THIS_MODULE, }; static struct config_item *userdatum_make_item(struct config_group *group, const char *name) { struct netconsole_target *nt; struct userdatum *udm; struct userdata *ud; size_t child_count; if (strlen(name) > MAX_USERDATA_NAME_LENGTH) return ERR_PTR(-ENAMETOOLONG); ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); child_count = list_count_nodes(&nt->userdata_group.cg_children); if (child_count >= MAX_USERDATA_ITEMS) return ERR_PTR(-ENOSPC); udm = kzalloc(sizeof(*udm), GFP_KERNEL); if (!udm) return ERR_PTR(-ENOMEM); config_item_init_type_name(&udm->item, name, &userdatum_type); return &udm->item; } static void userdatum_drop(struct config_group *group, struct config_item *item) { struct netconsole_target *nt; struct userdata *ud; ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); mutex_lock(&dynamic_netconsole_mutex); update_userdata(nt); config_item_put(item); mutex_unlock(&dynamic_netconsole_mutex); } static struct configfs_attribute *userdata_attrs[] = { NULL, }; static struct configfs_group_operations userdata_ops = { .make_item = userdatum_make_item, .drop_item = userdatum_drop, }; static struct config_item_type userdata_type = { .ct_item_ops = &userdatum_ops, .ct_group_ops = &userdata_ops, .ct_attrs = userdata_attrs, .ct_owner = THIS_MODULE, }; CONFIGFS_ATTR(, enabled); CONFIGFS_ATTR(, extended); CONFIGFS_ATTR(, dev_name); CONFIGFS_ATTR(, local_port); CONFIGFS_ATTR(, remote_port); CONFIGFS_ATTR(, local_ip); CONFIGFS_ATTR(, remote_ip); CONFIGFS_ATTR_RO(, local_mac); CONFIGFS_ATTR(, remote_mac); CONFIGFS_ATTR(, release); static struct configfs_attribute *netconsole_target_attrs[] = { &attr_enabled, &attr_extended, &attr_release, &attr_dev_name, &attr_local_port, &attr_remote_port, &attr_local_ip, &attr_remote_ip, &attr_local_mac, &attr_remote_mac, NULL, }; /* * Item operations and type for netconsole_target. */ static void netconsole_target_release(struct config_item *item) { kfree(to_target(item)); } static struct configfs_item_operations netconsole_target_item_ops = { .release = netconsole_target_release, }; static const struct config_item_type netconsole_target_type = { .ct_attrs = netconsole_target_attrs, .ct_item_ops = &netconsole_target_item_ops, .ct_owner = THIS_MODULE, }; static void init_target_config_group(struct netconsole_target *nt, const char *name) { config_group_init_type_name(&nt->group, name, &netconsole_target_type); config_group_init_type_name(&nt->userdata_group, "userdata", &userdata_type); configfs_add_default_group(&nt->userdata_group, &nt->group); } static struct netconsole_target *find_cmdline_target(const char *name) { struct netconsole_target *nt, *ret = NULL; unsigned long flags; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!strcmp(nt->group.cg_item.ci_name, name)) { ret = nt; break; } } spin_unlock_irqrestore(&target_list_lock, flags); return ret; } /* * Group operations and type for netconsole_subsys. */ static struct config_group *make_netconsole_target(struct config_group *group, const char *name) { struct netconsole_target *nt; unsigned long flags; /* Checking if a target by this name was created at boot time. If so, * attach a configfs entry to that target. This enables dynamic * control. */ if (!strncmp(name, NETCONSOLE_PARAM_TARGET_PREFIX, strlen(NETCONSOLE_PARAM_TARGET_PREFIX))) { nt = find_cmdline_target(name); if (nt) { init_target_config_group(nt, name); return &nt->group; } } nt = alloc_and_init(); if (!nt) return ERR_PTR(-ENOMEM); /* Initialize the config_group member */ init_target_config_group(nt, name); /* Adding, but it is disabled */ spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); return &nt->group; } static void drop_netconsole_target(struct config_group *group, struct config_item *item) { unsigned long flags; struct netconsole_target *nt = to_target(item); spin_lock_irqsave(&target_list_lock, flags); list_del(&nt->list); spin_unlock_irqrestore(&target_list_lock, flags); /* * The target may have never been enabled, or was manually disabled * before being removed so netpoll may have already been cleaned up. */ if (nt->enabled) netpoll_cleanup(&nt->np); config_item_put(&nt->group.cg_item); } static struct configfs_group_operations netconsole_subsys_group_ops = { .make_group = make_netconsole_target, .drop_item = drop_netconsole_target, }; static const struct config_item_type netconsole_subsys_type = { .ct_group_ops = &netconsole_subsys_group_ops, .ct_owner = THIS_MODULE, }; /* The netconsole configfs subsystem */ static struct configfs_subsystem netconsole_subsys = { .su_group = { .cg_item = { .ci_namebuf = "netconsole", .ci_type = &netconsole_subsys_type, }, }, }; static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { char target_name[16]; snprintf(target_name, sizeof(target_name), "%s%d", NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); init_target_config_group(nt, target_name); } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Handle network interface device notifications */ static int netconsole_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { unsigned long flags; struct netconsole_target *nt; struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; if (!(event == NETDEV_CHANGENAME || event == NETDEV_UNREGISTER || event == NETDEV_RELEASE || event == NETDEV_JOIN)) goto done; spin_lock_irqsave(&target_list_lock, flags); restart: list_for_each_entry(nt, &target_list, list) { netconsole_target_get(nt); if (nt->np.dev == dev) { switch (event) { case NETDEV_CHANGENAME: strscpy(nt->np.dev_name, dev->name, IFNAMSIZ); break; case NETDEV_RELEASE: case NETDEV_JOIN: case NETDEV_UNREGISTER: /* rtnl_lock already held * we might sleep in __netpoll_cleanup() */ spin_unlock_irqrestore(&target_list_lock, flags); __netpoll_cleanup(&nt->np); spin_lock_irqsave(&target_list_lock, flags); netdev_put(nt->np.dev, &nt->np.dev_tracker); nt->np.dev = NULL; nt->enabled = false; stopped = true; netconsole_target_put(nt); goto restart; } } netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); if (stopped) { const char *msg = "had an event"; switch (event) { case NETDEV_UNREGISTER: msg = "unregistered"; break; case NETDEV_RELEASE: msg = "released slaves"; break; case NETDEV_JOIN: msg = "is joining a master device"; break; } pr_info("network logging stopped on interface %s as it %s\n", dev->name, msg); } done: return NOTIFY_DONE; } static struct notifier_block netconsole_netdev_notifier = { .notifier_call = netconsole_netdev_event, }; /** * send_ext_msg_udp - send extended log message to target * @nt: target to send message to * @msg: extended log message to send * @msg_len: length of message * * Transfer extended log @msg to @nt. If @msg is longer than * MAX_PRINT_CHUNK, it'll be split and transmitted in multiple chunks with * ncfrag header field added to identify them. */ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, int msg_len) { static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */ const char *header, *body; int offset = 0; int header_len, body_len; const char *msg_ready = msg; const char *release; int release_len = 0; int userdata_len = 0; char *userdata = NULL; #ifdef CONFIG_NETCONSOLE_DYNAMIC userdata = nt->userdata_complete; userdata_len = nt->userdata_length; #endif if (nt->release) { release = init_utsname()->release; release_len = strlen(release) + 1; } if (msg_len + release_len + userdata_len <= MAX_PRINT_CHUNK) { /* No fragmentation needed */ if (nt->release) { scnprintf(buf, MAX_PRINT_CHUNK, "%s,%s", release, msg); msg_len += release_len; } else { memcpy(buf, msg, msg_len); } if (userdata) msg_len += scnprintf(&buf[msg_len], MAX_PRINT_CHUNK - msg_len, "%s", userdata); msg_ready = buf; netpoll_send_udp(&nt->np, msg_ready, msg_len); return; } /* need to insert extra header fields, detect header and body */ header = msg; body = memchr(msg, ';', msg_len); if (WARN_ON_ONCE(!body)) return; header_len = body - header; body_len = msg_len - header_len - 1; body++; /* * Transfer multiple chunks with the following extra header. * "ncfrag=<byte-offset>/<total-bytes>" */ if (nt->release) scnprintf(buf, MAX_PRINT_CHUNK, "%s,", release); memcpy(buf + release_len, header, header_len); header_len += release_len; while (offset < body_len + userdata_len) { int this_header = header_len; int this_offset = 0; int this_chunk = 0; this_header += scnprintf(buf + this_header, sizeof(buf) - this_header, ",ncfrag=%d/%d;", offset, body_len + userdata_len); /* Not all body data has been written yet */ if (offset < body_len) { this_chunk = min(body_len - offset, MAX_PRINT_CHUNK - this_header); if (WARN_ON_ONCE(this_chunk <= 0)) return; memcpy(buf + this_header, body + offset, this_chunk); this_offset += this_chunk; } /* Body is fully written and there is pending userdata to write, * append userdata in this chunk */ if (offset + this_offset >= body_len && offset + this_offset < userdata_len + body_len) { int sent_userdata = (offset + this_offset) - body_len; int preceding_bytes = this_chunk + this_header; if (WARN_ON_ONCE(sent_userdata < 0)) return; this_chunk = min(userdata_len - sent_userdata, MAX_PRINT_CHUNK - preceding_bytes); if (WARN_ON_ONCE(this_chunk <= 0)) return; memcpy(buf + this_header + this_offset, userdata + sent_userdata, this_chunk); this_offset += this_chunk; } netpoll_send_udp(&nt->np, buf, this_header + this_offset); offset += this_offset; } } static void write_ext_msg(struct console *con, const char *msg, unsigned int len) { struct netconsole_target *nt; unsigned long flags; if ((oops_only && !oops_in_progress) || list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) if (nt->extended && nt->enabled && netif_running(nt->np.dev)) send_ext_msg_udp(nt, msg, len); spin_unlock_irqrestore(&target_list_lock, flags); } static void write_msg(struct console *con, const char *msg, unsigned int len) { int frag, left; unsigned long flags; struct netconsole_target *nt; const char *tmp; if (oops_only && !oops_in_progress) return; /* Avoid taking lock and disabling interrupts unnecessarily */ if (list_empty(&target_list)) return; spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { if (!nt->extended && nt->enabled && netif_running(nt->np.dev)) { /* * We nest this inside the for-each-target loop above * so that we're able to get as much logging out to * at least one target if we die inside here, instead * of unnecessarily keeping all targets in lock-step. */ tmp = msg; for (left = len; left;) { frag = min(left, MAX_PRINT_CHUNK); netpoll_send_udp(&nt->np, tmp, frag); tmp += frag; left -= frag; } } } spin_unlock_irqrestore(&target_list_lock, flags); } /* Allocate new target (from boot/module param) and setup netpoll for it */ static struct netconsole_target *alloc_param_target(char *target_config, int cmdline_count) { struct netconsole_target *nt; int err; nt = alloc_and_init(); if (!nt) { err = -ENOMEM; goto fail; } if (*target_config == '+') { nt->extended = true; target_config++; } if (*target_config == 'r') { if (!nt->extended) { pr_err("Netconsole configuration error. Release feature requires extended log message"); err = -EINVAL; goto fail; } nt->release = true; target_config++; } /* Parse parameters and setup netpoll */ err = netpoll_parse_options(&nt->np, target_config); if (err) goto fail; err = netpoll_setup(&nt->np); if (err) goto fail; populate_configfs_item(nt, cmdline_count); nt->enabled = true; return nt; fail: kfree(nt); return ERR_PTR(err); } /* Cleanup netpoll for given target (from boot/module param) and free it */ static void free_param_target(struct netconsole_target *nt) { netpoll_cleanup(&nt->np); kfree(nt); } static struct console netconsole_ext = { .name = "netcon_ext", .flags = CON_ENABLED | CON_EXTENDED, .write = write_ext_msg, }; static struct console netconsole = { .name = "netcon", .flags = CON_ENABLED, .write = write_msg, }; static int __init init_netconsole(void) { int err; struct netconsole_target *nt, *tmp; unsigned int count = 0; bool extended = false; unsigned long flags; char *target_config; char *input = config; if (strnlen(input, MAX_PARAM_LENGTH)) { while ((target_config = strsep(&input, ";"))) { nt = alloc_param_target(target_config, count); if (IS_ERR(nt)) { err = PTR_ERR(nt); goto fail; } /* Dump existing printks when we register */ if (nt->extended) { extended = true; netconsole_ext.flags |= CON_PRINTBUFFER; } else { netconsole.flags |= CON_PRINTBUFFER; } spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); count++; } } err = register_netdevice_notifier(&netconsole_netdev_notifier); if (err) goto fail; err = dynamic_netconsole_init(); if (err) goto undonotifier; if (extended) register_console(&netconsole_ext); register_console(&netconsole); pr_info("network logging started\n"); return err; undonotifier: unregister_netdevice_notifier(&netconsole_netdev_notifier); fail: pr_err("cleaning up\n"); /* * Remove all targets and destroy them (only targets created * from the boot/module option exist here). Skipping the list * lock is safe here, and netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } return err; } static void __exit cleanup_netconsole(void) { struct netconsole_target *nt, *tmp; if (console_is_registered(&netconsole_ext)) unregister_console(&netconsole_ext); unregister_console(&netconsole); dynamic_netconsole_exit(); unregister_netdevice_notifier(&netconsole_netdev_notifier); /* * Targets created via configfs pin references on our module * and would first be rmdir(2)'ed from userspace. We reach * here only when they are already destroyed, and only those * created from the boot/module option are left, so remove and * destroy them. Skipping the list lock is safe here, and * netpoll_cleanup() will sleep. */ list_for_each_entry_safe(nt, tmp, &target_list, list) { list_del(&nt->list); free_param_target(nt); } } /* * Use late_initcall to ensure netconsole is * initialized after network device driver if built-in. * * late_initcall() and module_init() are identical if built as module. */ late_initcall(init_netconsole); module_exit(cleanup_netconsole); |
| 42 42 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Implementations of the security context functions. * * Author: Ondrej Mosnacek <omosnacek@gmail.com> * Copyright (C) 2020 Red Hat, Inc. */ #include <linux/jhash.h> #include "context.h" #include "mls.h" u32 context_compute_hash(const struct context *c) { u32 hash = 0; /* * If a context is invalid, it will always be represented by a * context struct with only the len & str set (and vice versa) * under a given policy. Since context structs from different * policies should never meet, it is safe to hash valid and * invalid contexts differently. The context_cmp() function * already operates under the same assumption. */ if (c->len) return full_name_hash(NULL, c->str, c->len); hash = jhash_3words(c->user, c->role, c->type, hash); hash = mls_range_hash(&c->range, hash); return hash; } |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" #include "internal.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 3 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, &seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) * * desc_update_last_finalized:A / desc_last_finalized_seq:A * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos) { struct prb_data_ring *data_ring = &rb->text_data_ring; unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* * Data blocks are not created for empty lines. Instead, the * reader will recognize these special lpos values and handle * it appropriately. */ blk_lpos->begin = EMPTY_LINE_LPOS; blk_lpos->next = EMPTY_LINE_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { /* Failed to allocate, specify a data-less block. */ blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* If the data block does not increase, there is nothing to do. */ if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) return NULL; /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { /* * Records that are just empty lines are also valid, even * though they do not have a data block. For such records * explicitly return empty string data to signify success. */ if (blk_lpos->begin == EMPTY_LINE_LPOS && blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; } /* Data lost, invalid, or otherwise unavailable. */ return NULL; } /* Regular data block: @begin less than @next and in same wrap. */ if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && blk_lpos->begin < blk_lpos->next) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == DATA_WRAPS(data_ring, blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* A valid data block will always have at least an ID. */ if (WARN_ON_ONCE(*data_size < sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB If desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * @last_finalized_seq value guarantees that all records up to and including * this sequence number are finalized and can be read. The only exception are * too old records which have already been overwritten. * * It is also guaranteed that @last_finalized_seq only increases. * * Be aware that finalized records following non-finalized records are not * reported because they are not yet available to the reader. For example, * a new record stored via printk() will not be available to a printer if * it follows a record that has not been finalized yet. However, once that * non-finalized record becomes finalized, @last_finalized_seq will be * appropriately updated and the full set of finalized records will be * available to the printer. And since each printk() caller will either * directly print or trigger deferred printing of all available unprinted * records, all printk() messages will get printed. */ static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long ulseq; /* * Guarantee the sequence number is loaded before loading the * associated record in order to guarantee that the record can be * seen by this CPU. This pairs with desc_update_last_finalized:A. */ ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq ); /* LMM(desc_last_finalized_seq:A) */ return __ulseq_to_u64seq(rb, ulseq); } static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count); /* * Check if there are records directly following @last_finalized_seq that are * finalized. If so, update @last_finalized_seq to the latest of these * records. It is not allowed to skip over records that are not yet finalized. */ static void desc_update_last_finalized(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; u64 old_seq = desc_last_finalized_seq(rb); unsigned long oldval; unsigned long newval; u64 finalized_seq; u64 try_seq; try_again: finalized_seq = old_seq; try_seq = finalized_seq + 1; /* Try to find later finalized records. */ while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { finalized_seq = try_seq; try_seq++; } /* No update needed if no later finalized record was found. */ if (finalized_seq == old_seq) return; oldval = __u64seq_to_ulseq(old_seq); newval = __u64seq_to_ulseq(finalized_seq); /* * Set the sequence number of a later finalized record that has been * seen. * * Guarantee the record data is visible to other CPUs before storing * its sequence number. This pairs with desc_last_finalized_seq:A. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then desc_read:A reads from * _prb_commit:B. * * Relies on: * * RELEASE from _prb_commit:B to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to desc_read:A * * Note: _prb_commit:B and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A * CPU (which performs the release) must have previously seen * _prb_commit:B. */ if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ old_seq = __ulseq_to_u64seq(rb, oldval); goto try_again; } } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ desc_update_last_finalized(rb); } } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB _prb_commit:B to prb_commit:A * matching * MB desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(e->rb, e->id); } /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { _prb_commit(e, desc_finalized); desc_update_last_finalized(e->rb); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /** * prb_next_reserve_seq() - Get the sequence number after the most recently * reserved record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what sequence * number will be assigned to the next reserved record. * * Note that depending on the situation, this value can be equal to or * higher than the sequence number returned by prb_next_seq(). * * Context: Any context. * Return: The sequence number that will be assigned to the next record * reserved. */ u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long last_finalized_id; atomic_long_t *state_var; u64 last_finalized_seq; unsigned long head_id; struct prb_desc desc; unsigned long diff; struct prb_desc *d; int err; /* * It may not be possible to read a sequence number for @head_id. * So the ID of @last_finailzed_seq is used to calculate what the * sequence number of @head_id will be. */ try_again: last_finalized_seq = desc_last_finalized_seq(rb); /* * @head_id is loaded after @last_finalized_seq to ensure that * it points to the record with @last_finalized_seq or newer. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then * prb_next_reserve_seq:A reads from desc_reserve:D. * * Relies on: * * RELEASE from desc_reserve:D to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A * * Note: desc_reserve:D and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A CPU * (which performs the release) must have previously seen * desc_read:C, which implies desc_reserve:D can be seen. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ d = to_desc(desc_ring, last_finalized_seq); state_var = &d->state_var; /* Extract the ID, used to specify the descriptor to read. */ last_finalized_id = DESC_ID(atomic_long_read(state_var)); /* Ensure @last_finalized_id is correct. */ err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); if (err == -EINVAL) { if (last_finalized_seq == 0) { /* * No record has been finalized or even reserved yet. * * The @head_id is initialized such that the first * increment will yield the first record (seq=0). * Handle it separately to avoid a negative @diff * below. */ if (head_id == DESC0_ID(desc_ring->count_bits)) return 0; /* * One or more descriptors are already reserved. Use * the descriptor ID of the first one (@seq=0) for * the @diff below. */ last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; } else { /* Record must have been overwritten. Try again. */ goto try_again; } } /* Diff of known descriptor IDs to compute related sequence numbers. */ diff = head_id - last_finalized_id; /* * @head_id points to the most recently reserved record, but this * function returns the sequence number that will be assigned to the * next (not yet reserved) record. Thus +1 is needed. */ return (last_finalized_seq + diff + 1); } /* * Non-blocking read of a record. * * On success @seq is updated to the record that was read and (if provided) * @r and @line_count will contain the read/calculated data. * * On failure @seq is updated to a record that is not yet available to the * reader, but it will be the next record available to the reader. * * Note: When the current CPU is in panic, this function will skip over any * non-existent/non-finalized records in order to allow the panic CPU * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { /* * Non-existent/non-finalized record. Must stop. * * For panic situations it cannot be expected that * non-finalized records will become finalized. But * there may be other finalized records beyond that * need to be printed for a panic situation. If this * is the panic CPU, skip this * non-existent/non-finalized record unless it is * at or beyond the head, in which case it is not * possible to continue. * * Note that new messages printed on panic CPU are * finalized when we are here. The only exception * might be the last message without trailing newline. * But it would have the sequence number returned * by "prb_next_reserve_seq() - 1". */ if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb))) (*seq)++; else return false; } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. It is guaranteed that all records * previous to the returned value have been finalized and are (or were) * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { u64 seq; seq = desc_last_finalized_seq(rb); /* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++; /* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/plist.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/freezer.h> #include "futex.h" /* * READ this before attempting to hack on futexes! * * Basic futex operation and ordering guarantees * ============================================= * * The waiter reads the futex value in user space and calls * futex_wait(). This function computes the hash bucket and acquires * the hash bucket lock. After that it reads the futex user space value * again and verifies that the data has not changed. If it has not changed * it enqueues itself into the hash bucket, releases the hash bucket lock * and schedules. * * The waker side modifies the user space value of the futex and calls * futex_wake(). This function computes the hash bucket and acquires the * hash bucket lock. Then it looks for waiters on that futex in the hash * bucket and wakes them. * * In futex wake up scenarios where no tasks are blocked on a futex, taking * the hb spinlock can be avoided and simply return. In order for this * optimization to work, ordering guarantees must exist so that the waiter * being added to the list is acknowledged when the list is concurrently being * checked by the waker, avoiding scenarios like the following: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * uval = *futex; * *futex = newval; * sys_futex(WAKE, futex); * futex_wake(futex); * if (queue_empty()) * return; * if (uval == val) * lock(hash_bucket(futex)); * queue(); * unlock(hash_bucket(futex)); * schedule(); * * This would cause the waiter on CPU 0 to wait forever because it * missed the transition of the user space value from val to newval * and the waker did not find the waiter in the hash bucket queue. * * The correct serialization ensures that a waiter either observes * the changed user space value before blocking or is woken by a * concurrent waker: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * * waiters++; (a) * smp_mb(); (A) <-- paired with -. * | * lock(hash_bucket(futex)); | * | * uval = *futex; | * | *futex = newval; * | sys_futex(WAKE, futex); * | futex_wake(futex); * | * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); * schedule(); if (waiters) * lock(hash_bucket(futex)); * else wake_waiters(futex); * waiters--; (b) unlock(hash_bucket(futex)); * * Where (A) orders the waiters increment and the futex value read through * atomic operations (see futex_hb_waiters_inc) and where (B) orders the write * to futex and the waiters read (see futex_hb_waiters_pending()). * * This yields the following case (where X:=waiters, Y:=futex): * * X = Y = 0 * * w[X]=1 w[Y]=1 * MB MB * r[Y]=y r[X]=x * * Which guarantees that x==0 && y==0 is impossible; which translates back into * the guarantee that we cannot both miss the futex variable change and the * enqueue. * * Note that a new waiter is accounted for in (a) even when it is possible that * the wait call can return error, in which case we backtrack from it in (b). * Refer to the comment in futex_q_lock(). * * Similarly, in order to account for waiters being requeued on another * address we always increment the waiters for the destination bucket before * acquiring the lock. It then decrements them again after releasing it - * the code that actually moves the futex(es) between hash buckets (requeue_futex) * will do the additional required waiter count housekeeping. This is done for * double_lock_hb() and double_unlock_hb(), respectively. */ bool __futex_wake_mark(struct futex_q *q) { if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) return false; __futex_unqueue(q); /* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL * is written, without taking any locks. This is possible in the event * of a spurious wakeup, for example. A memory barrier is required here * to prevent the following store to lock_ptr from getting ahead of the * plist_del in __futex_unqueue(). */ smp_store_release(&q->lock_ptr, NULL); return true; } /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. Callers * must ensure to later call wake_up_q() for the actual * wakeups to occur. */ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) { struct task_struct *p = q->task; get_task_struct(p); if (!__futex_wake_mark(q)) { put_task_struct(p); return; } /* * Queue the task for later wakeup for after we've released * the hb->lock. */ wake_q_add_safe(wake_q, p); } /* * Wake up waiters matching bitset queued on this futex (uaddr). */ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; DEFINE_WAKE_Q(wake_q); int ret; if (!bitset) return -EINVAL; ret = get_futex_key(uaddr, flags, &key, FUTEX_READ); if (unlikely(ret != 0)) return ret; if ((flags & FLAGS_STRICT) && !nr_wake) return 0; hb = futex_hash(&key); /* Make sure we really have tasks to wakeup */ if (!futex_hb_waiters_pending(hb)) return ret; spin_lock(&hb->lock); plist_for_each_entry_safe(this, next, &hb->chain, list) { if (futex_match (&this->key, &key)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; break; } /* Check if one of the bits is set in both bitsets */ if (!(this->bitset & bitset)) continue; this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } spin_unlock(&hb->lock); wake_up_q(&wake_q); return ret; } static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { unsigned int op = (encoded_op & 0x70000000) >> 28; unsigned int cmp = (encoded_op & 0x0f000000) >> 24; int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11); int cmparg = sign_extend32(encoded_op & 0x00000fff, 11); int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) { char comm[sizeof(current->comm)]; /* * kill this print and return -EINVAL when userspace * is sane again */ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", get_task_comm(comm, current), oparg); oparg &= 31; } oparg = 1 << oparg; } pagefault_disable(); ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr); pagefault_enable(); if (ret) return ret; switch (cmp) { case FUTEX_OP_CMP_EQ: return oldval == cmparg; case FUTEX_OP_CMP_NE: return oldval != cmparg; case FUTEX_OP_CMP_LT: return oldval < cmparg; case FUTEX_OP_CMP_GE: return oldval >= cmparg; case FUTEX_OP_CMP_LE: return oldval <= cmparg; case FUTEX_OP_CMP_GT: return oldval > cmparg; default: return -ENOSYS; } } /* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; int ret, op_ret; DEFINE_WAKE_Q(wake_q); retry: ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) return ret; hb1 = futex_hash(&key1); hb2 = futex_hash(&key2); retry_private: double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { double_unlock_hb(hb1, hb2); if (!IS_ENABLED(CONFIG_MMU) || unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { /* * we don't get EFAULT from MMU faults if we don't have * an MMU, but we might get them from range checking */ ret = op_ret; return ret; } if (op_ret == -EFAULT) { ret = fault_in_user_writeable(uaddr2); if (ret) return ret; } cond_resched(); if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } plist_for_each_entry_safe(this, next, &hb1->chain, list) { if (futex_match (&this->key, &key1)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } if (op_ret > 0) { op_ret = 0; plist_for_each_entry_safe(this, next, &hb2->chain, list) { if (futex_match (&this->key, &key2)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++op_ret >= nr_wake2) break; } } ret += op_ret; } out_unlock: double_unlock_hb(hb1, hb2); wake_up_q(&wake_q); return ret; } static long futex_wait_restart(struct restart_block *restart); /** * futex_wait_queue() - futex_queue() and wait for wakeup, timeout, or signal * @hb: the futex hash bucket, must be locked by the caller * @q: the futex_q to queue up on * @timeout: the prepared hrtimer_sleeper, or null for no timeout */ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout) { /* * The task state is guaranteed to be set before another task can * wake it. set_current_state() is implemented using smp_store_mb() and * futex_queue() calls spin_unlock() upon completion, both serializing * access to the hash list and forcing another memory barrier. */ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); futex_queue(q, hb); /* Arm the timer */ if (timeout) hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS); /* * If we have been removed from the hash list, then another task * has tried to wake us, and we can skip the call to schedule(). */ if (likely(!plist_node_empty(&q->list))) { /* * If the timer has already expired, current will already be * flagged for rescheduling. Only call schedule if there * is no timeout, or if it has yet to expire. */ if (!timeout || timeout->task) schedule(); } __set_current_state(TASK_RUNNING); } /** * futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list * * Helper to unqueue a list of futexes. This can't fail. * * Return: * - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ int futex_unqueue_multiple(struct futex_vector *v, int count) { int ret = -1, i; for (i = 0; i < count; i++) { if (!futex_unqueue(&v[i].q)) ret = i; } return ret; } /** * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes * @vs: The futex list to wait on * @count: The size of the list * @woken: Index of the last woken futex, if any. Used to notify the * caller that it can return this index to userspace (return parameter) * * Prepare multiple futexes in a single step and enqueue them. This may fail if * the futex list is invalid or if any futex was already awoken. On success the * task is ready to interruptible sleep. * * Return: * - 1 - One of the futexes was woken by another thread * - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) { struct futex_hash_bucket *hb; bool retry = false; int ret, i; u32 uval; /* * Enqueuing multiple futexes is tricky, because we need to enqueue * each futex on the list before dealing with the next one to avoid * deadlocking on the hash bucket. But, before enqueuing, we need to * make sure that current->state is TASK_INTERRUPTIBLE, so we don't * lose any wake events, which cannot be done before the get_futex_key * of the next key, because it calls get_user_pages, which can sleep. * Thus, we fetch the list of futexes keys in two steps, by first * pinning all the memory keys in the futex key, and only then we read * each key and queue the corresponding futex. * * Private futexes doesn't need to recalculate hash in retry, so skip * get_futex_key() when retrying. */ retry: for (i = 0; i < count; i++) { if (!(vs[i].w.flags & FLAGS_SHARED) && retry) continue; ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), vs[i].w.flags, &vs[i].q.key, FUTEX_READ); if (unlikely(ret)) return ret; } set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); for (i = 0; i < count; i++) { u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; struct futex_q *q = &vs[i].q; u32 val = vs[i].w.val; hb = futex_q_lock(q); ret = futex_get_value_locked(&uval, uaddr); if (!ret && uval == val) { /* * The bucket lock can't be held while dealing with the * next futex. Queue each futex at this moment so hb can * be unlocked. */ futex_queue(q, hb); continue; } futex_q_unlock(hb); __set_current_state(TASK_RUNNING); /* * Even if something went wrong, if we find out that a futex * was woken, we don't return error and return this index to * userspace */ *woken = futex_unqueue_multiple(vs, i); if (*woken >= 0) return 1; if (ret) { /* * If we need to handle a page fault, we need to do so * without any lock and any enqueued futex (otherwise * we could lose some wakeup). So we do it here, after * undoing all the work done so far. In success, we * retry all the work. */ if (get_user(uval, uaddr)) return -EFAULT; retry = true; goto retry; } if (uval != val) return -EWOULDBLOCK; } return 0; } /** * futex_sleep_multiple - Check sleeping conditions and sleep * @vs: List of futexes to wait for * @count: Length of vs * @to: Timeout * * Sleep if and only if the timeout hasn't expired and no futex on the list has * been woken up. */ static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { if (to && !to->task) return; for (; count; count--, vs++) { if (!READ_ONCE(vs->q.lock_ptr)) return; } schedule(); } /** * futex_wait_multiple - Prepare to wait on and enqueue several futexes * @vs: The list of futexes to wait on * @count: The number of objects * @to: Timeout before giving up and returning to userspace * * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function * sleeps on a group of futexes and returns on the first futex that is * wake, or after the timeout has elapsed. * * Return: * - >=0 - Hint to the futex that was awoken * - <0 - On error */ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { int ret, hint = 0; if (to) hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); while (1) { ret = futex_wait_multiple_setup(vs, count, &hint); if (ret) { if (ret > 0) { /* A futex was woken during setup */ ret = hint; } return ret; } futex_sleep_multiple(vs, count, to); __set_current_state(TASK_RUNNING); ret = futex_unqueue_multiple(vs, count); if (ret >= 0) return ret; if (to && !to->task) return -ETIMEDOUT; else if (signal_pending(current)) return -ERESTARTSYS; /* * The final case is a spurious wakeup, for * which just retry. */ } } /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address * @val: the expected value * @flags: futex flags (FLAGS_SHARED, etc.) * @q: the associated futex_q * @hb: storage for hash_bucket pointer to be returned to caller * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. * Return with the hb lock held on success, and unlocked on failure. * * Return: * - 0 - uaddr contains val and hb has been locked; * - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked */ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, struct futex_hash_bucket **hb) { u32 uval; int ret; /* * Access the page AFTER the hash-bucket is locked. * Order is important: * * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); * Userspace waker: if (cond(var)) { var = new; futex_wake(&var); } * * The basic logical guarantee of a futex is that it blocks ONLY * if cond(var) is known to be true at the time of blocking, for * any cond. If we locked the hash-bucket after testing *uaddr, that * would open a race condition where we could block indefinitely with * cond(var) false, which would violate the guarantee. * * On the other hand, we insert q and release the hash-bucket only * after testing *uaddr. This guarantees that futex_wait() will NOT * absorb a wakeup if *uaddr does not match the desired values * while the syscall executes. */ retry: ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ); if (unlikely(ret != 0)) return ret; retry_private: *hb = futex_q_lock(q); ret = futex_get_value_locked(&uval, uaddr); if (ret) { futex_q_unlock(*hb); ret = get_user(uval, uaddr); if (ret) return ret; if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } if (uval != val) { futex_q_unlock(*hb); ret = -EWOULDBLOCK; } return ret; } int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset) { struct futex_q q = futex_q_init; struct futex_hash_bucket *hb; int ret; if (!bitset) return -EINVAL; q.bitset = bitset; retry: /* * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ ret = futex_wait_setup(uaddr, val, flags, &q, &hb); if (ret) return ret; /* futex_queue and wait for wakeup, timeout, or a signal. */ futex_wait_queue(hb, &q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ if (!futex_unqueue(&q)) return 0; if (to && !to->task) return -ETIMEDOUT; /* * We expect signal_pending(current), but we might be the * victim of a spurious wakeup as well. */ if (!signal_pending(current)) goto retry; return -ERESTARTSYS; } int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) { struct hrtimer_sleeper timeout, *to; struct restart_block *restart; int ret; to = futex_setup_timer(abs_time, &timeout, flags, current->timer_slack_ns); ret = __futex_wait(uaddr, flags, val, to, bitset); /* No timeout, nothing to clean up. */ if (!to) return ret; hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); if (ret == -ERESTARTSYS) { restart = ¤t->restart_block; restart->futex.uaddr = uaddr; restart->futex.val = val; restart->futex.time = *abs_time; restart->futex.bitset = bitset; restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; return set_restart_fn(restart, futex_wait_restart); } return ret; } static long futex_wait_restart(struct restart_block *restart) { u32 __user *uaddr = restart->futex.uaddr; ktime_t t, *tp = NULL; if (restart->futex.flags & FLAGS_HAS_TIMEOUT) { t = restart->futex.time; tp = &t; } restart->fn = do_no_restart_syscall; return (long)futex_wait(uaddr, restart->futex.flags, restart->futex.val, tp, restart->futex.bitset); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LLIST_H #define LLIST_H /* * Lock-less NULL terminated single linked list * * Cases where locking is not needed: * If there are multiple producers and multiple consumers, llist_add can be * used in producers and llist_del_all can be used in consumers simultaneously * without locking. Also a single consumer can use llist_del_first while * multiple producers simultaneously use llist_add, without any locking. * * Cases where locking is needed: * If we have multiple consumers with llist_del_first used in one consumer, and * llist_del_first or llist_del_all used in other consumers, then a lock is * needed. This is because llist_del_first depends on list->first->next not * changing, but without lock protection, there's no way to be sure about that * if a preemption happens in the middle of the delete operation and on being * preempted back, the list->first is the same as before causing the cmpxchg in * llist_del_first to succeed. For example, while a llist_del_first operation * is in progress in one consumer, then a llist_del_first, llist_add, * llist_add (or llist_del_all, llist_add, llist_add) sequence in another * consumer may cause violations. * * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * * Where, a particular row's operation can happen concurrently with a column's * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list * entries can not be traversed safely before deleted from the list. * The order of deleted entries is from the newest to the oldest added * one. If you want to traverse from the oldest to the newest, you * must reverse the order by yourself before traversing. * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/stddef.h> #include <linux/types.h> struct llist_head { struct llist_node *first; }; struct llist_node { struct llist_node *next; }; #define LLIST_HEAD_INIT(name) { NULL } #define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) /** * init_llist_head - initialize lock-less list head * @head: the head for your lock-less list */ static inline void init_llist_head(struct llist_head *list) { list->first = NULL; } /** * init_llist_node - initialize lock-less list node * @node: the node to be initialised * * In cases where there is a need to test if a node is on * a list or not, this initialises the node to clearly * not be on any list. */ static inline void init_llist_node(struct llist_node *node) { node->next = node; } /** * llist_on_list - test if a lock-list list node is on a list * @node: the node to test * * When a node is on a list the ->next pointer will be NULL or * some other node. It can never point to itself. We use that * in init_llist_node() to record that a node is not on any list, * and here to test whether it is on any list. */ static inline bool llist_on_list(const struct llist_node *node) { return node->next != node; } /** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. * @member: the name of the llist_node within the struct. */ #define llist_entry(ptr, type, member) \ container_of(ptr, type, member) /** * member_address_is_nonnull - check whether the member address is not NULL * @ptr: the object pointer (struct type * that contains the llist_node) * @member: the name of the llist_node within the struct. * * This macro is conceptually the same as * &ptr->member != NULL * but it works around the fact that compilers can decide that taking a member * address is never a NULL pointer. * * Real objects that start at a high address and have a member at NULL are * unlikely to exist, but such pointers may be returned e.g. by the * container_of() macro. */ #define member_address_is_nonnull(ptr, member) \ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) /** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each(pos, node) \ for ((pos) = (node); pos; (pos) = (pos)->next) /** * llist_for_each_safe - iterate over some deleted entries of a lock-less list * safe against removal of list entry * @pos: the &struct llist_node to use as a loop cursor * @n: another &struct llist_node to use as temporary storage * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_safe(pos, n, node) \ for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) /** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type * safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @node: the first entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * * Not guaranteed to be accurate or up to date. Just a quick way to * test whether the list is empty without deleting something from the * list. */ static inline bool llist_empty(const struct llist_head *head) { return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) { return node->next; } extern bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head); static inline bool __llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head) { new_last->next = head->first; head->first = new_first; return new_last->next == NULL; } /** * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list * * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { return llist_add_batch(new, new, head); } static inline bool __llist_add(struct llist_node *new, struct llist_head *head) { return __llist_add_batch(new, new, head); } /** * llist_del_all - delete all entries from lock-less list * @head: the head of lock-less list to delete all entries * * If list is empty, return NULL, otherwise, delete all entries and * return the pointer to the first entry. The order of entries * deleted is from the newest to the oldest added one. */ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } static inline struct llist_node *__llist_del_all(struct llist_head *head) { struct llist_node *first = head->first; head->first = NULL; return first; } extern struct llist_node *llist_del_first(struct llist_head *head); /** * llist_del_first_init - delete first entry from lock-list and mark is as being off-list * @head: the head of lock-less list to delete from. * * This behave the same as llist_del_first() except that llist_init_node() is called * on the returned node so that llist_on_list() will report false for the node. */ static inline struct llist_node *llist_del_first_init(struct llist_head *head) { struct llist_node *n = llist_del_first(head); if (n) init_llist_node(n); return n; } extern bool llist_del_first_this(struct llist_head *head, struct llist_node *this); struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_H */ |
| 41 200 3 37 33 141 300 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for atomic bit * operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #include <linux/instrumented.h> /** * set_bit - Atomically set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); } /** * clear_bit - Clears a bit in memory * @nr: Bit to clear * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). */ static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); } /** * change_bit - Toggle a bit in memory * @nr: Bit to change * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); } /** * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } /** * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } /** * test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 181 181 181 181 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 155 224 224 234 209 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct * selinux_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct * selinux_msg_msg(const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct * selinux_ipc(const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } static inline struct superblock_security_struct * selinux_superblock(const struct super_block *superblock) { return superblock->s_security + selinux_blob_sizes.lbs_superblock; } #endif /* _SELINUX_OBJSEC_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | // SPDX-License-Identifier: GPL-2.0-only /* * Guest PC manipulation helpers * * Copyright (C) 2012,2013 - ARM Ltd * Copyright (C) 2020 - Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ #define __ARM64_KVM_HYP_ADJUST_PC_H__ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu); } else { *vcpu_pc(vcpu) += 4; *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /* * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu); write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } /* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ static inline void kvm_skip_host_instr(void) { write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); } #endif |
| 180 180 180 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/init.c * * Copyright (C) 1995-2005 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/errno.h> #include <linux/swap.h> #include <linux/init.h> #include <linux/cache.h> #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/initrd.h> #include <linux/gfp.h> #include <linux/math.h> #include <linux/memblock.h> #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> #include <linux/efi.h> #include <linux/swiotlb.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/hugetlb.h> #include <linux/acpi_iort.h> #include <linux/kmemleak.h> #include <linux/execmem.h> #include <asm/boot.h> #include <asm/fixmap.h> #include <asm/kasan.h> #include <asm/kernel-pgtable.h> #include <asm/kvm_host.h> #include <asm/memory.h> #include <asm/numa.h> #include <asm/sections.h> #include <asm/setup.h> #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/alternative.h> #include <asm/xen/swiotlb-xen.h> /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() * executes, which assigns it its actual value. So use a default value * that cannot be mistaken for a real physical address. */ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* * If the corresponding config options are enabled, we create both ZONE_DMA * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, * otherwise it is empty. */ phys_addr_t __ro_after_init arm64_dma_phys_limit; /* * To make optimal use of block mappings when laying out the linear * mapping, round down the base of physical memory to a size that can * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE * (64k granule), or a multiple that can be mapped using contiguous bits * in the page tables: 32 * PMD_SIZE (16k granule) */ #if defined(CONFIG_ARM64_4K_PAGES) #define ARM64_MEMSTART_SHIFT PUD_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT #else #define ARM64_MEMSTART_SHIFT PMD_SHIFT #endif /* * sparsemem vmemmap imposes an additional requirement on the alignment of * memstart_addr, due to the fact that the base of the vmemmap region * has a direct correspondence, and needs to appear sufficiently aligned * in the virtual address space. */ #if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS #define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) #else #define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) #endif static void __init arch_reserve_crashkernel(void) { unsigned long long low_size = 0; unsigned long long crash_base, crash_size; char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), &crash_size, &crash_base, &low_size, &high); if (ret) return; reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high); } /* * Return the maximum physical address for a zone accessible by the given bits * limit. If DRAM starts above 32-bit, expand the zone to the maximum * available memory, otherwise cap it at 32-bit. */ static phys_addr_t __init max_zone_phys(unsigned int zone_bits) { phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits); phys_addr_t phys_start = memblock_start_of_DRAM(); if (phys_start > U32_MAX) zone_mask = PHYS_ADDR_MAX; else if (phys_start > zone_mask) zone_mask = U32_MAX; return min(zone_mask, memblock_end_of_DRAM() - 1) + 1; } static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; unsigned int __maybe_unused dt_zone_dma_bits; phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL)); zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits); arm64_dma_phys_limit = max_zone_phys(zone_dma_bits); max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); if (!arm64_dma_phys_limit) arm64_dma_phys_limit = dma32_phys_limit; #endif if (!arm64_dma_phys_limit) arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max_pfn; free_area_init(max_zone_pfns); } int pfn_is_map_memory(unsigned long pfn) { phys_addr_t addr = PFN_PHYS(pfn); /* avoid false positives for bogus PFNs, see comment in pfn_valid() */ if (PHYS_PFN(addr) != pfn) return 0; return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_is_map_memory); static phys_addr_t memory_limit __ro_after_init = PHYS_ADDR_MAX; /* * Limit the memory size that was specified via FDT. */ static int __init early_mem(char *p) { if (!p) return 1; memory_limit = memparse(p, &p) & PAGE_MASK; pr_notice("Memory limited to %lldMB\n", memory_limit >> 20); return 0; } early_param("mem", early_mem); void __init arm64_memblock_init(void) { s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual); /* * Corner case: 52-bit VA capable systems running KVM in nVHE mode may * be limited in their ability to support a linear map that exceeds 51 * bits of VA space, depending on the placement of the ID map. Given * that the placement of the ID map may be randomized, let's simply * limit the kernel's linear map to 51 bits as well if we detect this * configuration. */ if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 && is_hyp_mode_available() && !is_kernel_in_hyp_mode()) { pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n"); linear_region_size = min_t(u64, linear_region_size, BIT(51)); } /* Remove memory above our supported physical address size */ memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX); /* * Select a suitable value for the base of physical memory. */ memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); if ((memblock_end_of_DRAM() - memstart_addr) > linear_region_size) pr_warn("Memory doesn't fit in the linear mapping, VA_BITS too small\n"); /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be * high in memory. */ memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa_symbol(_end)), ULLONG_MAX); if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) { /* ensure that memstart_addr remains sufficiently aligned */ memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size, ARM64_MEMSTART_ALIGN); memblock_remove(0, memstart_addr); } /* * If we are running with a 52-bit kernel VA config on a system that * does not support it, we have to place the available physical * memory in the 48-bit addressable part of the linear region, i.e., * we have to move it upward. Since memstart_addr represents the * physical address of PAGE_OFFSET, we have to *subtract* from it. */ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52); /* * Apply the memory limit if it was set. Since the kernel may be loaded * high up in memory, add back the kernel region that must be accessible * via the linear mapping. */ if (memory_limit != PHYS_ADDR_MAX) { memblock_mem_limit_remove_map(memory_limit); memblock_add(__pa_symbol(_text), (u64)(_end - _text)); } if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* * Add back the memory we just removed if it results in the * initrd to become inaccessible via the linear mapping. * Otherwise, this is a no-op */ u64 base = phys_initrd_start & PAGE_MASK; u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base; /* * We can only add back the initrd memory if we don't end up * with more memory than we can address via the linear mapping. * It is up to the bootloader to position the kernel and the * initrd reasonably close to each other (i.e., within 32 GB of * each other) so that all granule/#levels combinations can * always access both. */ if (WARN(base < memblock_start_of_DRAM() || base + size > memblock_start_of_DRAM() + linear_region_size, "initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) { phys_initrd_size = 0; } else { memblock_add(base, size); memblock_clear_nomap(base, size); memblock_reserve(base, size); } } if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); int parange = cpuid_feature_extract_unsigned_field( mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); s64 range = linear_region_size - BIT(id_aa64mmfr0_parange_to_phys_shift(parange)); /* * If the size of the linear region exceeds, by a sufficient * margin, the size of the region that the physical memory can * span, randomize the linear region as well. */ if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) { range /= ARM64_MEMSTART_ALIGN; memstart_addr -= ARM64_MEMSTART_ALIGN * ((range * memstart_offset_seed) >> 16); } } /* * Register the kernel text, kernel data, initrd, and initial * pagetables with memblock. */ memblock_reserve(__pa_symbol(_stext), _end - _stext); if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* the generic initrd code expects virtual addresses */ initrd_start = __phys_to_virt(phys_initrd_start); initrd_end = initrd_start + phys_initrd_size; } early_init_fdt_scan_reserved_mem(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; } void __init bootmem_init(void) { unsigned long min, max; min = PFN_UP(memblock_start_of_DRAM()); max = PFN_DOWN(memblock_end_of_DRAM()); early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT); max_pfn = max_low_pfn = max; min_low_pfn = min; arch_numa_init(); /* * must be done after arch_numa_init() which calls numa_init() to * initialize node_online_map that gets used in hugetlb_cma_reserve() * while allocating required CMA size across online nodes. */ #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) arm64_hugetlb_cma_reserve(); #endif kvm_hyp_reserve(); /* * sparse_init() tries to allocate memory from memblock, so must be * done after the fixed reservations */ sparse_init(); zone_sizes_init(); /* * Reserve the CMA area after arm64_dma_phys_limit was initialised. */ dma_contiguous_reserve(arm64_dma_phys_limit); /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ arch_reserve_crashkernel(); memblock_dump_all(); } /* * mem_init() marks the free areas in the mem_map and tells us how much memory * is free. This is done after various parts of the system have claimed their * memory after the kernel image. */ void __init mem_init(void) { bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit); if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) { /* * If no bouncing needed for ZONE_DMA, reduce the swiotlb * buffer for kmalloc() bouncing to 1MB per 1GB of RAM. */ unsigned long size = DIV_ROUND_UP(memblock_phys_mem_size(), 1024); swiotlb_adjust_size(min(swiotlb_size_or_default(), size)); swiotlb = true; } swiotlb_init(swiotlb, SWIOTLB_VERBOSE); /* this will put all unused low memory onto the freelists */ memblock_free_all(); /* * Check boundaries twice: Some fundamental inconsistencies can be * detected at build time already. */ #ifdef CONFIG_COMPAT BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64); #endif /* * Selected page table levels should match when derived from * scratch using the virtual address range and page size. */ BUILD_BUG_ON(ARM64_HW_PGTABLE_LEVELS(CONFIG_ARM64_VA_BITS) != CONFIG_PGTABLE_LEVELS); if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; /* * On a machine this small we won't get anywhere without * overcommit, so turn it on by default. */ sysctl_overcommit_memory = OVERCOMMIT_ALWAYS; } } void free_initmem(void) { free_reserved_area(lm_alias(__init_begin), lm_alias(__init_end), POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which * is not supported by kallsyms. */ vunmap_range((u64)__init_begin, (u64)__init_end); } void dump_mem_limit(void) { if (memory_limit != PHYS_ADDR_MAX) { pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20); } else { pr_emerg("Memory Limit: none\n"); } } #ifdef CONFIG_EXECMEM static u64 module_direct_base __ro_after_init = 0; static u64 module_plt_base __ro_after_init = 0; /* * Choose a random page-aligned base address for a window of 'size' bytes which * entirely contains the interval [start, end - 1]. */ static u64 __init random_bounding_box(u64 size, u64 start, u64 end) { u64 max_pgoff, pgoff; if ((end - start) >= size) return 0; max_pgoff = (size - (end - start)) / PAGE_SIZE; pgoff = get_random_u32_inclusive(0, max_pgoff); return start - pgoff * PAGE_SIZE; } /* * Modules may directly reference data and text anywhere within the kernel * image and other modules. References using PREL32 relocations have a +/-2G * range, and so we need to ensure that the entire kernel image and all modules * fall within a 2G window such that these are always within range. * * Modules may directly branch to functions and code within the kernel text, * and to functions and code within other modules. These branches will use * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure * that the entire kernel text and all module text falls within a 128M window * such that these are always within range. With PLTs, we can expand this to a * 2G window. * * We chose the 128M region to surround the entire kernel image (rather than * just the text) as using the same bounds for the 128M and 2G regions ensures * by construction that we never select a 128M region that is not a subset of * the 2G region. For very large and unusual kernel configurations this means * we may fall back to PLTs where they could have been avoided, but this keeps * the logic significantly simpler. */ static int __init module_init_limits(void) { u64 kernel_end = (u64)_end; u64 kernel_start = (u64)_text; u64 kernel_size = kernel_end - kernel_start; /* * The default modules region is placed immediately below the kernel * image, and is large enough to use the full 2G relocation range. */ BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END); BUILD_BUG_ON(MODULES_VSIZE < SZ_2G); if (!kaslr_enabled()) { if (kernel_size < SZ_128M) module_direct_base = kernel_end - SZ_128M; if (kernel_size < SZ_2G) module_plt_base = kernel_end - SZ_2G; } else { u64 min = kernel_start; u64 max = kernel_end; if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n"); } else { module_direct_base = random_bounding_box(SZ_128M, min, max); if (module_direct_base) { min = module_direct_base; max = module_direct_base + SZ_128M; } } module_plt_base = random_bounding_box(SZ_2G, min, max); } pr_info("%llu pages in range for non-PLT usage", module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0); pr_info("%llu pages in range for PLT usage", module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0); return 0; } static struct execmem_info execmem_info __ro_after_init; struct execmem_info __init *execmem_arch_setup(void) { unsigned long fallback_start = 0, fallback_end = 0; unsigned long start = 0, end = 0; module_init_limits(); /* * Where possible, prefer to allocate within direct branch range of the * kernel such that no PLTs are necessary. */ if (module_direct_base) { start = module_direct_base; end = module_direct_base + SZ_128M; if (module_plt_base) { fallback_start = module_plt_base; fallback_end = module_plt_base + SZ_2G; } } else if (module_plt_base) { start = module_plt_base; end = module_plt_base + SZ_2G; } execmem_info = (struct execmem_info){ .ranges = { [EXECMEM_DEFAULT] = { .start = start, .end = end, .pgprot = PAGE_KERNEL, .alignment = 1, .fallback_start = fallback_start, .fallback_end = fallback_end, }, [EXECMEM_KPROBES] = { .start = VMALLOC_START, .end = VMALLOC_END, .pgprot = PAGE_KERNEL_ROX, .alignment = 1, }, [EXECMEM_BPF] = { .start = VMALLOC_START, .end = VMALLOC_END, .pgprot = PAGE_KERNEL, .alignment = 1, }, }, }; return &execmem_info; } #endif /* CONFIG_EXECMEM */ |
| 121 1 120 112 9 113 120 120 120 120 120 120 120 114 120 8 120 120 120 120 120 117 6 117 120 121 130 3 131 131 129 131 131 131 7 131 127 130 2 1 130 3 130 130 6 130 4 130 127 3 4 1 130 125 130 130 130 130 130 130 130 131 131 131 130 26 122 122 8 118 122 131 131 131 13 13 13 12 13 13 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/dnotify.h> #include <linux/compat.h> #include <linux/mnt_idmapping.h> #include <linux/filelock.h> #include "internal.h" int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(idmap, dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { struct mnt_idmap *idmap; struct inode *inode; long error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = mnt_want_write(path->mnt); if (error) goto out; idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = security_path_truncate(path); if (!error) error = do_truncate(idmap, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); out: return error; } EXPORT_SYMBOL_GPL(vfs_truncate); long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (!error) { error = vfs_truncate(&path, length); path_put(&path); } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return do_sys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return do_sys_truncate(path, length); } #endif long do_ftruncate(struct file *file, loff_t length, int small) { struct inode *inode; struct dentry *dentry; int error; /* explicitly opened as large or we are on 64-bit box */ if (file->f_flags & O_LARGEFILE) small = 0; dentry = file->f_path.dentry; inode = dentry->d_inode; if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) return -EINVAL; /* Cannot ftruncate over 2^31 bytes without large file support */ if (small && length > MAX_NON_LFS) return -EINVAL; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; sb_start_write(inode->i_sb); error = security_file_truncate(file); if (!error) error = do_truncate(file_mnt_idmap(file), dentry, length, ATTR_MTIME | ATTR_CTIME, file); sb_end_write(inode->i_sb); return error; } long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct fd f; int error; if (length < 0) return -EINVAL; f = fdget(fd); if (!f.file) return -EBADF; error = do_ftruncate(f.file, length, small); fdput(f); return error; } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length) { return do_sys_ftruncate(fd, length, 1); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length) { return do_sys_ftruncate(fd, length, 1); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return do_sys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return do_sys_ftruncate(fd, length, 0); } #endif /* BITS_PER_LONG == 32 */ #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64) COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname, compat_arg_u64_dual(length)) { return ksys_truncate(pathname, compat_arg_u64_glue(length)); } #endif #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64) COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd, compat_arg_u64_dual(length)) { return ksys_ftruncate(fd, compat_arg_u64_glue(length)); } #endif int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret; if (offset < 0 || len <= 0) return -EINVAL; /* Return error if mode is not supported */ if (mode & ~FALLOC_FL_SUPPORTED_MASK) return -EOPNOTSUPP; /* Punch hole and zero range are mutually exclusive */ if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; /* Punch hole must have keep size set */ if ((mode & FALLOC_FL_PUNCH_HOLE) && !(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* Collapse range should only be used exclusively. */ if ((mode & FALLOC_FL_COLLAPSE_RANGE) && (mode & ~FALLOC_FL_COLLAPSE_RANGE)) return -EINVAL; /* Insert range should only be used exclusively. */ if ((mode & FALLOC_FL_INSERT_RANGE) && (mode & ~FALLOC_FL_INSERT_RANGE)) return -EINVAL; /* Unshare range should only be used with allocate mode. */ if ((mode & FALLOC_FL_UNSHARE_RANGE) && (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * We can only allow pure fallocate on append only files */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wrap through zero too */ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fallocate(f.file, mode, offset, len); fdput(f); } return error; } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE) COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset), compat_arg_u64_dual(len)) { return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset), compat_arg_u64_glue(len)); } #endif /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. * * Creating new credentials is expensive, so we try to skip doing it, * which we can if the result would match what we already got. */ static bool access_need_override_creds(int flags) { const struct cred *cred; if (flags & AT_EACCESS) return false; cred = current_cred(); if (!uid_eq(cred->fsuid, cred->uid) || !gid_eq(cred->fsgid, cred->gid)) return true; if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(cred->user_ns, 0); if (!uid_eq(cred->uid, root_uid)) { if (!cap_isclear(cred->cap_effective)) return true; } else { if (!cap_isidentical(cred->cap_effective, cred->cap_permitted)) return true; } } return false; } static const struct cred *access_override_creds(void) { const struct cred *old_cred; struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; /* * XXX access_need_override_creds performs checks in hopes of skipping * this work. Make sure it stays in sync if making any changes in this * routine. */ override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-racy to avoid RCU * freeing. */ override_cred->non_rcu = 1; old_cred = override_creds(override_cred); /* override_cred() gets its own ref */ put_cred(override_cred); return old_cred; } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (access_need_override_creds(flags)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } retry: res = user_path_at(dfd, filename, lookup_flags, &path); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path)) goto out_path_release; } res = inode_permission(mnt_idmap(path.mnt), inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; /* * This is a rare case where using __mnt_is_readonly() * is OK without a mnt_want/drop_write() pair. Since * no actual write to the fs is performed here, we do * not need to telegraph to that to anyone. * * By doing this, we accept that this access is * inherently racy and know that the fs may change * state before we even see this result. */ if (__mnt_is_readonly(path.mnt)) res = -EROFS; out_path_release: path_put(&path); if (retry_estale(res, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: if (old_cred) revert_creds(old_cred); return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { return do_faccessat(dfd, filename, mode, 0); } SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, int, flags) { return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return do_faccessat(AT_FDCWD, filename, mode, 0); } SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; set_fs_pwd(current->fs, &path); dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); int error; error = -EBADF; if (!f.file) goto out; error = -ENOTDIR; if (!d_can_lookup(f.file->f_path.dentry)) goto out_putf; error = file_permission(f.file, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (error) goto dput_and_out; set_fs_root(current->fs, &path); error = 0; dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; struct iattr newattrs; int error; error = mnt_want_write(path->mnt); if (error) return error; retry_deleg: inode_lock(inode); error = security_path_chmod(path, mode); if (error) goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path->mnt); return error; } int vfs_fchmod(struct file *file, umode_t mode) { audit_file(file); return chmod_common(&file->f_path, mode); } SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { struct fd f = fdget(fd); int err = -EBADF; if (f.file) { err = vfs_fchmod(f.file, mode); fdput(f); } return err; } static int do_fchmodat(int dfd, const char __user *filename, umode_t mode, unsigned int flags) { struct path path; int error; unsigned int lookup_flags; if (unlikely(flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))) return -EINVAL; lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (!error) { error = chmod_common(&path, mode); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE4(fchmodat2, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, flags) { return do_fchmodat(dfd, filename, mode, flags); } SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) { return do_fchmodat(dfd, filename, mode, 0); } SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { return do_fchmodat(AT_FDCWD, filename, mode, 0); } /* * Check whether @kuid is valid and if so generate and set vfsuid_t in * ia_vfsuid. * * Return: true if @kuid is valid, false if not. */ static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid) { if (!uid_valid(kuid)) return false; attr->ia_valid |= ATTR_UID; attr->ia_vfsuid = VFSUIDT_INIT(kuid); return true; } /* * Check whether @kgid is valid and if so generate and set vfsgid_t in * ia_vfsgid. * * Return: true if @kgid is valid, false if not. */ static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid) { if (!gid_valid(kgid)) return false; attr->ia_valid |= ATTR_GID; attr->ia_vfsgid = VFSGIDT_INIT(kgid); return true; } int chown_common(const struct path *path, uid_t user, gid_t group) { struct mnt_idmap *idmap; struct user_namespace *fs_userns; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; struct iattr newattrs; kuid_t uid; kgid_t gid; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); idmap = mnt_idmap(path->mnt); fs_userns = i_user_ns(inode); retry_deleg: newattrs.ia_vfsuid = INVALID_VFSUID; newattrs.ia_vfsgid = INVALID_VFSGID; newattrs.ia_valid = ATTR_CTIME; if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid)) return -EINVAL; if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid)) return -EINVAL; inode_lock(inode); if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(idmap, inode); /* Continue to send actual fs values, not the mount values. */ error = security_path_chown( path, from_vfsuid(idmap, fs_userns, newattrs.ia_vfsuid), from_vfsgid(idmap, fs_userns, newattrs.ia_vfsgid)); if (!error) error = notify_change(idmap, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag) { struct path path; int error = -EINVAL; int lookup_flags; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) goto out; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = mnt_want_write(path.mnt); if (error) goto out_release; error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { return do_fchownat(dfd, filename, user, group, flag); } SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, AT_SYMLINK_NOFOLLOW); } int vfs_fchown(struct file *file, uid_t user, gid_t group) { int error; error = mnt_want_write_file(file); if (error) return error; audit_file(file); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); return error; } int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fchown(f.file, user, group); fdput(f); } return error; } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { return ksys_fchown(fd, user, group); } static inline int file_get_write_access(struct file *f) { int error; error = get_write_access(f->f_inode); if (unlikely(error)) return error; error = mnt_get_write_access(f->f_path.mnt); if (unlikely(error)) goto cleanup_inode; if (unlikely(f->f_mode & FMODE_BACKING)) { error = mnt_get_write_access(backing_file_user_path(f)->mnt); if (unlikely(error)) goto cleanup_mnt; } return 0; cleanup_mnt: mnt_put_write_access(f->f_path.mnt); cleanup_inode: put_write_access(f->f_inode); return error; } static int do_dentry_open(struct file *f, int (*open)(struct inode *, struct file *)) { static const struct file_operations empty_fops = {}; struct inode *inode = f->f_path.dentry->d_inode; int error; path_get(&f->f_path); f->f_inode = inode; f->f_mapping = inode->i_mapping; f->f_wb_err = filemap_sample_wb_err(f->f_mapping); f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH | FMODE_OPENED; f->f_op = &empty_fops; return 0; } if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_inc(inode); } else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = file_get_write_access(f); if (unlikely(error)) goto cleanup_file; f->f_mode |= FMODE_WRITER; } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } error = security_file_open(f); if (error) goto cleanup_all; error = break_lease(file_inode(f), f->f_flags); if (error) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (!open) open = f->f_op->open; if (open) { error = open(inode, f); if (error) goto cleanup_all; } f->f_mode |= FMODE_OPENED; if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; if ((f->f_mode & FMODE_LSEEK) && !f->f_op->llseek) f->f_mode &= ~FMODE_LSEEK; if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO) f->f_mode |= FMODE_CAN_ODIRECT; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); f->f_iocb_flags = iocb_flags(f); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; /* * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ if (f->f_mode & FMODE_WRITE) { /* * Paired with smp_mb() in collapse_file() to ensure nr_thps * is up to date and the update to i_writecount by * get_write_access() is visible. Ensures subsequent insertion * of THPs into the page cache will fail. */ smp_mb(); if (filemap_nr_thps(inode->i_mapping)) { struct address_space *mapping = inode->i_mapping; filemap_invalidate_lock(inode->i_mapping); /* * unmap_mapping_range just need to be called once * here, because the private pages is not need to be * unmapped mapping (e.g. data segment of dynamic * shared libraries here). */ unmap_mapping_range(mapping, 0, 0, 0); truncate_inode_pages(mapping, 0); filemap_invalidate_unlock(inode->i_mapping); } } /* * Once we return a file with FMODE_OPENED, __fput() will call * fsnotify_close(), so we need fsnotify_open() here for symmetry. */ fsnotify_open(f); return 0; cleanup_all: if (WARN_ON_ONCE(error > 0)) error = -EINVAL; fops_put(f->f_op); put_file_access(f); cleanup_file: path_put(&f->f_path); f->f_path.mnt = NULL; f->f_path.dentry = NULL; f->f_inode = NULL; return error; } /** * finish_open - finish opening a file * @file: file pointer * @dentry: pointer to dentry * @open: open callback * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. * * NB: the dentry reference is _not_ consumed. If, for example, the dentry is * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry; return do_dentry_open(file, open); } EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer * @dentry: dentry or NULL (as returned from ->lookup()) * * This can be used to set the result of a successful lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * * Returns "0" which must be the return value of ->atomic_open() after having * called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { file->f_path.dentry = dentry; return 0; } EXPORT_SYMBOL(finish_no_open); char *file_path(struct file *filp, char *buf, int buflen) { return d_path(&filp->f_path, buf, buflen); } EXPORT_SYMBOL(file_path); /** * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized */ int vfs_open(const struct path *path, struct file *file) { file->f_path = *path; return do_dentry_open(file, NULL); } struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; struct file *f; /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(dentry_open); /** * dentry_create - Create and open a file * @path: path to create * @flags: O_ flags * @mode: mode bits for new file * @cred: credentials to use * * Caller must hold the parent directory's lock, and have prepared * a negative dentry, placed in @path->dentry, for the new file. * * Caller sets @path->mnt to the vfsmount of the filesystem where * the new file is to be created. The parent directory and the * negative dentry must reside on the same filesystem instance. * * On success, returns a "struct file *". Otherwise a ERR_PTR * is returned. */ struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred) { struct file *f; int error; f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; error = vfs_create(mnt_idmap(path->mnt), d_inode(path->dentry->d_parent), path->dentry, mode, true); if (!error) error = vfs_open(path, f); if (unlikely(error)) { fput(f); return ERR_PTR(error); } return f; } EXPORT_SYMBOL(dentry_create); /** * kernel_file_open - open a file for kernel internal use * @path: path of the file to open * @flags: open flags * @cred: credentials for open * * Open a file for use by in-kernel consumers. The file is not accounted * against nr_files and must not be installed into the file descriptor * table. * * Return: Opened file on success, an error pointer on failure. */ struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred) { struct file *f; int error; f = alloc_empty_file_noaccount(flags, cred); if (IS_ERR(f)) return f; f->f_path = *path; error = do_dentry_open(f, NULL); if (error) { fput(f); f = ERR_PTR(error); } return f; } EXPORT_SYMBOL_GPL(kernel_file_open); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) inline struct open_how build_open_how(int flags, umode_t mode) { struct open_how how = { .flags = flags & VALID_OPEN_FLAGS, .mode = mode & S_IALLUGO, }; /* O_PATH beats everything else. */ if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS; /* Modes should only be set for create-like flags. */ if (!WILL_CREATE(how.flags)) how.mode = 0; return how; } inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; u64 strip = __FMODE_NONOTIFY | O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), "struct open_flags doesn't yet handle flags > 32 bits"); /* * Strip flags that either shouldn't be set by userspace like * FMODE_NONOTIFY or that aren't relevant in determining struct * open_flags like O_CLOEXEC. */ flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ if (flags & ~VALID_OPEN_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; /* Scoping flags are mutually exclusive. */ if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT)) return -EINVAL; /* Deal with the mode. */ if (WILL_CREATE(flags)) { if (how->mode & ~S_IALLUGO) return -EINVAL; op->mode = how->mode | S_IFREG; } else { if (how->mode != 0) return -EINVAL; op->mode = 0; } /* * Block bugs where O_DIRECTORY | O_CREAT created regular files. * Note, that blocking O_DIRECTORY | O_CREAT here also protects * O_TMPFILE below which requires O_DIRECTORY being raised. */ if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT)) return -EINVAL; /* Now handle the creative implementation of O_TMPFILE. */ if (flags & __O_TMPFILE) { /* * In order to ensure programs get explicit errors when trying * to use O_TMPFILE on old kernels we enforce that O_DIRECTORY * is raised alongside __O_TMPFILE. */ if (!(flags & O_DIRECTORY)) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; } if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) return -EINVAL; acc_mode = 0; } /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's * always set instead of having to deal with possibly weird behaviour * for malicious applications setting only __O_SYNC. */ if (flags & __O_SYNC) flags |= O_DSYNC; op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ if (flags & O_TRUNC) acc_mode |= MAY_WRITE; /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flags & O_APPEND) acc_mode |= MAY_APPEND; op->acc_mode = acc_mode; op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; if (flags & O_CREAT) { op->intent |= LOOKUP_CREATE; if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL; flags |= O_NOFOLLOW; } } if (flags & O_DIRECTORY) lookup_flags |= LOOKUP_DIRECTORY; if (!(flags & O_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (how->resolve & RESOLVE_NO_XDEV) lookup_flags |= LOOKUP_NO_XDEV; if (how->resolve & RESOLVE_NO_MAGICLINKS) lookup_flags |= LOOKUP_NO_MAGICLINKS; if (how->resolve & RESOLVE_NO_SYMLINKS) lookup_flags |= LOOKUP_NO_SYMLINKS; if (how->resolve & RESOLVE_BENEATH) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } op->lookup_flags = lookup_flags; return 0; } /** * file_open_name - open file and return file pointer * * @name: struct filename containing path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *file_open_name(struct filename *name, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_filp_open(AT_FDCWD, name, &op); } /** * filp_open - open file and return file pointer * * @filename: path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *filp_open(const char *filename, int flags, umode_t mode) { struct filename *name = getname_kernel(filename); struct file *file = ERR_CAST(name); if (!IS_ERR(name)) { file = file_open_name(name, flags, mode); putname(name); } return file; } EXPORT_SYMBOL(filp_open); struct file *file_open_root(const struct path *root, const char *filename, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open_root(root, filename, &op); } EXPORT_SYMBOL(file_open_root); static long do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; int fd = build_open_flags(how, &op); struct filename *tmp; if (fd) return fd; tmp = getname(filename); if (IS_ERR(tmp)) return PTR_ERR(tmp); fd = get_unused_fd_flags(how->flags); if (fd >= 0) { struct file *f = do_filp_open(dfd, tmp, &op); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); } else { fd_install(fd, f); } } putname(tmp); return fd; } long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_how how = build_open_how(flags, mode); return do_sys_openat2(dfd, filename, &how); } SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(dfd, filename, flags, mode); } SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, struct open_how __user *, how, size_t, usize) { int err; struct open_how tmp; BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0); BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST); if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) return err; audit_openat2_how(&tmp); /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; return do_sys_openat2(dfd, filename, &tmp); } #ifdef CONFIG_COMPAT /* * Exactly like sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(AT_FDCWD, filename, flags, mode); } /* * Exactly like sys_openat(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(dfd, filename, flags, mode); } #endif #ifndef __alpha__ /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { int flags = O_CREAT | O_WRONLY | O_TRUNC; if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, pathname, flags, mode); } #endif /* * "id" is the POSIX thread ID. We use the * files pointer for this.. */ static int filp_flush(struct file *filp, fl_owner_t id) { int retval = 0; if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, "VFS: Close: file count is 0 (f_op=%ps)", filp->f_op)) { return 0; } if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id); locks_remove_posix(filp, id); } return retval; } int filp_close(struct file *filp, fl_owner_t id) { int retval; retval = filp_flush(filp, id); fput(filp); return retval; } EXPORT_SYMBOL(filp_close); /* * Careful here! We test whether the file pointer is NULL before * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ SYSCALL_DEFINE1(close, unsigned int, fd) { int retval; struct file *file; file = file_close_fd(fd); if (!file) return -EBADF; retval = filp_flush(file, current->files); /* * We're returning to user space. Don't bother * with any delayed fput() cases. */ __fput_sync(file); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || retval == -ERESTARTNOINTR || retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; return retval; } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: reserved for future extensions * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { return __close_range(fd, max_fd, flags); } /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); return 0; } return -EPERM; } /* * Called when an inode is about to be open. * We use this to disallow opening large files on 32bit systems if * the caller didn't specify O_LARGEFILE. On 64bit systems we force * on this flag in sys_open. */ int generic_file_open(struct inode * inode, struct file * filp) { if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(generic_file_open); /* * This is used by subsystems that don't want seekable * file descriptors. The function is not supposed to ever fail, the only * reason it returns an 'int' and not 'void' is so that it can be plugged * directly into file_operations structure. */ int nonseekable_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); return 0; } EXPORT_SYMBOL(nonseekable_open); /* * stream_open is used by subsystems that want stream-like file descriptors. * Such file descriptors are not seekable and don't have notion of position * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). * Contrary to file descriptors of other regular files, .read() and .write() * can run simultaneously. * * stream_open never fails and is marked to return int so that it could be * directly used as file_operations.open . */ int stream_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } EXPORT_SYMBOL(stream_open); |
| 17 17 8 9 3 6 9 9 3 6 9 4 2 2 4 3 2 1 3 2 13 4 2 2 13 13 8 13 13 42 42 13 13 13 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 19 19 19 19 2 21 1 1 1 1 42 42 42 42 42 19 19 19 19 11 11 11 3 3 8 1 1 1 1 1 1 19 19 2 8 8 8 8 8 2 2 1 17 17 17 8 8 8 8 8 8 9 9 9 9 9 9 9 8 2 2 2 2 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 9 9 9 9 4 4 3 3 4 4 4 4 4 4 4 1 3 3 3 4 4 14 4 4 14 14 14 4 4 2 14 8 9 9 9 8 8 6 8 8 8 9 9 9 9 9 9 9 42 42 41 9 8 1 1 9 9 9 1 9 9 9 9 9 9 8 8 9 1 1 19 19 19 19 19 3 9 9 3 9 4 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <linux/migrate.h> #include <linux/nospec.h> #include <linux/delayacct.h> #include <linux/memory.h> #include <linux/mm_inline.h> #include <linux/padata.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" #include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { return cma_pages_valid(hugetlb_cma[folio_nid(folio)], &folio->page, 1 << order); } #else static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { return false; } #endif static unsigned long hugetlb_cma_size __initdata; __initdata struct list_head huge_boot_pages[MAX_NUMNODES]; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) return false; if (spool->max_hpages != -1) return spool->used_hpages == 0; if (spool->min_hpages != -1) return spool->rsv_hpages == spool->min_hpages; return true; } static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, unsigned long irq_flags) { spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock_irq(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; unsigned long flags; if (!spool) return delta; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool, flags); return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* * hugetlb vma_lock helper routines */ void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_read(&resv_map->rw_sema); } } void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_read(&resv_map->rw_sema); } } void hugetlb_vma_lock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_write(&resv_map->rw_sema); } } void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; return down_write_trylock(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); return down_write_trylock(&resv_map->rw_sema); } return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); lockdep_assert_held(&resv_map->rw_sema); } } void hugetlb_vma_lock_release(struct kref *kref) { struct hugetlb_vma_lock *vma_lock = container_of(kref, struct hugetlb_vma_lock, refs); kfree(vma_lock); } static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; /* * vma_lock structure may or not be released as a result of put, * it certainly will no longer be attached to vma so clear pointer. * Semaphore synchronizes access to vma_lock->vma field. */ vma_lock->vma = NULL; vma->vm_private_data = NULL; up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); } static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); /* no free for anon vmas, but still need to unlock */ up_write(&resv_map->rw_sema); } } static void hugetlb_vma_lock_free(struct vm_area_struct *vma) { /* * Only present in sharable vmas. */ if (!vma || !__vma_shareable_lock(vma)) return; if (vma->vm_private_data) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); __hugetlb_vma_unlock_write_put(vma_lock); } } static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) { struct hugetlb_vma_lock *vma_lock; /* Only establish in (flags) sharable vmas */ if (!vma || !(vma->vm_flags & VM_MAYSHARE)) return; /* Should never get here with non-NULL vm_private_data */ if (vma->vm_private_data) return; vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL); if (!vma_lock) { /* * If we can not allocate structure, then vma can not * participate in pmd sharing. This is only a possible * performance enhancement and memory saving issue. * However, the lock is also used to synchronize page * faults with truncation. If the lock is not present, * unlikely races could leave pages in a file past i_size * until the file is removed. Warn in the unlikely case of * allocation failure. */ pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); return; } kref_init(&vma_lock->refs); init_rwsem(&vma_lock->rw_sema); vma_lock->vma = vma; vma->vm_private_data = vma_lock; } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg, *prg; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } static inline long hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { struct file_region *nrg; if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; return to - from; } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *iter, *trg = NULL; struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (iter->to > last_accounted_offset) last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (iter->from >= t) { rg = iter->link.prev; break; } /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, iter->from, h, h_cg, regions_needed); last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (!rg) rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { LIST_HEAD(allocated_regions); int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. * * Folios in this VMA will be aligned to, and at least the size of the * number of bytes returned by this function. * * Return: The default size of the folios allocated when backing a VMA. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } bool __vma_private_lock(struct vm_area_struct *vma) { return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER); } void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); /* * Clear vm_private_data * - For shared mappings this is a per-vma semaphore that may be * allocated in a subsequent call to hugetlb_vm_op_open. * Before clearing, make sure pointer is not associated with vma * as this will leak the structure. This is the case when called * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already * been called to allocate a new structure. * - For MAP_PRIVATE mappings, this is the reserve map which does * not apply to children. Faults generated by the children are * not guaranteed to succeed, even if read-only. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock && vma_lock->vma != vma) vma->vm_private_data = NULL; } else vma->vm_private_data = NULL; } /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. * This function should be only used by move_vma() and operate on * same sized vma. It should never come here with last ref on the * reservation. */ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { /* * Clear the old hugetlb private page reservation. * It has already been transferred to new_vma. * * During a mremap() operation of a hugetlb vma we call move_vma() * which copies vma into new_vma and unmaps vma. After the copy * operation both new_vma and vma share a reference to the resv_map * struct, and at that point vma is about to be unmapped. We don't * want to return the reservation to the pool at unmap of vma because * the reservation still lives on in new_vma, so simply decrement the * ref here and remove the resv_map reference from this vma. */ struct resv_map *reservations = vma_resv_map(vma); if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); } hugetlb_dup_vma_private(vma); } /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { if (vma->vm_flags & VM_NORESERVE) { /* * This address is already reserved by other process(chg == 0), * so, we should decrement reserved count. Without decrementing, * reserve count remains after releasing inode, because this * allocated page will go into page cache and is regarded as * coming from reserved pool in releasing step. Currently, we * don't have any other solution to deal with this situation * properly, so add work-around here. */ if (vma->vm_flags & VM_MAYSHARE && chg == 0) return true; else return false; } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) { /* * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) return false; else return true; } /* * Only the process that called mmap() has reserves for * private mappings. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Like the shared case above, a hole punch or truncate * could have been performed on the private mapping. * Examine the value of chg to determine if reserves * actually exist or were previously consumed. * Very Subtle - The value of chg comes from a previous * call to vma_needs_reserves(). The reserve map for * private mappings has different (opposite) semantics * than that of shared mappings. vma_needs_reserves() * has already taken this difference in semantics into * account. Therefore, the meaning of chg is the same * as in the shared case above. Code could easily be * combined, but keeping it separate draws attention to * subtle differences. */ if (chg) return false; else return true; } return false; } static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; folio_set_hugetlb_freed(folio); } static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid) { struct folio *folio; bool pin = !!(current->flags & PF_MEMALLOC_PIN); lockdep_assert_held(&hugetlb_lock); list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) { if (pin && !folio_is_longterm_pinnable(folio)) continue; if (folio_test_hwpoison(folio)) continue; list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return folio; } return NULL; } static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct folio *folio; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); folio = dequeue_hugetlb_folio_node_exact(h, node); if (folio) return folio; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static unsigned long available_huge_pages(struct hstate *h) { return h->free_huge_pages - h->resv_huge_pages; } static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } mpol_cond_put(mpol); return folio; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(int *next_node, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(*next_node, nodes_allowed); *next_node = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) /* used to demote non-gigantic_huge pages as well */ static void __destroy_compound_gigantic_folio(struct folio *folio, unsigned int order, bool demote) { int i; int nr_pages = 1 << order; struct page *p; atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_pincount, 0); for (i = 1; i < nr_pages; i++) { p = folio_page(folio, i); p->flags &= ~PAGE_FLAGS_CHECK_AT_FREE; p->mapping = NULL; clear_compound_head(p); if (!demote) set_page_refcounted(p); } __folio_clear_head(folio); } static void destroy_compound_hugetlb_folio_for_demote(struct folio *folio, unsigned int order) { __destroy_compound_gigantic_folio(folio, order, true); } #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { __destroy_compound_gigantic_folio(folio, order, false); } static void free_gigantic_folio(struct folio *folio, unsigned int order) { /* * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ #ifdef CONFIG_CMA int nid = folio_nid(folio); if (cma_release(hugetlb_cma[nid], &folio->page, 1 << order)) return; #endif free_contig_range(folio_pfn(folio), 1 << order); } #ifdef CONFIG_CONTIG_ALLOC static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { struct page *page; unsigned long nr_pages = pages_per_huge_page(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); #ifdef CONFIG_CMA { int node; if (hugetlb_cma[nid]) { page = cma_alloc(hugetlb_cma[nid], nr_pages, huge_page_order(h), true); if (page) return page_folio(page); } if (!(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; page = cma_alloc(hugetlb_cma[node], nr_pages, huge_page_order(h), true); if (page) return page_folio(page); } } } #endif page = alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); return page ? page_folio(page) : NULL; } #else /* !CONFIG_CONTIG_ALLOC */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } static inline void free_gigantic_folio(struct folio *folio, unsigned int order) { } static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif /* * Remove hugetlb folio from lists. * If vmemmap exists for the folio, clear the hugetlb flag so that the * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * * A reference is held on the folio, except in the case of demote. * * Must be called with hugetlb lock held. */ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus, bool demote) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { h->free_huge_pages--; h->free_huge_pages_node[nid]--; } if (adjust_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } /* * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); /* * In the case of demote we do not ref count the page as it will soon * be turned into a page of smaller size. */ if (!demote) folio_ref_unfreeze(folio, 1); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { __remove_hugetlb_folio(h, folio, adjust_surplus, false); } static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio, bool adjust_surplus) { __remove_hugetlb_folio(h, folio, adjust_surplus, true); } static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int zeroed; int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; if (adjust_surplus) { h->surplus_huge_pages++; h->surplus_huge_pages_node[nid]++; } __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above * folio_change_private(folio, NULL) cleared it. */ folio_set_hugetlb_vmemmap_optimized(folio); /* * This folio is about to be managed by the hugetlb allocator and * should have no users. Drop our reference, and check for others * just in case. */ zeroed = folio_put_testzero(folio); if (unlikely(!zeroed)) /* * It is VERY unlikely soneone else has taken a ref * on the folio. In this case, we simply return as * free_huge_folio() will be called when this other ref * is dropped. */ return; arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; /* * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; /* * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the * page and put the page back on the hugetlb free list and treat * as a surplus page. */ add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } /* * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } /* * Non-gigantic pages demoted from CMA allocated gigantic pages * need to be given back to CMA in free_gigantic_folio. */ if (hstate_is_gigantic(h) || hugetlb_cma_folio(folio, huge_page_order(h))) { destroy_compound_gigantic_folio(folio, huge_page_order(h)); free_gigantic_folio(folio, huge_page_order(h)); } else { INIT_LIST_HEAD(&folio->_deferred_list); folio_put(folio); } } /* * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. * * free_hpage_workfn() locklessly retrieves the linked list of pages to be * freed and frees them one-by-one. As the page->mapping pointer is going * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node * structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; node = llist_del_all(&hpage_freelist); while (node) { struct folio *folio; struct hstate *h; folio = container_of((struct address_space **)node, struct folio, mapping); node = node->next; folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ h = size_to_hstate(folio_size(folio)); __update_and_free_hugetlb_folio(h, folio); cond_resched(); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { __update_and_free_hugetlb_folio(h, folio); return; } /* * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. * * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void bulk_vmemmap_restore_error(struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; if (!list_empty(non_hvo_folios)) { /* * Free any restored hugetlb pages so that restore of the * entire list can be retried. * The idea is that in the common case of ENOMEM errors freeing * hugetlb pages with vmemmap we will free up memory so that we * can allocate vmemmap for more hugetlb pages. */ list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } else { /* * In the case where there are no folios which can be * immediately freed, we loop through the list trying to restore * vmemmap individually in the hope that someone elsewhere may * have done something to cause success (such as freeing some * memory). If unable to restore a hugetlb page, the hugetlb * page is made a surplus page and removed from the list. * If are able to restore vmemmap and free one hugetlb page, we * quit processing the list to retry the bulk operation. */ list_for_each_entry_safe(folio, t_folio, folio_list, lru) if (hugetlb_vmemmap_restore_folio(h, folio)) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); break; } } } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *folio_list) { long ret; struct folio *folio, *t_folio; LIST_HEAD(non_hvo_folios); /* * First allocate required vmemmmap (if necessary) for all folios. * Carefully handle errors and free up any available hugetlb pages * in an effort to make forward progress. */ retry: ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); if (ret < 0) { bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); goto retry; } /* * At this point, list should be empty, ret should be >= 0 and there * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); hugetlb_set_folio_subpool(folio, NULL); if (folio_test_anon(folio)) __ClearPageAnonExclusive(&folio->page); folio->mapping = NULL; restore_reserve = folio_test_hugetlb_restore_reserve(folio); folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_folio(hstate_index(h), pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Must be called with the hugetlb lock held */ static void __prep_account_new_huge_page(struct hstate *h, int nid) { lockdep_assert_held(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; } static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { init_new_hugetlb_folio(h, folio); hugetlb_vmemmap_optimize_folio(h, folio); } static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } static bool __prep_compound_gigantic_folio(struct folio *folio, unsigned int order, bool demote) { int i, j; int nr_pages = 1 << order; struct page *p; __folio_clear_reserved(folio); for (i = 0; i < nr_pages; i++) { p = folio_page(folio, i); /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic * hugepages and clear the PG_reserved bit from all tail pages * too. Otherwise drivers using get_user_pages() to access tail * pages may get the reference counting wrong if they see * PG_reserved set on a tail page (despite the head page not * having PG_reserved set). Enforcing this consistency between * head and tail pages allows drivers to optimize away a check * on the head page when they need know if put_page() is needed * after get_user_pages(). */ if (i != 0) /* head page cleared above */ __ClearPageReserved(p); /* * Subtle and very unlikely * * Gigantic 'page allocators' such as memblock or cma will * return a set of pages with each page ref counted. We need * to turn this set of pages into a compound page with tail * page ref counts set to zero. Code such as speculative page * cache adding could take a ref on a 'to be' tail page. * We need to respect any increased ref count, and only set * the ref count to zero if count is currently 1. If count * is not 1, we return an error. An error return indicates * the set of pages can not be converted to a gigantic page. * The caller who allocated the pages should then discard the * pages using the appropriate free interface. * * In the case of demote, the ref count will be zero. */ if (!demote) { if (!page_ref_freeze(p, 1)) { pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); goto out_error; } } else { VM_BUG_ON_PAGE(page_count(p), p); } if (i != 0) set_compound_head(p, &folio->page); } __folio_set_head(folio); /* we rely on prep_new_hugetlb_folio to set the hugetlb flag */ folio_set_order(folio, order); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_pincount, 0); return true; out_error: /* undo page modifications made above */ for (j = 0; j < i; j++) { p = folio_page(folio, j); if (j != 0) clear_compound_head(p); set_page_refcounted(p); } /* need to clear PG_reserved on remaining tail pages */ for (; j < nr_pages; j++) { p = folio_page(folio, j); __ClearPageReserved(p); } return false; } static bool prep_compound_gigantic_folio(struct folio *folio, unsigned int order) { return __prep_compound_gigantic_folio(folio, order, false); } static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, unsigned int order) { return __prep_compound_gigantic_folio(folio, order, true); } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); struct folio *folio; bool alloc_try_hard = true; bool retry = true; /* * By default we always try hard to allocate the folio with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; gfp_mask |= __GFP_COMP|__GFP_NOWARN; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: folio = __folio_alloc(gfp_mask, order, nid, nmask); if (folio && !folio_ref_freeze(folio, 1)) { folio_put(folio); if (retry) { /* retry once */ retry = false; goto retry; } /* WOW! twice in a row. */ pr_warn("HugeTLB unexpected inflated folio ref count\n"); folio = NULL; } /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a * folio this indicates an overall state change. Clear bit so * that we resume normal 'try hard' allocations. */ if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); return folio; } static struct folio *__alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; bool retry = false; retry: if (hstate_is_gigantic(h)) folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (!folio) return NULL; if (hstate_is_gigantic(h)) { if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { /* * Rare failure to convert pages to compound page. * Free pages and try again - ONCE! */ free_gigantic_folio(folio, huge_page_order(h)); if (!retry) { retry = true; goto retry; } return NULL; } } return folio; } static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(h, folio); return folio; } /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages * * Note that returned page is 'frozen': ref count of head page and all tail * pages is zero. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (!folio) return NULL; prep_new_hugetlb_folio(h, folio, folio_nid(folio)); return folio; } static void prep_and_add_allocated_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); /* Add all new pool pages to free lists in one lock cycle */ spin_lock_irqsave(&hugetlb_lock, flags); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); } spin_unlock_irqrestore(&hugetlb_lock, flags); } /* * Allocates a fresh hugetlb page in a node interleaved manner. The page * will later be added to the appropriate hugetlb pool. */ static struct folio *alloc_pool_huge_folio(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry, int *next_node) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nr_nodes, node; for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (folio) return folio; } return NULL; } /* * Remove huge page from pool from next node to free. Attempt to keep * persistent huge pages more or less balanced over allowed nodes. * This routine only 'removes' the hugetlb page. The caller must make * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { folio = list_entry(h->hugepage_freelists[node].next, struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } return folio; } /* * Dissolve a given free hugetlb folio into free buddy pages. This function * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages * when the system is under memory pressure and the feature of * freeing unused vmemmap pages associated with each hugetlb page * is enabled. * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } if (!folio_ref_count(folio)) { struct hstate *h = folio_hstate(folio); if (!available_huge_pages(h)) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } remove_hugetlb_folio(h, folio, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* * Normally update_and_free_hugtlb_folio will allocate required vmemmmap * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. * * The folio_test_hugetlb check here is because * remove_hugetlb_folio will clear hugetlb folio flag for * non-vmemmap optimized hugetlb folios. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, false); h->max_huge_pages++; goto out; } } else rc = 0; update_and_free_hugetlb_folio(h, folio, false); return rc; } out: spin_unlock_irq(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_hugetlb_folio() returns with an error, all * free hugetlb folios that were dissolved before that error are lost. */ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; if (!hugepages_supported()) return rc; order = huge_page_order(&default_hstate); for_each_hstate(h) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { folio = pfn_folio(pfn); rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock_irq(&hugetlb_lock); folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_folio * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); free_huge_folio(folio); return NULL; } h->surplus_huge_pages++; h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); return folio; } static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) return NULL; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; /* fresh huge pages are frozen */ folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ folio_set_hugetlb_temporary(folio); return folio; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask | __GFP_NOWARN; gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; } /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { struct folio *folio; folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); return folio; } } spin_unlock_irq(&hugetlb_lock); /* We cannot fallback to other nodes, as we could break the per-node pool. */ if (!allow_alloc_fallback) gfp_mask |= __GFP_THISNODE; return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, long delta) __must_hold(&hugetlb_lock) { LIST_HEAD(surplus_list); struct folio *folio, *tmp; int ret; long i; long needed, allocated; bool alloc_ok = true; lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; ret = -ENOMEM; retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), NUMA_NO_NODE, NULL); if (!folio) { alloc_ok = false; break; } list_add(&folio->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ enqueue_hugetlb_folio(h, folio); } free: spin_unlock_irq(&hugetlb_lock); /* * Free unnecessary surplus pages to the buddy allocator. * Pages have no ref count, call free_huge_folio directly. */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) free_huge_folio(folio); spin_lock_irq(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { struct folio *folio; folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); if (!folio) goto out; list_add(&folio->lru, &page_list); } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. * * vma_del_reservation is used in error paths where an entry in the reserve * map was created during huge page allocation and must be removed. It is to * be called after calling vma_needs_reservation to determine if a reservation * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; case VMA_DEL_RESV: if (vma->vm_flags & VM_MAYSHARE) { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } else { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. * * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret > 0) return 0; if (ret == 0) return 1; return ret; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } static long vma_del_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); } /* * This routine is called to restore reservation information on error paths. * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the folio consumed the reservation. * hugetlb_restore_reserve is set in the folio. * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_folio later in the error path will increment the * global reserve count. But, free_huge_folio does not have enough context * to adjust the reservation map. This case deals primarily with private * mappings. Adjust the reserve map here to be consistent with global * reserve count adjustments to be made by free_huge_folio. Make sure the * reserve map indicates there is a reservation present. * * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio) { long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear hugetlb_restore_reserve so * that global reserve count will not be incremented * by free_huge_folio. This will make it appear * as though the reservation for this folio was * consumed. This may prevent the task from * faulting in the folio at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) (void)vma_add_reservation(h, vma, address); else vma_end_reservation(h, vma, address); } else { if (!rc) { /* * This indicates there is an entry in the reserve map * not added by alloc_hugetlb_folio. We know it was added * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. */ rc = vma_del_reservation(h, vma, address); if (rc < 0) /* * VERY rare out of memory condition. Since * we can not delete the entry, set * hugetlb_restore_reserve so that the reserve * count will be incremented when the folio * is freed. This reserve will be consumed * on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else if (rc < 0) { /* * Rare out of memory condition from * vma_needs_reservation call. Memory allocation is * only attempted if a new entry is needed. Therefore, * this implies there is not an entry in the * reserve map. * * For shared mappings, no entry in the map indicates * no reservation. We are done. */ if (!(vma->vm_flags & VM_MAYSHARE)) /* * For private mappings, no entry indicates * a reservation is present. Since we can * not add an entry, set hugetlb_restore_reserve * on the folio so reserve count will be * incremented when freed. This reserve will * be consumed on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else /* * No reservation present, do nothing */ vma_end_reservation(h, vma, address); } } /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one * @h: struct hstate old page belongs to * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { bool isolated; /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); isolated = isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ spin_unlock_irq(&hugetlb_lock); cond_resched(); goto retry; } else { if (!new_folio) { spin_unlock_irq(&hugetlb_lock); new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); if (!new_folio) return -ENOMEM; __prep_new_hugetlb_folio(h, new_folio); goto retry; } /* * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() * and enqueue_hugetlb_folio() for new_folio. The counters will * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); enqueue_hugetlb_folio(h, new_folio); /* * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); if (new_folio) { /* Folio has a zero ref count, but needs a ref to be freed */ folio_ref_unfreeze(new_folio, 1); update_and_free_hugetlb_folio(h, new_folio, false); } return ret; } int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { struct hstate *h; struct folio *folio = page_folio(page); int ret = -EBUSY; /* * The page might have been dissolved from under our feet, so make sure * to carefully check the state under the lock. * Return success when racing as if we dissolved the page ourselves. */ spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { h = folio_hstate(folio); } else { spin_unlock_irq(&hugetlb_lock); return 0; } spin_unlock_irq(&hugetlb_lock); /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ if (hstate_is_gigantic(h)) return -ENOMEM; if (folio_ref_count(folio) && isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); return ret; } struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; long map_chg, map_commit, nr_pages = pages_per_huge_page(h); long gbl_chg; int memcg_charge_ret, ret, idx; struct hugetlb_cgroup *h_cg = NULL; struct mem_cgroup *memcg; bool deferred_reserve; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; memcg = get_mem_cgroup_from_current(); memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages); if (memcg_charge_ret == -ENOMEM) { mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } idx = hstate_index(h); /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); if (map_chg < 0) { if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } /* * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Allocations for MAP_NORESERVE mappings also need to be * checked against any subpool limit. */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; /* * Even though there was no reservation in the region/reserve * map, there could be reservations associated with the * subpool that can be used. This would be indicated if the * return value of hugepage_subpool_get_pages() is zero. * However, if avoid_reserve is specified we still avoid even * the subpool reservations. */ if (avoid_reserve) gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. */ deferred_reserve = map_chg || avoid_reserve; if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } spin_unlock_irq(&hugetlb_lock); hugetlb_set_folio_subpool(folio, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) { spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); spin_unlock_irq(&hugetlb_lock); } } if (!memcg_charge_ret) mem_cgroup_commit_charge(folio, memcg); mem_cgroup_put(memcg); return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (deferred_reserve) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); out_end_reservation: vma_end_reservation(h, vma, addr); if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOSPC); } int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h, int nid) { struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node = nid; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; goto found; } /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_MEMORY]) { m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). */ if (!m) return 0; goto found; } found: /* * Only initialize the head struct page in memmap_init_reserved_pages, * rest of the struct pages will be initialized by the HugeTLB * subsystem itself. * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages[node]); m->hstate = h; return 1; } /* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, unsigned long start_page_number, unsigned long end_page_number) { enum zone_type zone = zone_idx(folio_zone(folio)); int nid = folio_nid(folio); unsigned long head_pfn = folio_pfn(folio); unsigned long pfn, end_pfn = head_pfn + end_page_number; int ret; for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); prep_compound_tail((struct page *)folio, pfn - head_pfn); ret = page_ref_freeze(page, 1); VM_BUG_ON(!ret); } } static void __init hugetlb_folio_init_vmemmap(struct folio *folio, struct hstate *h, unsigned long nr_pages) { int ret; /* Prepare folio head */ __folio_clear_reserved(folio); __folio_set_head(folio); ret = folio_ref_freeze(folio, 1); VM_BUG_ON(!ret); /* Initialize the necessary tail struct pages */ hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); prep_compound_head((struct page *)folio, huge_page_order(h)); } static void __init prep_and_add_bootmem_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { if (!folio_test_hugetlb_vmemmap_optimized(folio)) { /* * If HVO fails, initialize all tail struct pages * We do not worry about potential long lock hold * time as this is early in boot and there should * be no contention. */ hugetlb_folio_init_tail_vmemmap(folio, HUGETLB_VMEMMAP_RESERVE_PAGES, pages_per_huge_page(h)); } /* Subdivide locks to achieve better parallel performance */ spin_lock_irqsave(&hugetlb_lock, flags); __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages. */ static void __init gather_bootmem_prealloc_node(unsigned long nid) { LIST_HEAD(folio_list); struct huge_bootmem_page *m; struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry(m, &huge_boot_pages[nid], list) { struct page *page = virt_to_page(m); struct folio *folio = (void *)page; h = m->hstate; /* * It is possible to have multiple huge page sizes (hstates) * in this list. If so, process each size separately. */ if (h != prev_h && prev_h != NULL) prep_and_add_bootmem_folios(prev_h, &folio_list); prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); hugetlb_folio_init_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES); init_new_hugetlb_folio(h, folio); list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. */ adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } prep_and_add_bootmem_folios(h, &folio_list); } static void __init gather_bootmem_prealloc_parallel(unsigned long start, unsigned long end, void *arg) { int nid; for (nid = start; nid < end; nid++) gather_bootmem_prealloc_node(nid); } static void __init gather_bootmem_prealloc(void) { struct padata_mt_job job = { .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, .size = num_node_state(N_MEMORY), .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), .numa_aware = true, }; padata_do_multithreaded(&job); } static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h, nid)) break; } else { struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); if (!folio) break; free_huge_folio(folio); /* free it into the hugepage allocator */ } cond_resched(); } if (i == h->max_huge_pages_node[nid]) return; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", h->max_huge_pages_node[nid], buf, nid, i); h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); h->max_huge_pages_node[nid] = i; } static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h) { int i; bool node_specific_alloc = false; for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; } } return node_specific_alloc; } static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h) { if (allocated < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, allocated); h->max_huge_pages = allocated; } } static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg) { struct hstate *h = (struct hstate *)arg; int i, num = end - start; nodemask_t node_alloc_noretry; LIST_HEAD(folio_list); int next_node = first_online_node; /* Bit mask controlling how hard we retry per-node allocations.*/ nodes_clear(node_alloc_noretry); for (i = 0; i < num; ++i) { struct folio *folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], &node_alloc_noretry, &next_node); if (!folio) break; list_move(&folio->lru, &folio_list); cond_resched(); } prep_and_add_allocated_folios(h, &folio_list); } static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h) { unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; cond_resched(); } return i; } static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) { struct padata_mt_job job = { .fn_arg = h, .align = 1, .numa_aware = true }; job.thread_fn = hugetlb_pages_alloc_boot_node; job.start = 0; job.size = h->max_huge_pages; /* * job.max_threads is twice the num_node_state(N_MEMORY), * * Tests below indicate that a multiplier of 2 significantly improves * performance, and although larger values also provide improvements, * the gains are marginal. * * Therefore, choosing 2 as the multiplier strikes a good balance between * enhancing parallel processing capabilities and maintaining efficient * resource management. * * +------------+-------+-------+-------+-------+-------+ * | multiplier | 1 | 2 | 3 | 4 | 5 | * +------------+-------+-------+-------+-------+-------+ * | 256G 2node | 358ms | 215ms | 157ms | 134ms | 126ms | * | 2T 4node | 979ms | 679ms | 543ms | 489ms | 481ms | * | 50G 2node | 71ms | 44ms | 37ms | 30ms | 31ms | * +------------+-------+-------+-------+-------+-------+ */ job.max_threads = num_node_state(N_MEMORY) * 2; job.min_chunk = h->max_huge_pages / num_node_state(N_MEMORY) / 2; padata_do_multithreaded(&job); return h->nr_huge_pages; } /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. * - For gigantic pages, this is called early in the boot process and * pages are allocated from memblock allocated or something similar. * Gigantic pages are actually added to pools later with the routine * gather_bootmem_prealloc. * - For non-gigantic pages, this is called later in the boot process after * all of mm is up and functional. Pages are allocated from buddy and * then added to hugetlb pools. */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long allocated; static bool initialized __initdata; /* skip gigantic hugepages allocation if hugetlb_cma enabled */ if (hstate_is_gigantic(h) && hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); return; } /* hugetlb_hstate_alloc_pages will be called many times, initialize huge_boot_pages once */ if (!initialized) { int i = 0; for (i = 0; i < MAX_NUMNODES; i++) INIT_LIST_HEAD(&huge_boot_pages[i]); initialized = true; } /* do node specific alloc */ if (hugetlb_hstate_alloc_pages_specific_nodes(h)) return; /* below will do all node balanced alloc */ if (hstate_is_gigantic(h)) allocated = hugetlb_gigantic_pages_alloc_boot(h); else allocated = hugetlb_pages_alloc_boot(h); hugetlb_hstate_alloc_pages_errcheck(allocated, h); } static void __init hugetlb_init_hstates(void) { struct hstate *h, *h2; for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); /* * Set demote order for each hstate. Note that * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. * - If CMA allocation is possible, we can not demote * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) continue; if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) continue; for_each_hstate(h2) { if (h2 == h) continue; if (h2->order < h->order && h2->order > h->demote_order) h->demote_order = h2->order; } } } static void __init report_hugepages(void) { struct hstate *h; for_each_hstate(h) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; /* * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; if (folio_test_highmem(folio)) continue; remove_hugetlb_folio(h, folio, false); list_add(&folio->lru, &page_list); } } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count; unsigned long allocated; struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; /* * resize_lock mutex prevents concurrent adjustments to number of * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += persistent_huge_pages(h) - (h->nr_huge_pages_node[nid] - h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_hugetlb_folio() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } allocated = 0; while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page * and reducing the surplus. */ spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry, &h->next_nid_to_alloc); if (!folio) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } list_add(&folio->lru, &page_list); allocated++; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } spin_lock_irq(&hugetlb_lock); } /* Add allocated pages to the pool */ if (!list_empty(&page_list)) { spin_unlock_irq(&hugetlb_lock); prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_hugetlb_folio() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); /* * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); if (!folio) break; list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) { int i, nid = folio_nid(folio); struct hstate *target_hstate; struct page *subpage; struct folio *inner_folio; int rc = 0; target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); remove_hugetlb_folio_for_demote(h, folio, false); spin_unlock_irq(&hugetlb_lock); /* * If vmemmap already existed for folio, the remove routine above would * have cleared the hugetlb folio flag. Hence the folio is technically * no longer a hugetlb folio. hugetlb_vmemmap_restore_folio can only be * passed hugetlb folios and will BUG otherwise. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { /* Allocation of vmemmmap failed, we can not demote folio */ spin_lock_irq(&hugetlb_lock); folio_ref_unfreeze(folio, 1); add_hugetlb_folio(h, folio, false); return rc; } } /* * Use destroy_compound_hugetlb_folio_for_demote for all huge page * sizes as it will not ref count folios. */ destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(h)); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * * Note that we already hold h->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ mutex_lock(&target_hstate->resize_lock); for (i = 0; i < pages_per_huge_page(h); i += pages_per_huge_page(target_hstate)) { subpage = folio_page(folio, i); inner_folio = page_folio(subpage); if (hstate_is_gigantic(target_hstate)) prep_compound_gigantic_folio_for_demote(inner_folio, target_hstate->order); else prep_compound_page(subpage, target_hstate->order); folio_change_private(inner_folio, NULL); prep_new_hugetlb_folio(target_hstate, inner_folio, nid); free_huge_folio(inner_folio); } mutex_unlock(&target_hstate->resize_lock); spin_lock_irq(&hugetlb_lock); /* * Not absolutely necessary, but for consistency update max_huge_pages * based on pool changes for the demoted page. */ h->max_huge_pages--; target_hstate->max_huge_pages += pages_per_huge_page(h) / pages_per_huge_page(target_hstate); return rc; } static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) __must_hold(&hugetlb_lock) { int nr_nodes, node; struct folio *folio; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ if (!h->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { list_for_each_entry(folio, &h->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; return demote_free_hugetlb_folio(h, folio); } } /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR_WO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_WO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock_irq(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static ssize_t demote_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned long nr_demote; unsigned long nr_available; nodemask_t nodes_allowed, *n_mask; struct hstate *h; int err; int nid; err = kstrtoul(buf, 10, &nr_demote); if (err) return err; h = kobj_to_hstate(kobj, &nid); if (nid != NUMA_NO_NODE) { init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } else { n_mask = &node_states[N_MEMORY]; } /* Synchronize with other sysfs operations modifying huge pages */ mutex_lock(&h->resize_lock); spin_lock_irq(&hugetlb_lock); while (nr_demote) { /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. */ if (nid != NUMA_NO_NODE) nr_available = h->free_huge_pages_node[nid]; else nr_available = h->free_huge_pages; nr_available -= h->resv_huge_pages; if (!nr_available) break; err = demote_pool_huge_page(h, n_mask); if (err) break; nr_demote--; } spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); if (err) return err; return len; } HSTATE_ATTR_WO(demote); static ssize_t demote_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; return sysfs_emit(buf, "%lukB\n", demote_size); } static ssize_t demote_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct hstate *h, *demote_hstate; unsigned long demote_size; unsigned int demote_order; demote_size = (unsigned long)memparse(buf, NULL); demote_hstate = size_to_hstate(demote_size); if (!demote_hstate) return -EINVAL; demote_order = demote_hstate->order; if (demote_order < HUGETLB_PAGE_ORDER) return -EINVAL; /* demote order must be smaller than hstate order */ h = kobj_to_hstate(kobj, NULL); if (demote_order >= h->order) return -EINVAL; /* resize_lock synchronizes access to demote size and writes */ mutex_lock(&h->resize_lock); h->demote_order = demote_order; mutex_unlock(&h->resize_lock); return count; } HSTATE_ATTR(demote_size); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static struct attribute *hstate_demote_attrs[] = { &demote_size_attr.attr, &demote_attr.attr, NULL, }; static const struct attribute_group hstate_demote_attr_group = { .attrs = hstate_demote_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } if (h->demote_order) { retval = sysfs_create_group(hstate_kobjs[hi], &hstate_demote_attr_group); if (retval) { pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group); kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } } return 0; } #ifdef CONFIG_NUMA static bool hugetlb_sysfs_initialized __ro_after_init; /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); struct kobject *hstate_kobj = nhs->hstate_kobjs[idx]; if (!hstate_kobj) continue; if (h->demote_order) sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group); sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group); kobject_put(hstate_kobj); nhs->hstate_kobjs[idx] = NULL; } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (!hugetlb_sysfs_initialized) return; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_online_node(nid) hugetlb_register_node(node_devices[nid]); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif #ifdef CONFIG_CMA static void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_check(void) { } #endif static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s", h->name); } #ifdef CONFIG_NUMA hugetlb_sysfs_initialized = true; #endif hugetlb_register_all_nodes(); } #ifdef CONFIG_SYSCTL static void hugetlb_sysctl_init(void); #else static inline void hugetlb_sysctl_init(void) { } #endif static int __init hugetlb_init(void) { int i; BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < __NR_HPAGEFLAGS); if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); h = &hstates[hugetlb_max_hstate++]; mutex_init(&h->resize_lock); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/SZ_1K); parsed_hstate = h; } bool __init __weak hugetlb_node_alloc_supported(void) { return true; } static void __init hugepages_clear_pages_in_node(void) { if (!hugetlb_max_hstate) { default_hstate_max_huge_pages = 0; memset(default_hugepages_in_node, 0, sizeof(default_hugepages_in_node)); } else { parsed_hstate->max_huge_pages = 0; memset(parsed_hstate->max_huge_pages_node, 0, sizeof(parsed_hstate->max_huge_pages_node)); } } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; int node = NUMA_NO_NODE; int count; unsigned long tmp; char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 1; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } while (*p) { count = 0; if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; /* Parameter is node format */ if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 1; } if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; if (!hugetlb_max_hstate) default_hugepages_in_node[node] = tmp; else parsed_hstate->max_huge_pages_node[node] = tmp; *mhp += tmp; /* Go to parse next node*/ if (p[count] == ',') p += count + 1; else break; } else { if (p != s) goto invalid; *mhp = tmp; break; } } /* * Global state is always initialized later in hugetlb_init. * But we need to allocate gigantic hstates here early to still * use the bootmem allocator. */ if (hugetlb_max_hstate && hstate_is_gigantic(parsed_hstate)) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); hugepages_clear_pages_in_node(); return 1; } __setup("hugepages=", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return 1; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return 1; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 1; } __setup("hugepagesz=", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return 1; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; } return 1; } __setup("default_hugepagesz=", default_hugepagesz_setup); static nodemask_t *policy_mbind_nodemask(gfp_t gfp) { #ifdef CONFIG_NUMA struct mempolicy *mpol = get_task_policy(current); /* * Only enforce MPOL_BIND policy which overlaps with cpuset policy * (from policy_nodemask) specifically for hugetlb case */ if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) return &mpol->nodes; #endif return NULL; } static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mbind_nodemask; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } static int hugetlb_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ static int hugetlb_overcommit_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock_irq(&hugetlb_lock); } out: return ret; } static struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_sysctl_handler, }, #ifdef CONFIG_NUMA { .procname = "nr_hugepages_mempolicy", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, #endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_overcommit_handler, }, }; static void hugetlb_sysctl_init(void) { register_sysctl_init("vm", hugetlb_table); } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, huge_page_size(h) / SZ_1K); } seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo_node(int nid) { struct hstate *h; if (!hugepages_supported()) return; for_each_hstate(h) printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", K(atomic_long_read(&mm->hugetlb_usage))); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; if (!delta) return 0; spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock_irq(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } /* * vma_lock structure for sharable mappings is vma specific. * Clear old pointer (if copied via vm_area_dup) and allocate * new structure. Before clearing, make sure vma_lock is not * for this vma. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock) { if (vma_lock->vma != vma) { vma->vm_private_data = NULL; hugetlb_vma_lock_alloc(vma); } else pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); } else hugetlb_vma_lock_alloc(vma); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; hugetlb_vma_lock_free(vma); resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. */ if (addr & ~PUD_MASK) { /* * hugetlb_vm_op_split is called right before we attempt to * split the VMA. We will need to unshare PMDs in the old and * new VMAs, so let's unshare before we split. */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) hugetlb_unshare_pmds(vma, floor, ceil); } return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { entry = huge_pte_wrprotect(mk_huge_pte(page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry; struct folio *pte_folio; unsigned long addr; bool cow = is_cow_mapping(src_vma->vm_flags); struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; unsigned long last_addr_mask; int ret = 0; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings the vma lock must be held before * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ hugetlb_vma_lock_read(src_vma); } last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } /* * If the pagetables are shared don't copy or take references. * * dst_pte == src_pte is the common case of src/dest sharing. * However, src could have 'unshared' and dst shares with * another vma. So page_count of ptep page is checked instead * to reliably determine whether pte is shared. */ if (page_count(virt_to_page(dst_pte)) > 1) { addr |= last_addr_mask; continue; } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); again: if (huge_pte_none(entry)) { /* * Skip if src entry none. */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_pte); pte_folio = page_folio(pte_page(entry)); folio_get(pte_folio); /* * Failing to duplicate the anon rmap is a rare case * where we see pinned hugetlb pages while they're * prone to COW. We need to do the COW earlier during * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ new_folio = alloc_hugetlb_folio(dst_vma, addr, 1); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); break; } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; } if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) { raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } else { hugetlb_vma_unlock_read(src_vma); } return ret; } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; pte_t pte; dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); /* * We don't have to worry about the ordering of src and dst ptlocks * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); if (src_ptl != dst_ptl) spin_unlock(src_ptl); spin_unlock(dst_ptl); } int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { struct hstate *h = hstate_vma(vma); struct address_space *mapping = vma->vm_file->f_mapping; unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* * In case of shared PMDs, we should cover the maximum possible * range. */ flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } if (huge_pte_none(huge_ptep_get(src_pte))) continue; if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { shared_pmd = true; old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); return len + old_addr - old_end; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); bool adjust_reservation = false; unsigned long last_addr_mask; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to * drop the uffd-wp bit in this zap, then replace the * pte with a marker. */ if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { if (page != ref_page) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(page_folio(page)); /* * Restore the reservation for anonymous page, otherwise the * backing page could be stolen by someone. * If there we are freeing a surplus, do not set the restore * reservation bit. */ if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(page_folio(page))) { folio_set_hugetlb_restore_reserve(page_folio(page)); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } spin_unlock(ptl); /* * Adjust the reservation for the region that will have the * reserve restored. Keep in mind that vma_needs_reservation() changes * resv->adds_in_progress if it succeeds. If this is not done, * do_exit() will not see it, and will keep the reservation * forever. */ if (adjust_reservation) { int rc = vma_needs_reservation(h, vma, address); if (rc < 0) /* Pressumably allocate_file_region_entries failed * to allocate a file_region struct. Clear * hugetlb_restore_reserve so that global reserve * count will not be incremented by free_huge_folio. * Act as if we consumed the reservation. */ folio_clear_hugetlb_restore_reserve(page_folio(page)); else if (rc) vma_add_reservation(h, vma, address); } tlb_remove_page_size(tlb, page, huge_page_size(h)); /* * Bail out after unmapping reference page if supplied */ if (ref_page) break; } tlb_end_vma(tlb, vma); /* * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We * could defer the flush until now, since by holding i_mmap_rwsem we * guaranteed that the last refernece would not be dropped. But we must * do the flushing before we return, as otherwise i_mmap_rwsem will be * dropped and the last reference to the shared PMDs page might be * dropped as well. * * In theory we could defer the freeing of the PMD pages as well, but * huge_pmd_unshare() relies on the exact page_count for the PMD page to * detect sharing, so we cannot defer the release of the page either. * Instead, do flush now. */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); } void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); } void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { zap_flags_t zap_flags = details ? details->zap_flags : 0; if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* * Unlock and free the vma lock before releasing i_mmap_rwsem. * When the vma_lock is freed, this makes the vma ineligible * for pmd sharing. And, i_mmap_rwsem is required to set up * pmd sharing. This is important as page tables for this * unmapped range will be asynchrously deleted. If the page * tables are shared, there will be issues when accessed by * someone else. */ __hugetlb_vma_unlock_write_free(vma); } else { hugetlb_vma_unlock_write(vma); } if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; pte_t pte = huge_ptep_get(vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; int outside_reserve = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; /* * Never handle CoW for uffd-wp protected pages. It should be only * handled when the uffd-wp protection is removed. * * Note that only the CoW optimization path (in hugetlb_no_page()) * can trigger this, because hugetlb_fault() will always resolve * uffd-wp bit first. */ if (!unshare && huge_pte_uffd_wp(pte)) return 0; /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. */ if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) return VM_FAULT_SIGSEGV; /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } old_folio = page_folio(pte_page(pte)); delayacct_wpcopy_start(); retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive * owner and can reuse this page. * * Note that we don't rely on the (safer) folio refcount here, because * copying the hugetlb folio when there are unexpected (temporary) * folio references could harm simple fork()+exit() users when * we run out of free hugetlb folios: we would have to kill processes * in scenarios that used to work. As a side effect, there can still * be leaks between processes, for example, with FOLL_GET users. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { if (!PageAnonExclusive(&old_folio->page)) { folio_move_anon_rmap(old_folio, vma); SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) set_huge_ptep_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(folio_test_anon(old_folio) && PageAnonExclusive(&old_folio->page), &old_folio->page); /* * If the process that created a MAP_PRIVATE mapping is about to * perform a COW due to a shared page count, attempt to satisfy * the allocation without using the existing reserves. The pagecache * page is used to determine if the reserve at this address was * consumed or not. If reserves were used, a partial faulted mapping * at the time of fork() could consume its reserves on COW instead * of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_folio != pagecache_folio) outside_reserve = 1; folio_get(old_folio); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve); if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (outside_reserve) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; folio_put(old_folio); /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); unmap_ref_private(mm, vma, &old_folio->page, vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ delayacct_wpcopy_end(); return 0; } ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out_release_all; if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_release_all; } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare); /* Break COW or unshare */ huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* * No restore in case of successful pagetable update (Break COW or * unshare) */ if (new_folio != old_folio) restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; } /* * Return whether there is a pagecache page to back given address within VMA. */ bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); if (IS_ERR(folio)) return false; folio_put(folio); return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); if (unlikely(err)) { __folio_clear_locked(folio); return err; } folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf, struct address_space *mapping, unsigned long reason) { u32 hash; /* * vma_lock and hugetlb_fault_mutex must be dropped before handling * userfault. Also mmap_lock could be dropped due to handling * userfault, any vma operation should be careful from here. */ hugetlb_vma_unlock_read(vmf->vma); hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(vmf, reason); } /* * Recheck pte with pgtable lock. Returns true if pte didn't change, or * false if pte changed or is changing. */ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, pte_t *ptep, pte_t old_pte) { spinlock_t *ptl; bool same; ptl = huge_pte_lock(h, mm, ptep); same = pte_same(huge_ptep_get(ptep), old_pte); spin_unlock(ptl); return same; } static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct folio *folio; pte_t new_pte; bool new_folio, new_pagecache_folio = false; u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW/unsharing. Warn that such a situation has occurred as it may not * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ new_folio = false; folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { /* * Since hugetlb_no_page() was examining pte * without pgtable lock, we need to re-test under * lock because the pte may not be stable and could * have changed from under us. Try to detect * either changed or during-changing ptes and retry * properly when needed. * * Note that userfaultfd is actually fine with * false positives (e.g. caused by pte changed), * but not wrong logical events (e.g. caused by * reading a pte during changing). The latter can * confuse the userspace, so the strictness is very * much preferred. E.g., MISSING event should * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MISSING); } if (!(vma->vm_flags & VM_MAYSHARE)) { ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; } folio = alloc_hugetlb_folio(vma, vmf->address, 0); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } clear_huge_page(&folio->page, vmf->real_address, pages_per_huge_page(h)); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { int err = hugetlb_add_to_page_cache(folio, mapping, vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone * else consumed the reservation since hugetlb * fault mutex is held when add a hugetlb page * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ restore_reserve_on_error(h, vma, vmf->address, folio); folio_put(folio); ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); anon_rmap = 1; } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MINOR); } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf->address); } vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(vmf->pte), vmf->orig_pte)) goto backout; if (anon_rmap) hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ if (unlikely(pte_marker_uffd_wp(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_wp(folio, vmf); } spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ if (new_folio) folio_set_hugetlb_migratable(folio); folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(vmf->ptl); backout_unlocked: if (new_folio && !new_pagecache_folio) restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { vm_fault_t ret; u32 hash; struct folio *folio = NULL; struct folio *pagecache_folio = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), .real_address = address, .flags = flags, .pgoff = vma_hugecache_offset(h, vma, address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* * Some fields may not be initialized, be careful as it may * be hard to debug if called functions make assumptions */ }; /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ mapping = vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Acquire vma lock before calling huge_pte_alloc and hold * until finished with vmf.pte. This prevents huge_pmd_unshare from * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } vmf.orig_pte = huge_ptep_get(vmf.pte); if (huge_pte_none_mostly(vmf.orig_pte)) { if (is_pte_marker(vmf.orig_pte)) { pte_marker marker = pte_marker_get(pte_to_swp_entry(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } } /* * Other PTE markers should be handled the same way as none PTE. * * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mapping, &vmf); } ret = 0; /* * vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this * point, so this check prevents the kernel from going below assuming * that we have an active hugepage in pagecache. This goto expects * the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned) * check will properly handle it. */ if (!pte_present(vmf.orig_pte)) { if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the * huge_pte_lockptr() later in * migration_entry_wait_huge(). The vma lock will * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); migration_entry_wait_huge(vma, vmf.pte); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte))) ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } /* * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. Also lookup the pagecache page now as it is used to * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf.address); pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, vmf.pgoff); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(&vmf, VM_UFFD_WP); } vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } /* * hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and * pagecache_folio, so here we need take the former one * when folio != pagecache_folio or !pagecache_folio. */ folio = page_folio(pte_page(vmf.orig_pte)); if (folio != pagecache_folio) if (!folio_trylock(folio)) { need_wait_lock = 1; goto out_ptl; } folio_get(folio); if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { ret = hugetlb_wp(pagecache_folio, &vmf); goto out_put_page; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } vmf.orig_pte = pte_mkyoung(vmf.orig_pte); if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, vmf.address, vmf.pte); out_put_page: if (folio != pagecache_folio) folio_unlock(folio); folio_put(folio); out_ptl: spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } out_mutex: hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and * the page is not used after unlocked before returning from the current * page fault. So we are safe from accessing freed page, even if we wait * here without taking refcount. */ if (need_wait_lock) folio_wait_locked(folio); return ret; } #ifdef CONFIG_USERFAULTFD /* * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). */ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); /* * This is used to allocate a temporary hugetlb to hold the copied * content, which will then be copied again to the final hugetlb * consuming a reservation. Set the alloc_fallback to false to indicate * that breaking the per-node hugetlb pool is not allowed in this case. */ folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; } /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; int writable; bool folio_in_pagecache = false; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { ptl = huge_pte_lock(h, dst_mm, dst_pte); /* Don't overwrite any existing PTEs (even markers) */ if (!huge_pte_none(huge_ptep_get(dst_pte))) { spin_unlock(ptl); return -EEXIST; } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h)); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); return 0; } if (is_continue) { ret = -EFAULT; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*foliop) { /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } ret = copy_folio_from_user(folio, (const void __user *) src_addr, false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; /* Free the allocated folio which may have * consumed a reservation. */ restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied * contents. */ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); if (!folio) { ret = -ENOMEM; goto out; } *foliop = folio; /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { folio_put(*foliop); ret = -EEXIST; *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { folio_put(folio); goto out; } } /* * If we just allocated a new page, we need a memory barrier to ensure * that preceding stores to the page become visible before the * set_pte_at() write. The memory barrier inside __folio_mark_uptodate * is what we need. * * In the case where we have not allocated a new page (is_continue), * the page must already be uptodate. UFFDIO_CONTINUE already includes * an earlier smp_wmb() to ensure that prior stores will be visible * before the set_pte_at() write. */ if (!is_continue) __folio_mark_uptodate(folio); else WARN_ON_ONCE(!folio_test_uptodate(folio)); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; if (folio_test_hwpoison(folio)) goto out_release_unlock; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ ret = -EEXIST; if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; if (folio_in_pagecache) hugetlb_add_file_rmap(folio); else hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ if (wp_enabled || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; _dst_pte = make_huge_pte(dst_vma, &folio->page, writable); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not * supported, but we should still be clear in that this page cannot be * thrown away at will, even if write bit not set. */ _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); if (!is_continue) folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; continue; } /* * Userfaultfd wr-protect requires pgtable * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); if (!ptep) { pages = -ENOMEM; break; } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it * happened due to some reason. */ WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { /* Nothing to do. */ } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct page *page = pfn_swap_entry_to_page(entry); pte_t newpte = pte; if (is_writable_migration_entry(entry)) { if (PageAnon(page)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); else entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); pages++; } if (uffd_wp) newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* * Do nothing on a poison marker; page is * corrupted, permissons do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (uffd_wp) pte = huge_pte_mkuffd_wp(pte); else if (uffd_wp_resolve) pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } else { /* None pte */ if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), psize); } spin_unlock(ptl); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. If we actually * did unshare a page of pmds, flush the range corresponding to the pud. */ if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new * page. * * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); return pages > 0 ? (pages << h->order) : pages; } /* Return true if reservation was successful, false otherwise. */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg = -1, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return false; } /* * vma specific semaphore used for pmd sharing and fault/truncation * synchronization */ hugetlb_vma_lock_alloc(vma); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return true; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) goto out_err; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: hugetlb_vma_lock_free(vma); if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_resv_map(vma, NULL); } return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. * * Note that !resv_map implies freed == 0. So (chg - freed) * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. * * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || !range_in_vma(svma, sbase, s_end) || !svma->vm_private_data) return 0; return saddr; } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { unsigned long start = addr & PUD_MASK; unsigned long end = start + PUD_SIZE; #ifdef CONFIG_USERFAULTFD if (uffd_disable_huge_pmd_share(vma)) return false; #endif /* * check on proper vm_flags and page table alignment */ if (!(vma->vm_flags & VM_MAYSHARE)) return false; if (!vma->vm_private_data) /* vma lock required for sharing */ return false; if (!range_in_vma(vma, start, end)) return false; return true; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma needs to span at least one aligned PUD size, and the range * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { get_page(virt_to_page(spte)); break; } } } if (!spte) goto out; spin_lock(&mm->page_table_lock); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { put_page(virt_to_page(spte)); } spin_unlock(&mm->page_table_lock); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_unlock_read(mapping); return pte; } /* * unmap huge page backed by shared pte. * * Hugetlb pte page is ref counted at the time of mapping. If pte is shared * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) return 0; pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); return 1; } #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share(vma, addr) && pud_none(*pud)) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } if (pte) { pte_t pteval = ptep_get_lockless(pte); BUG_ON(pte_present(pteval) && !pte_huge(pteval)); } return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } /* * Return a mask that can be used to update an address to the last huge * page in a page table page mapping size. Used to skip non-present * page table entries when linearly scanning address ranges. Architectures * with unique huge page to page table relationships can define their own * version of this routine. */ unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); if (hp_size == PUD_SIZE) return P4D_SIZE - PUD_SIZE; else if (hp_size == PMD_SIZE) return PUD_SIZE - PMD_SIZE; else return 0UL; } #else /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /* * These functions are overwritable if your architecture needs its own * behavior. */ bool isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; } int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { *hugetlb = true; if (folio_test_hugetlb_freed(folio)) ret = 0; else if (folio_test_hugetlb_migratable(folio) || unpoison) ret = folio_try_get(folio); else ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; } int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } void folio_putback_active_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { struct hstate *h = folio_hstate(old_folio); hugetlb_cgroup_migrate(old_folio, new_folio); set_page_owner_migrate_reason(&new_folio->page, reason); /* * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (folio_test_hugetlb_temporary(new_folio)) { int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); /* * There is no need to transfer the per-node surplus state * when we do not cross the node. */ if (new_nid == old_nid) return; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock_irq(&hugetlb_lock); } } static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(mm, vma, address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } /* * This function will unconditionally remove all the shared pmd pgtable entries * within the specific vma for a hugetlbfs memory range. */ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { int nid, count = 0; unsigned long tmp; char *s = p; while (*s) { if (sscanf(s, "%lu%n", &tmp, &count) != 1) break; if (s[count] == ':') { if (tmp >= MAX_NUMNODES) break; nid = array_index_nospec(tmp, MAX_NUMNODES); s += count + 1; tmp = memparse(s, &s); hugetlb_cma_size_in_node[nid] = tmp; hugetlb_cma_size += tmp; /* * Skip the separator if have one, otherwise * break the parsing. */ if (*s == ',') s++; else break; } else { hugetlb_cma_size = memparse(p, &p); break; } } return 0; } early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; bool node_specific_cma_alloc = false; int nid; /* * HugeTLB CMA reservation is required for gigantic * huge pages which could not be allocated via the * page allocator. Just warn if there is any change * breaking this assumption. */ VM_WARN_ON(order <= MAX_PAGE_ORDER); cma_reserve_called = true; if (!hugetlb_cma_size) return; for (nid = 0; nid < MAX_NUMNODES; nid++) { if (hugetlb_cma_size_in_node[nid] == 0) continue; if (!node_online(nid)) { pr_warn("hugetlb_cma: invalid node %d specified\n", nid); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; continue; } if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", nid, (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; } else { node_specific_cma_alloc = true; } } /* Validate the CMA size again in case some invalid nodes specified. */ if (!hugetlb_cma_size) return; if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size = 0; return; } if (!node_specific_cma_alloc) { /* * If 3 GB area is requested on a machine with 4 numa nodes, * let's allocate 1 GB on first three nodes and ignore the last one. */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); } reserved = 0; for_each_online_node(nid) { int res; char name[CMA_MAX_NAME]; if (node_specific_cma_alloc) { if (hugetlb_cma_size_in_node[nid] == 0) continue; size = hugetlb_cma_size_in_node[nid]; } else { size = min(per_node, hugetlb_cma_size - reserved); } size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); /* * Note that 'order per bit' is based on smallest size that * may be returned to CMA allocator in the case of * huge page demotion. */ res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, HUGETLB_PAGE_ORDER, false, name, &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); continue; } reserved += size; pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", size / SZ_1M, nid); if (reserved >= hugetlb_cma_size) break; } if (!reserved) /* * hugetlb_cma_size is used to determine if allocations from * cma are possible. Set to zero if no cma regions are set up. */ hugetlb_cma_size = 0; } static void __init hugetlb_cma_check(void) { if (!hugetlb_cma_size || cma_reserve_called) return; pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); } #endif /* CONFIG_CMA */ |
| 7 7 7 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | // SPDX-License-Identifier: GPL-2.0-or-later /* * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> #include <asm/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) { int i; /* whitelist the allowed round counts */ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); for (i = 0; i < nrounds; i += 2) { x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } } /** * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. * The caller has already converted the endianness of the input. This function * also handles incrementing the block counter in the input matrix. */ void chacha_block_generic(u32 *state, u8 *stream, int nrounds) { u32 x[16]; int i; memcpy(x, state, 64); chacha_permute(x, nrounds); for (i = 0; i < ARRAY_SIZE(x); i++) put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); state[12]++; } EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha * skips the final addition of the initial state, and outputs only certain words * of the state. It should not be used for streaming directly. */ void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds) { u32 x[16]; memcpy(x, state, 64); chacha_permute(x, nrounds); memcpy(&stream[0], &x[0], 16); memcpy(&stream[4], &x[12], 16); } EXPORT_SYMBOL(hchacha_block_generic); |
| 42 42 42 41 42 42 42 42 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A security context is a set of security attributes * associated with each subject and object controlled * by the security policy. Security contexts are * externally represented as variable-length strings * that can be interpreted by a user or application * with an understanding of the security policy. * Internally, the security server uses a simple * structure. This structure is private to the * security server and can be changed without affecting * clients of the security server. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_CONTEXT_H_ #define _SS_CONTEXT_H_ #include "ebitmap.h" #include "mls_types.h" #include "security.h" /* * A security context consists of an authenticated user * identity, a role, a type and a MLS range. */ struct context { u32 user; u32 role; u32 type; u32 len; /* length of string in bytes */ struct mls_range range; char *str; /* string representation if context cannot be mapped. */ }; static inline void mls_context_init(struct context *c) { memset(&c->range, 0, sizeof(c->range)); } static inline int mls_context_cpy(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the low level of 'src'. */ static inline int mls_context_cpy_low(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the high level of 'src'. */ static inline int mls_context_cpy_high(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } static inline int mls_context_glblub(struct context *dst, const struct context *c1, const struct context *c2) { struct mls_range *dr = &dst->range; const struct mls_range *r1 = &c1->range, *r2 = &c2->range; int rc = 0; if (r1->level[1].sens < r2->level[0].sens || r2->level[1].sens < r1->level[0].sens) /* These ranges have no common sensitivities */ return -EINVAL; /* Take the greatest of the low */ dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens); /* Take the least of the high */ dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens); rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat, &r2->level[0].cat); if (rc) goto out; rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat, &r2->level[1].cat); if (rc) goto out; out: return rc; } static inline int mls_context_cmp(const struct context *c1, const struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) { ebitmap_destroy(&c->range.level[0].cat); ebitmap_destroy(&c->range.level[1].cat); mls_context_init(c); } static inline void context_init(struct context *c) { memset(c, 0, sizeof(*c)); } static inline int context_cpy(struct context *dst, const struct context *src) { int rc; dst->user = src->user; dst->role = src->role; dst->type = src->type; if (src->str) { dst->str = kstrdup(src->str, GFP_ATOMIC); if (!dst->str) return -ENOMEM; dst->len = src->len; } else { dst->str = NULL; dst->len = 0; } rc = mls_context_cpy(dst, src); if (rc) { kfree(dst->str); dst->str = NULL; dst->len = 0; return rc; } return 0; } static inline void context_destroy(struct context *c) { c->user = c->role = c->type = 0; kfree(c->str); c->str = NULL; c->len = 0; mls_context_destroy(c); } static inline int context_cmp(const struct context *c1, const struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && (c1->type == c2->type) && mls_context_cmp(c1, c2)); } u32 context_compute_hash(const struct context *c); #endif /* _SS_CONTEXT_H_ */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Linaro * Author: Christoffer Dall <christoffer.dall@linaro.org> */ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/interrupt.h> #include <linux/kvm_host.h> #include <linux/seq_file.h> #include <kvm/arm_vgic.h> #include <asm/kvm_mmu.h> #include "vgic.h" /* * Structure to control looping through the entire vgic state. We start at * zero for each field and move upwards. So, if dist_id is 0 we print the * distributor info. When dist_id is 1, we have already printed it and move * on. * * When vcpu_id < nr_cpus we print the vcpu info until vcpu_id == nr_cpus and * so on. */ struct vgic_state_iter { int nr_cpus; int nr_spis; int nr_lpis; int dist_id; int vcpu_id; unsigned long intid; int lpi_idx; }; static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) { struct vgic_dist *dist = &kvm->arch.vgic; if (iter->dist_id == 0) { iter->dist_id++; return; } /* * Let the xarray drive the iterator after the last SPI, as the iterator * has exhausted the sequentially-allocated INTID space. */ if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) { if (iter->lpi_idx < iter->nr_lpis) xa_find_after(&dist->lpi_xa, &iter->intid, VGIC_LPI_MAX_INTID, LPI_XA_MARK_DEBUG_ITER); iter->lpi_idx++; return; } iter->intid++; if (iter->intid == VGIC_NR_PRIVATE_IRQS && ++iter->vcpu_id < iter->nr_cpus) iter->intid = 0; } static int iter_mark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; int nr_lpis = 0; xa_for_each(&dist->lpi_xa, intid, irq) { if (!vgic_try_get_irq_kref(irq)) continue; xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); nr_lpis++; } return nr_lpis; } static void iter_unmark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; xa_for_each(&dist->lpi_xa, intid, irq) { xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); vgic_put_irq(kvm, irq); } } static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter, loff_t pos) { int nr_cpus = atomic_read(&kvm->online_vcpus); memset(iter, 0, sizeof(*iter)); iter->nr_cpus = nr_cpus; iter->nr_spis = kvm->arch.vgic.nr_spis; if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) iter->nr_lpis = iter_mark_lpis(kvm); /* Fast forward to the right position if needed */ while (pos--) iter_next(kvm, iter); } static bool end_of_vgic(struct vgic_state_iter *iter) { return iter->dist_id > 0 && iter->vcpu_id == iter->nr_cpus && iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && iter->lpi_idx > iter->nr_lpis; } static void *vgic_debug_start(struct seq_file *s, loff_t *pos) { struct kvm *kvm = s->private; struct vgic_state_iter *iter; mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; if (iter) { iter = ERR_PTR(-EBUSY); goto out; } iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { iter = ERR_PTR(-ENOMEM); goto out; } iter_init(kvm, iter, *pos); kvm->arch.vgic.iter = iter; if (end_of_vgic(iter)) iter = NULL; out: mutex_unlock(&kvm->arch.config_lock); return iter; } static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) { struct kvm *kvm = s->private; struct vgic_state_iter *iter = kvm->arch.vgic.iter; ++*pos; iter_next(kvm, iter); if (end_of_vgic(iter)) iter = NULL; return iter; } static void vgic_debug_stop(struct seq_file *s, void *v) { struct kvm *kvm = s->private; struct vgic_state_iter *iter; /* * If the seq file wasn't properly opened, there's nothing to clearn * up. */ if (IS_ERR(v)) return; mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; iter_unmark_lpis(kvm); kfree(iter); kvm->arch.vgic.iter = NULL; mutex_unlock(&kvm->arch.config_lock); } static void print_dist_state(struct seq_file *s, struct vgic_dist *dist, struct vgic_state_iter *iter) { bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3; seq_printf(s, "Distributor\n"); seq_printf(s, "===========\n"); seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2"); seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis); if (v3) seq_printf(s, "nr_lpis:\t%d\n", iter->nr_lpis); seq_printf(s, "enabled:\t%d\n", dist->enabled); seq_printf(s, "\n"); seq_printf(s, "P=pending_latch, L=line_level, A=active\n"); seq_printf(s, "E=enabled, H=hw, C=config (level=1, edge=0)\n"); seq_printf(s, "G=group\n"); } static void print_header(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int id = 0; char *hdr = "SPI "; if (vcpu) { hdr = "VCPU"; id = vcpu->vcpu_idx; } seq_printf(s, "\n"); seq_printf(s, "%s%2d TYP ID TGT_ID PLAEHCG HWID TARGET SRC PRI VCPU_ID\n", hdr, id); seq_printf(s, "----------------------------------------------------------------\n"); } static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { char *type; bool pending; if (irq->intid < VGIC_NR_SGIS) type = "SGI"; else if (irq->intid < VGIC_NR_PRIVATE_IRQS) type = "PPI"; else if (irq->intid < VGIC_MAX_SPI) type = "SPI"; else type = "LPI"; if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) print_header(s, irq, vcpu); pending = irq->pending_latch; if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; err = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &pending); WARN_ON_ONCE(err); } seq_printf(s, " %s %4d " " %2d " "%d%d%d%d%d%d%d " "%8d " "%8x " " %2x " "%3d " " %2d " "\n", type, irq->intid, (irq->target_vcpu) ? irq->target_vcpu->vcpu_idx : -1, pending, irq->line_level, irq->active, irq->enabled, irq->hw, irq->config == VGIC_CONFIG_LEVEL, irq->group, irq->hwintid, irq->mpidr, irq->source, irq->priority, (irq->vcpu) ? irq->vcpu->vcpu_idx : -1); } static int vgic_debug_show(struct seq_file *s, void *v) { struct kvm *kvm = s->private; struct vgic_state_iter *iter = v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; unsigned long flags; if (iter->dist_id == 0) { print_dist_state(s, &kvm->arch.vgic, iter); return 0; } if (!kvm->arch.vgic.initialized) return 0; if (iter->vcpu_id < iter->nr_cpus) vcpu = kvm_get_vcpu(kvm, iter->vcpu_id); /* * Expect this to succeed, as iter_mark_lpis() takes a reference on * every LPI to be visited. */ irq = vgic_get_irq(kvm, vcpu, iter->intid); if (WARN_ON_ONCE(!irq)) return -EINVAL; raw_spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; } static const struct seq_operations vgic_debug_sops = { .start = vgic_debug_start, .next = vgic_debug_next, .stop = vgic_debug_stop, .show = vgic_debug_show }; DEFINE_SEQ_ATTRIBUTE(vgic_debug); void vgic_debug_init(struct kvm *kvm) { debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm, &vgic_debug_fops); } void vgic_debug_destroy(struct kvm *kvm) { } |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017 ARM Ltd. */ #ifndef __ASM_DAIFFLAGS_H #define __ASM_DAIFFLAGS_H #include <linux/irqflags.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/ptrace.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ (PSR_I_BIT | PSR_F_BIT) #define DAIF_ERRCTX (PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) #define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) /* mask/save/unmask/restore all exceptions, including interrupts. */ static inline void local_daif_mask(void) { WARN_ON(system_has_prio_mask_debugging() && (read_sysreg_s(SYS_ICC_PMR_EL1) == (GIC_PRIO_IRQOFF | GIC_PRIO_PSR_I_SET))); asm volatile( "msr daifset, #0xf // local_daif_mask\n" : : : "memory"); /* Don't really care for a dsb here, we don't intend to enable IRQs */ if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); trace_hardirqs_off(); } static inline unsigned long local_daif_save_flags(void) { unsigned long flags; flags = read_sysreg(daif); if (system_uses_irq_prio_masking()) { /* If IRQs are masked with PMR, reflect it in the flags */ if (read_sysreg_s(SYS_ICC_PMR_EL1) != GIC_PRIO_IRQON) flags |= PSR_I_BIT | PSR_F_BIT; } return flags; } static inline unsigned long local_daif_save(void) { unsigned long flags; flags = local_daif_save_flags(); local_daif_mask(); return flags; } static inline void local_daif_restore(unsigned long flags) { bool irq_disabled = flags & PSR_I_BIT; WARN_ON(system_has_prio_mask_debugging() && (read_sysreg(daif) & (PSR_I_BIT | PSR_F_BIT)) != (PSR_I_BIT | PSR_F_BIT)); if (!irq_disabled) { trace_hardirqs_on(); if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; if (!(flags & PSR_A_BIT)) { /* * If interrupts are disabled but we can take * asynchronous errors, we can take NMIs */ flags &= ~(PSR_I_BIT | PSR_F_BIT); pmr = GIC_PRIO_IRQOFF; } else { pmr = GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET; } /* * There has been concern that the write to daif * might be reordered before this write to PMR. * From the ARM ARM DDI 0487D.a, section D1.7.1 * "Accessing PSTATE fields": * Writes to the PSTATE fields have side-effects on * various aspects of the PE operation. All of these * side-effects are guaranteed: * - Not to be visible to earlier instructions in * the execution stream. * - To be visible to later instructions in the * execution stream * * Also, writes to PMR are self-synchronizing, so no * interrupts with a lower priority than PMR is signaled * to the PE after the write. * * So we don't need additional synchronization here. */ gic_write_pmr(pmr); } write_sysreg(flags, daif); if (irq_disabled) trace_hardirqs_off(); } /* * Called by synchronous exception handlers to restore the DAIF bits that were * modified by taking an exception. */ static inline void local_daif_inherit(struct pt_regs *regs) { unsigned long flags = regs->pstate & DAIF_MASK; if (interrupts_enabled(regs)) trace_hardirqs_on(); if (system_uses_irq_prio_masking()) gic_write_pmr(regs->pmr_save); /* * We can't use local_daif_restore(regs->pstate) here as * system_has_prio_mask_debugging() won't restore the I bit if it can * use the pmr instead. */ write_sysreg(flags, daif); } #endif |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KERNEL_PRINTK_RINGBUFFER_H #define _KERNEL_PRINTK_RINGBUFFER_H #include <linux/atomic.h> #include <linux/dev_printk.h> /* * Meta information about each stored message. * * All fields are set by the printk code except for @seq, which is * set by the ringbuffer code. */ struct printk_info { u64 seq; /* sequence number */ u64 ts_nsec; /* timestamp in nanoseconds */ u16 text_len; /* length of text message */ u8 facility; /* syslog facility */ u8 flags:5; /* internal record flags */ u8 level:3; /* syslog level */ u32 caller_id; /* thread id or processor id */ struct dev_printk_info dev_info; }; /* * A structure providing the buffers, used by writers and readers. * * Writers: * Using prb_rec_init_wr(), a writer sets @text_buf_size before calling * prb_reserve(). On success, prb_reserve() sets @info and @text_buf to * buffers reserved for that writer. * * Readers: * Using prb_rec_init_rd(), a reader sets all fields before calling * prb_read_valid(). Note that the reader provides the @info and @text_buf, * buffers. On success, the struct pointed to by @info will be filled and * the char array pointed to by @text_buf will be filled with text data. */ struct printk_record { struct printk_info *info; char *text_buf; unsigned int text_buf_size; }; /* Specifies the logical position and span of a data block. */ struct prb_data_blk_lpos { unsigned long begin; unsigned long next; }; /* * A descriptor: the complete meta-data for a record. * * @state_var: A bitwise combination of descriptor ID and descriptor state. */ struct prb_desc { atomic_long_t state_var; struct prb_data_blk_lpos text_blk_lpos; }; /* A ringbuffer of "ID + data" elements. */ struct prb_data_ring { unsigned int size_bits; char *data; atomic_long_t head_lpos; atomic_long_t tail_lpos; }; /* A ringbuffer of "struct prb_desc" elements. */ struct prb_desc_ring { unsigned int count_bits; struct prb_desc *descs; struct printk_info *infos; atomic_long_t head_id; atomic_long_t tail_id; atomic_long_t last_finalized_seq; }; /* * The high level structure representing the printk ringbuffer. * * @fail: Count of failed prb_reserve() calls where not even a data-less * record was created. */ struct printk_ringbuffer { struct prb_desc_ring desc_ring; struct prb_data_ring text_data_ring; atomic_long_t fail; }; /* * Used by writers as a reserve/commit handle. * * @rb: Ringbuffer where the entry is reserved. * @irqflags: Saved irq flags to restore on entry commit. * @id: ID of the reserved descriptor. * @text_space: Total occupied buffer space in the text data ring, including * ID, alignment padding, and wrapping data blocks. * * This structure is an opaque handle for writers. Its contents are only * to be used by the ringbuffer implementation. */ struct prb_reserved_entry { struct printk_ringbuffer *rb; unsigned long irqflags; unsigned long id; unsigned int text_space; }; /* The possible responses of a descriptor state-query. */ enum desc_state { desc_miss = -1, /* ID mismatch (pseudo state) */ desc_reserved = 0x0, /* reserved, in use by writer */ desc_committed = 0x1, /* committed by writer, could get reopened */ desc_finalized = 0x2, /* committed, no further modification allowed */ desc_reusable = 0x3, /* free, not yet used by any writer */ }; #define _DATA_SIZE(sz_bits) (1UL << (sz_bits)) #define _DESCS_COUNT(ct_bits) (1U << (ct_bits)) #define DESC_SV_BITS (sizeof(unsigned long) * 8) #define DESC_FLAGS_SHIFT (DESC_SV_BITS - 2) #define DESC_FLAGS_MASK (3UL << DESC_FLAGS_SHIFT) #define DESC_STATE(sv) (3UL & (sv >> DESC_FLAGS_SHIFT)) #define DESC_SV(id, state) (((unsigned long)state << DESC_FLAGS_SHIFT) | id) #define DESC_ID_MASK (~DESC_FLAGS_MASK) #define DESC_ID(sv) ((sv) & DESC_ID_MASK) /* * Special data block logical position values (for fields of * @prb_desc.text_blk_lpos). * * - Bit0 is used to identify if the record has no data block. (Implemented in * the LPOS_DATALESS() macro.) * * - Bit1 specifies the reason for not having a data block. * * These special values could never be real lpos values because of the * meta data and alignment padding of data blocks. (See to_blk_size() for * details.) */ #define FAILED_LPOS 0x1 #define EMPTY_LINE_LPOS 0x3 #define FAILED_BLK_LPOS \ { \ .begin = FAILED_LPOS, \ .next = FAILED_LPOS, \ } /* * Descriptor Bootstrap * * The descriptor array is minimally initialized to allow immediate usage * by readers and writers. The requirements that the descriptor array * initialization must satisfy: * * Req1 * The tail must point to an existing (committed or reusable) descriptor. * This is required by the implementation of prb_first_seq(). * * Req2 * Readers must see that the ringbuffer is initially empty. * * Req3 * The first record reserved by a writer is assigned sequence number 0. * * To satisfy Req1, the tail initially points to a descriptor that is * minimally initialized (having no data block, i.e. data-less with the * data block's lpos @begin and @next values set to FAILED_LPOS). * * To satisfy Req2, the initial tail descriptor is initialized to the * reusable state. Readers recognize reusable descriptors as existing * records, but skip over them. * * To satisfy Req3, the last descriptor in the array is used as the initial * head (and tail) descriptor. This allows the first record reserved by a * writer (head + 1) to be the first descriptor in the array. (Only the first * descriptor in the array could have a valid sequence number of 0.) * * The first time a descriptor is reserved, it is assigned a sequence number * with the value of the array index. A "first time reserved" descriptor can * be recognized because it has a sequence number of 0 but does not have an * index of 0. (Only the first descriptor in the array could have a valid * sequence number of 0.) After the first reservation, all future reservations * (recycling) simply involve incrementing the sequence number by the array * count. * * Hack #1 * Only the first descriptor in the array is allowed to have the sequence * number 0. In this case it is not possible to recognize if it is being * reserved the first time (set to index value) or has been reserved * previously (increment by the array count). This is handled by _always_ * incrementing the sequence number by the array count when reserving the * first descriptor in the array. In order to satisfy Req3, the sequence * number of the first descriptor in the array is initialized to minus * the array count. Then, upon the first reservation, it is incremented * to 0, thus satisfying Req3. * * Hack #2 * prb_first_seq() can be called at any time by readers to retrieve the * sequence number of the tail descriptor. However, due to Req2 and Req3, * initially there are no records to report the sequence number of * (sequence numbers are u64 and there is nothing less than 0). To handle * this, the sequence number of the initial tail descriptor is initialized * to 0. Technically this is incorrect, because there is no record with * sequence number 0 (yet) and the tail descriptor is not the first * descriptor in the array. But it allows prb_read_valid() to correctly * report the existence of a record for _any_ given sequence number at all * times. Bootstrapping is complete when the tail is pushed the first * time, thus finally pointing to the first descriptor reserved by a * writer, which has the assigned sequence number 0. */ /* * Initiating Logical Value Overflows * * Both logical position (lpos) and ID values can be mapped to array indexes * but may experience overflows during the lifetime of the system. To ensure * that printk_ringbuffer can handle the overflows for these types, initial * values are chosen that map to the correct initial array indexes, but will * result in overflows soon. * * BLK0_LPOS * The initial @head_lpos and @tail_lpos for data rings. It is at index * 0 and the lpos value is such that it will overflow on the first wrap. * * DESC0_ID * The initial @head_id and @tail_id for the desc ring. It is at the last * index of the descriptor array (see Req3 above) and the ID value is such * that it will overflow on the second wrap. */ #define BLK0_LPOS(sz_bits) (-(_DATA_SIZE(sz_bits))) #define DESC0_ID(ct_bits) DESC_ID(-(_DESCS_COUNT(ct_bits) + 1)) #define DESC0_SV(ct_bits) DESC_SV(DESC0_ID(ct_bits), desc_reusable) /* * Define a ringbuffer with an external text data buffer. The same as * DEFINE_PRINTKRB() but requires specifying an external buffer for the * text data. * * Note: The specified external buffer must be of the size: * 2 ^ (descbits + avgtextbits) */ #define _DEFINE_PRINTKRB(name, descbits, avgtextbits, text_buf) \ static struct prb_desc _##name##_descs[_DESCS_COUNT(descbits)] = { \ /* the initial head and tail */ \ [_DESCS_COUNT(descbits) - 1] = { \ /* reusable */ \ .state_var = ATOMIC_INIT(DESC0_SV(descbits)), \ /* no associated data block */ \ .text_blk_lpos = FAILED_BLK_LPOS, \ }, \ }; \ static struct printk_info _##name##_infos[_DESCS_COUNT(descbits)] = { \ /* this will be the first record reserved by a writer */ \ [0] = { \ /* will be incremented to 0 on the first reservation */ \ .seq = -(u64)_DESCS_COUNT(descbits), \ }, \ /* the initial head and tail */ \ [_DESCS_COUNT(descbits) - 1] = { \ /* reports the first seq value during the bootstrap phase */ \ .seq = 0, \ }, \ }; \ static struct printk_ringbuffer name = { \ .desc_ring = { \ .count_bits = descbits, \ .descs = &_##name##_descs[0], \ .infos = &_##name##_infos[0], \ .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ .last_finalized_seq = ATOMIC_INIT(0), \ }, \ .text_data_ring = { \ .size_bits = (avgtextbits) + (descbits), \ .data = text_buf, \ .head_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ .tail_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ }, \ .fail = ATOMIC_LONG_INIT(0), \ } /** * DEFINE_PRINTKRB() - Define a ringbuffer. * * @name: The name of the ringbuffer variable. * @descbits: The number of descriptors as a power-of-2 value. * @avgtextbits: The average text data size per record as a power-of-2 value. * * This is a macro for defining a ringbuffer and all internal structures * such that it is ready for immediate use. See _DEFINE_PRINTKRB() for a * variant where the text data buffer can be specified externally. */ #define DEFINE_PRINTKRB(name, descbits, avgtextbits) \ static char _##name##_text[1U << ((avgtextbits) + (descbits))] \ __aligned(__alignof__(unsigned long)); \ _DEFINE_PRINTKRB(name, descbits, avgtextbits, &_##name##_text[0]) /* Writer Interface */ /** * prb_rec_init_wr() - Initialize a buffer for writing records. * * @r: The record to initialize. * @text_buf_size: The needed text buffer size. */ static inline void prb_rec_init_wr(struct printk_record *r, unsigned int text_buf_size) { r->info = NULL; r->text_buf = NULL; r->text_buf_size = text_buf_size; } bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r); bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size); void prb_commit(struct prb_reserved_entry *e); void prb_final_commit(struct prb_reserved_entry *e); void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int text_buf_size, struct prb_desc *descs, unsigned int descs_count_bits, struct printk_info *infos); unsigned int prb_record_text_space(struct prb_reserved_entry *e); /* Reader Interface */ /** * prb_rec_init_rd() - Initialize a buffer for reading records. * * @r: The record to initialize. * @info: A buffer to store record meta-data. * @text_buf: A buffer to store text data. * @text_buf_size: The size of @text_buf. * * Initialize all the fields that a reader is interested in. All arguments * (except @r) are optional. Only record data for arguments that are * non-NULL or non-zero will be read. */ static inline void prb_rec_init_rd(struct printk_record *r, struct printk_info *info, char *text_buf, unsigned int text_buf_size) { r->info = info; r->text_buf = text_buf; r->text_buf_size = text_buf_size; } /** * prb_for_each_record() - Iterate over the records of a ringbuffer. * * @from: The sequence number to begin with. * @rb: The ringbuffer to iterate over. * @s: A u64 to store the sequence number on each iteration. * @r: A printk_record to store the record on each iteration. * * This is a macro for conveniently iterating over a ringbuffer. * Note that @s may not be the sequence number of the record on each * iteration. For the sequence number, @r->info->seq should be checked. * * Context: Any context. */ #define prb_for_each_record(from, rb, s, r) \ for ((s) = from; prb_read_valid(rb, s, r); (s) = (r)->info->seq + 1) /** * prb_for_each_info() - Iterate over the meta data of a ringbuffer. * * @from: The sequence number to begin with. * @rb: The ringbuffer to iterate over. * @s: A u64 to store the sequence number on each iteration. * @i: A printk_info to store the record meta data on each iteration. * @lc: An unsigned int to store the text line count of each record. * * This is a macro for conveniently iterating over a ringbuffer. * Note that @s may not be the sequence number of the record on each * iteration. For the sequence number, @r->info->seq should be checked. * * Context: Any context. */ #define prb_for_each_info(from, rb, s, i, lc) \ for ((s) = from; prb_read_valid_info(rb, s, i, lc); (s) = (i)->seq + 1) bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r); bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count); u64 prb_first_seq(struct printk_ringbuffer *rb); u64 prb_first_valid_seq(struct printk_ringbuffer *rb); u64 prb_next_seq(struct printk_ringbuffer *rb); u64 prb_next_reserve_seq(struct printk_ringbuffer *rb); #ifdef CONFIG_64BIT #define __u64seq_to_ulseq(u64seq) (u64seq) #define __ulseq_to_u64seq(rb, ulseq) (ulseq) #else /* CONFIG_64BIT */ #define __u64seq_to_ulseq(u64seq) ((u32)u64seq) static inline u64 __ulseq_to_u64seq(struct printk_ringbuffer *rb, u32 ulseq) { u64 rb_first_seq = prb_first_seq(rb); u64 seq; /* * The provided sequence is only the lower 32 bits of the ringbuffer * sequence. It needs to be expanded to 64bit. Get the first sequence * number from the ringbuffer and fold it. * * Having a 32bit representation in the console is sufficient. * If a console ever gets more than 2^31 records behind * the ringbuffer then this is the least of the problems. * * Also the access to the ring buffer is always safe. */ seq = rb_first_seq - (s32)((u32)rb_first_seq - ulseq); return seq; } #endif /* CONFIG_64BIT */ #endif /* _KERNEL_PRINTK_RINGBUFFER_H */ |
| 259 257 120 120 120 240 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/tomoyo.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/lsm_hooks.h> #include <uapi/linux/lsm.h> #include "common.h" /** * tomoyo_domain - Get "struct tomoyo_domain_info" for current thread. * * Returns pointer to "struct tomoyo_domain_info" for current thread. */ struct tomoyo_domain_info *tomoyo_domain(void) { struct tomoyo_task *s = tomoyo_task(current); if (s->old_domain_info && !current->in_execve) { atomic_dec(&s->old_domain_info->users); s->old_domain_info = NULL; } return s->domain_info; } /** * tomoyo_cred_prepare - Target for security_prepare_creds(). * * @new: Pointer to "struct cred". * @old: Pointer to "struct cred". * @gfp: Memory allocation flags. * * Returns 0. */ static int tomoyo_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { /* Restore old_domain_info saved by previous execve() request. */ struct tomoyo_task *s = tomoyo_task(current); if (s->old_domain_info && !current->in_execve) { atomic_dec(&s->domain_info->users); s->domain_info = s->old_domain_info; s->old_domain_info = NULL; } return 0; } /** * tomoyo_bprm_committed_creds - Target for security_bprm_committed_creds(). * * @bprm: Pointer to "struct linux_binprm". */ static void tomoyo_bprm_committed_creds(const struct linux_binprm *bprm) { /* Clear old_domain_info saved by execve() request. */ struct tomoyo_task *s = tomoyo_task(current); atomic_dec(&s->old_domain_info->users); s->old_domain_info = NULL; } #ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER /** * tomoyo_bprm_creds_for_exec - Target for security_bprm_creds_for_exec(). * * @bprm: Pointer to "struct linux_binprm". * * Returns 0. */ static int tomoyo_bprm_creds_for_exec(struct linux_binprm *bprm) { /* * Load policy if /sbin/tomoyo-init exists and /sbin/init is requested * for the first time. */ if (!tomoyo_policy_loaded) tomoyo_load_policy(bprm->filename); return 0; } #endif /** * tomoyo_bprm_check_security - Target for security_bprm_check(). * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_bprm_check_security(struct linux_binprm *bprm) { struct tomoyo_task *s = tomoyo_task(current); /* * Execute permission is checked against pathname passed to execve() * using current domain. */ if (!s->old_domain_info) { const int idx = tomoyo_read_lock(); const int err = tomoyo_find_next_domain(bprm); tomoyo_read_unlock(idx); return err; } /* * Read permission is checked against interpreters using next domain. */ return tomoyo_check_open_permission(s->domain_info, &bprm->file->f_path, O_RDONLY); } /** * tomoyo_inode_getattr - Target for security_inode_getattr(). * * @path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_inode_getattr(const struct path *path) { return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, path, NULL); } /** * tomoyo_path_truncate - Target for security_path_truncate(). * * @path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_truncate(const struct path *path) { return tomoyo_path_perm(TOMOYO_TYPE_TRUNCATE, path, NULL); } /** * tomoyo_file_truncate - Target for security_file_truncate(). * * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_truncate(struct file *file) { return tomoyo_path_truncate(&file->f_path); } /** * tomoyo_path_unlink - Target for security_path_unlink(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_unlink(const struct path *parent, struct dentry *dentry) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_perm(TOMOYO_TYPE_UNLINK, &path, NULL); } /** * tomoyo_path_mkdir - Target for security_path_mkdir(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * @mode: DAC permission mode. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_mkdir(const struct path *parent, struct dentry *dentry, umode_t mode) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_number_perm(TOMOYO_TYPE_MKDIR, &path, mode & S_IALLUGO); } /** * tomoyo_path_rmdir - Target for security_path_rmdir(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_rmdir(const struct path *parent, struct dentry *dentry) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_perm(TOMOYO_TYPE_RMDIR, &path, NULL); } /** * tomoyo_path_symlink - Target for security_path_symlink(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * @old_name: Symlink's content. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_symlink(const struct path *parent, struct dentry *dentry, const char *old_name) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_perm(TOMOYO_TYPE_SYMLINK, &path, old_name); } /** * tomoyo_path_mknod - Target for security_path_mknod(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * @mode: DAC permission mode. * @dev: Device attributes. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_mknod(const struct path *parent, struct dentry *dentry, umode_t mode, unsigned int dev) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; int type = TOMOYO_TYPE_CREATE; const unsigned int perm = mode & S_IALLUGO; switch (mode & S_IFMT) { case S_IFCHR: type = TOMOYO_TYPE_MKCHAR; break; case S_IFBLK: type = TOMOYO_TYPE_MKBLOCK; break; default: goto no_dev; } return tomoyo_mkdev_perm(type, &path, perm, dev); no_dev: switch (mode & S_IFMT) { case S_IFIFO: type = TOMOYO_TYPE_MKFIFO; break; case S_IFSOCK: type = TOMOYO_TYPE_MKSOCK; break; } return tomoyo_path_number_perm(type, &path, perm); } /** * tomoyo_path_link - Target for security_path_link(). * * @old_dentry: Pointer to "struct dentry". * @new_dir: Pointer to "struct path". * @new_dentry: Pointer to "struct dentry". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { struct path path1 = { .mnt = new_dir->mnt, .dentry = old_dentry }; struct path path2 = { .mnt = new_dir->mnt, .dentry = new_dentry }; return tomoyo_path2_perm(TOMOYO_TYPE_LINK, &path1, &path2); } /** * tomoyo_path_rename - Target for security_path_rename(). * * @old_parent: Pointer to "struct path". * @old_dentry: Pointer to "struct dentry". * @new_parent: Pointer to "struct path". * @new_dentry: Pointer to "struct dentry". * @flags: Rename options. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_rename(const struct path *old_parent, struct dentry *old_dentry, const struct path *new_parent, struct dentry *new_dentry, const unsigned int flags) { struct path path1 = { .mnt = old_parent->mnt, .dentry = old_dentry }; struct path path2 = { .mnt = new_parent->mnt, .dentry = new_dentry }; if (flags & RENAME_EXCHANGE) { const int err = tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path2, &path1); if (err) return err; } return tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path1, &path2); } /** * tomoyo_file_fcntl - Target for security_file_fcntl(). * * @file: Pointer to "struct file". * @cmd: Command for fcntl(). * @arg: Argument for @cmd. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { if (!(cmd == F_SETFL && ((arg ^ file->f_flags) & O_APPEND))) return 0; return tomoyo_check_open_permission(tomoyo_domain(), &file->f_path, O_WRONLY | (arg & O_APPEND)); } /** * tomoyo_file_open - Target for security_file_open(). * * @f: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_open(struct file *f) { /* Don't check read permission here if called from execve(). */ /* Illogically, FMODE_EXEC is in f_flags, not f_mode. */ if (f->f_flags & __FMODE_EXEC) return 0; return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path, f->f_flags); } /** * tomoyo_file_ioctl - Target for security_file_ioctl(). * * @file: Pointer to "struct file". * @cmd: Command for ioctl(). * @arg: Argument for @cmd. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return tomoyo_path_number_perm(TOMOYO_TYPE_IOCTL, &file->f_path, cmd); } /** * tomoyo_path_chmod - Target for security_path_chmod(). * * @path: Pointer to "struct path". * @mode: DAC permission mode. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_chmod(const struct path *path, umode_t mode) { return tomoyo_path_number_perm(TOMOYO_TYPE_CHMOD, path, mode & S_IALLUGO); } /** * tomoyo_path_chown - Target for security_path_chown(). * * @path: Pointer to "struct path". * @uid: Owner ID. * @gid: Group ID. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { int error = 0; if (uid_valid(uid)) error = tomoyo_path_number_perm(TOMOYO_TYPE_CHOWN, path, from_kuid(&init_user_ns, uid)); if (!error && gid_valid(gid)) error = tomoyo_path_number_perm(TOMOYO_TYPE_CHGRP, path, from_kgid(&init_user_ns, gid)); return error; } /** * tomoyo_path_chroot - Target for security_path_chroot(). * * @path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_chroot(const struct path *path) { return tomoyo_path_perm(TOMOYO_TYPE_CHROOT, path, NULL); } /** * tomoyo_sb_mount - Target for security_sb_mount(). * * @dev_name: Name of device file. Maybe NULL. * @path: Pointer to "struct path". * @type: Name of filesystem type. Maybe NULL. * @flags: Mount options. * @data: Optional data. Maybe NULL. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return tomoyo_mount_permission(dev_name, path, type, flags, data); } /** * tomoyo_sb_umount - Target for security_sb_umount(). * * @mnt: Pointer to "struct vfsmount". * @flags: Unmount options. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_sb_umount(struct vfsmount *mnt, int flags) { struct path path = { .mnt = mnt, .dentry = mnt->mnt_root }; return tomoyo_path_perm(TOMOYO_TYPE_UMOUNT, &path, NULL); } /** * tomoyo_sb_pivotroot - Target for security_sb_pivotroot(). * * @old_path: Pointer to "struct path". * @new_path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return tomoyo_path2_perm(TOMOYO_TYPE_PIVOT_ROOT, new_path, old_path); } /** * tomoyo_socket_listen - Check permission for listen(). * * @sock: Pointer to "struct socket". * @backlog: Backlog parameter. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_listen(struct socket *sock, int backlog) { return tomoyo_socket_listen_permission(sock); } /** * tomoyo_socket_connect - Check permission for connect(). * * @sock: Pointer to "struct socket". * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_connect(struct socket *sock, struct sockaddr *addr, int addr_len) { return tomoyo_socket_connect_permission(sock, addr, addr_len); } /** * tomoyo_socket_bind - Check permission for bind(). * * @sock: Pointer to "struct socket". * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { return tomoyo_socket_bind_permission(sock, addr, addr_len); } /** * tomoyo_socket_sendmsg - Check permission for sendmsg(). * * @sock: Pointer to "struct socket". * @msg: Pointer to "struct msghdr". * @size: Size of message. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return tomoyo_socket_sendmsg_permission(sock, msg, size); } struct lsm_blob_sizes tomoyo_blob_sizes __ro_after_init = { .lbs_task = sizeof(struct tomoyo_task), }; /** * tomoyo_task_alloc - Target for security_task_alloc(). * * @task: Pointer to "struct task_struct". * @clone_flags: clone() flags. * * Returns 0. */ static int tomoyo_task_alloc(struct task_struct *task, unsigned long clone_flags) { struct tomoyo_task *old = tomoyo_task(current); struct tomoyo_task *new = tomoyo_task(task); new->domain_info = old->domain_info; atomic_inc(&new->domain_info->users); new->old_domain_info = NULL; return 0; } /** * tomoyo_task_free - Target for security_task_free(). * * @task: Pointer to "struct task_struct". */ static void tomoyo_task_free(struct task_struct *task) { struct tomoyo_task *s = tomoyo_task(task); if (s->domain_info) { atomic_dec(&s->domain_info->users); s->domain_info = NULL; } if (s->old_domain_info) { atomic_dec(&s->old_domain_info->users); s->old_domain_info = NULL; } } static const struct lsm_id tomoyo_lsmid = { .name = "tomoyo", .id = LSM_ID_TOMOYO, }; /* * tomoyo_security_ops is a "struct security_operations" which is used for * registering TOMOYO. */ static struct security_hook_list tomoyo_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, tomoyo_cred_prepare), LSM_HOOK_INIT(bprm_committed_creds, tomoyo_bprm_committed_creds), LSM_HOOK_INIT(task_alloc, tomoyo_task_alloc), LSM_HOOK_INIT(task_free, tomoyo_task_free), #ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER LSM_HOOK_INIT(bprm_creds_for_exec, tomoyo_bprm_creds_for_exec), #endif LSM_HOOK_INIT(bprm_check_security, tomoyo_bprm_check_security), LSM_HOOK_INIT(file_fcntl, tomoyo_file_fcntl), LSM_HOOK_INIT(file_open, tomoyo_file_open), LSM_HOOK_INIT(file_truncate, tomoyo_file_truncate), LSM_HOOK_INIT(path_truncate, tomoyo_path_truncate), LSM_HOOK_INIT(path_unlink, tomoyo_path_unlink), LSM_HOOK_INIT(path_mkdir, tomoyo_path_mkdir), LSM_HOOK_INIT(path_rmdir, tomoyo_path_rmdir), LSM_HOOK_INIT(path_symlink, tomoyo_path_symlink), LSM_HOOK_INIT(path_mknod, tomoyo_path_mknod), LSM_HOOK_INIT(path_link, tomoyo_path_link), LSM_HOOK_INIT(path_rename, tomoyo_path_rename), LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr), LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl), LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod), LSM_HOOK_INIT(path_chown, tomoyo_path_chown), LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot), LSM_HOOK_INIT(sb_mount, tomoyo_sb_mount), LSM_HOOK_INIT(sb_umount, tomoyo_sb_umount), LSM_HOOK_INIT(sb_pivotroot, tomoyo_sb_pivotroot), LSM_HOOK_INIT(socket_bind, tomoyo_socket_bind), LSM_HOOK_INIT(socket_connect, tomoyo_socket_connect), LSM_HOOK_INIT(socket_listen, tomoyo_socket_listen), LSM_HOOK_INIT(socket_sendmsg, tomoyo_socket_sendmsg), }; /* Lock for GC. */ DEFINE_SRCU(tomoyo_ss); int tomoyo_enabled __ro_after_init = 1; /** * tomoyo_init - Register TOMOYO Linux as a LSM module. * * Returns 0. */ static int __init tomoyo_init(void) { struct tomoyo_task *s = tomoyo_task(current); /* register ourselves with the security framework */ security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), &tomoyo_lsmid); pr_info("TOMOYO Linux initialized\n"); s->domain_info = &tomoyo_kernel_domain; atomic_inc(&tomoyo_kernel_domain.users); s->old_domain_info = NULL; tomoyo_mm_init(); return 0; } DEFINE_LSM(tomoyo) = { .name = "tomoyo", .enabled = &tomoyo_enabled, .flags = LSM_FLAG_LEGACY_MAJOR, .blobs = &tomoyo_blob_sizes, .init = tomoyo_init, }; |
| 3 3 3 3 3 124 123 123 124 124 123 124 85 85 85 124 123 124 124 124 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 | // SPDX-License-Identifier: GPL-2.0 /* * mm/pgtable-generic.c * * Generic pgtable methods declared in linux/pgtable.h * * Copyright (C) 2010 Linus Torvalds */ #include <linux/pagemap.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mm_inline.h> #include <asm/pgalloc.h> #include <asm/tlb.h> /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but * very seldom) called out from the p?d_none_or_clear_bad macros. */ void pgd_clear_bad(pgd_t *pgd) { pgd_ERROR(*pgd); pgd_clear(pgd); } #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *p4d) { p4d_ERROR(*p4d); p4d_clear(p4d); } #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); pud_clear(pud); } #endif /* * Note that the pmd variant below can't be stub'ed out just as for p4d/pud * above. pmd folding is special and typically pmd_* macros refer to upper * level even when folded */ void pmd_clear_bad(pmd_t *pmd) { pmd_ERROR(*pmd); pmd_clear(pmd); } #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* * Only sets the access flags (dirty, accessed), as well as write * permission. Furthermore, we know it always gets set to a "more * permissive" setting, which allows most architectures to optimize * this. We return whether the PTE actually changed, which in turn * instructs the caller to do things like update__mmu_cache. This * used to be done in the caller, but sparc needs minor faults to * force that call on sun4c so we changed this macro slightly */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(ptep_get(ptep), entry); if (changed) { set_pte_at(vma->vm_mm, address, ptep, entry); flush_tlb_fix_spurious_fault(vma, address, ptep); } return changed; } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { int young; young = ptep_test_and_clear_young(vma, address, ptep); if (young) flush_tlb_page(vma, address); return young; } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { struct mm_struct *mm = (vma)->vm_mm; pte_t pte; pte = ptep_get_and_clear(mm, address, ptep); if (pte_accessible(mm, pte)) flush_tlb_page(vma, address); return pte; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed) { set_pmd_at(vma->vm_mm, address, pmdp, entry); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { int young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { pud_t pud; VM_BUG_ON(address & ~HPAGE_PUD_MASK); VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp)); pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return pud; } #endif #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(&pgtable->lru); else list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru); pmd_huge_pte(mm, pmdp) = pgtable; } #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW /* no "address" argument so destroys page coloring of some arch */ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable; assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ pgtable = pmd_huge_pte(mm, pmdp); pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru, struct page, lru); if (pmd_huge_pte(mm, pmdp)) list_del(&pgtable->lru); return pgtable; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif #ifndef pmdp_collapse_flush pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { /* * pmd and hugepage pte format are same. So we could * use the same function. */ pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); /* collapse entails shooting down ptes not pmd */ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif /* arch define pte_free_defer in asm/pgalloc.h for its own implementation */ #ifndef pte_free_defer static void pte_free_now(struct rcu_head *head) { struct page *page; page = container_of(head, struct page, rcu_head); pte_free(NULL /* mm not passed and not used */, (pgtable_t)page); } void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) { struct page *page; page = pgtable; call_rcu(&page->rcu_head, pte_free_now); } #endif /* pte_free_defer */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \ (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU)) /* * See the comment above ptep_get_lockless() in include/linux/pgtable.h: * the barriers in pmdp_get_lockless() cannot guarantee that the value in * pmd_high actually belongs with the value in pmd_low; but holding interrupts * off blocks the TLB flush between present updates, which guarantees that a * successful __pte_offset_map() points to a page from matched halves. */ static unsigned long pmdp_get_lockless_start(void) { unsigned long irqflags; local_irq_save(irqflags); return irqflags; } static void pmdp_get_lockless_end(unsigned long irqflags) { local_irq_restore(irqflags); } #else static unsigned long pmdp_get_lockless_start(void) { return 0; } static void pmdp_get_lockless_end(unsigned long irqflags) { } #endif pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { unsigned long irqflags; pmd_t pmdval; rcu_read_lock(); irqflags = pmdp_get_lockless_start(); pmdval = pmdp_get_lockless(pmd); pmdp_get_lockless_end(irqflags); if (pmdvalp) *pmdvalp = pmdval; if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval))) goto nomap; if (unlikely(pmd_trans_huge(pmdval) || pmd_devmap(pmdval))) goto nomap; if (unlikely(pmd_bad(pmdval))) { pmd_clear_bad(pmd); goto nomap; } return __pte_map(&pmdval, addr); nomap: rcu_read_unlock(); return NULL; } pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { pmd_t pmdval; pte_t *pte; pte = __pte_offset_map(pmd, addr, &pmdval); if (likely(pte)) *ptlp = pte_lockptr(mm, &pmdval); return pte; } /* * pte_offset_map_lock(mm, pmd, addr, ptlp), and its internal implementation * __pte_offset_map_lock() below, is usually called with the pmd pointer for * addr, reached by walking down the mm's pgd, p4d, pud for addr: either while * holding mmap_lock or vma lock for read or for write; or in truncate or rmap * context, while holding file's i_mmap_lock or anon_vma lock for read (or for * write). In a few cases, it may be used with pmd pointing to a pmd_t already * copied to or constructed on the stack. * * When successful, it returns the pte pointer for addr, with its page table * kmapped if necessary (when CONFIG_HIGHPTE), and locked against concurrent * modification by software, with a pointer to that spinlock in ptlp (in some * configs mm->page_table_lock, in SPLIT_PTLOCK configs a spinlock in table's * struct page). pte_unmap_unlock(pte, ptl) to unlock and unmap afterwards. * * But it is unsuccessful, returning NULL with *ptlp unchanged, if there is no * page table at *pmd: if, for example, the page table has just been removed, * or replaced by the huge pmd of a THP. (When successful, *pmd is rechecked * after acquiring the ptlock, and retried internally if it changed: so that a * page table can be safely removed or replaced by THP while holding its lock.) * * pte_offset_map(pmd, addr), and its internal helper __pte_offset_map() above, * just returns the pte pointer for addr, its page table kmapped if necessary; * or NULL if there is no page table at *pmd. It does not attempt to lock the * page table, so cannot normally be used when the page table is to be updated, * or when entries read must be stable. But it does take rcu_read_lock(): so * that even when page table is racily removed, it remains a valid though empty * and disconnected table. Until pte_unmap(pte) unmaps and rcu_read_unlock()s * afterwards. * * pte_offset_map_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map(); * but when successful, it also outputs a pointer to the spinlock in ptlp - as * pte_offset_map_lock() does, but in this case without locking it. This helps * the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time * act on a changed *pmd: pte_offset_map_nolock() provides the correct spinlock * pointer for the page table that it returns. In principle, the caller should * recheck *pmd once the lock is taken; in practice, no callsite needs that - * either the mmap_lock for write, or pte_same() check on contents, is enough. * * Note that free_pgtables(), used after unmapping detached vmas, or when * exiting the whole mm, does not take page table lock before freeing a page * table, and may not use RCU at all: "outsiders" like khugepaged should avoid * pte_offset_map() and co once the vma is detached from mm or mm_users is zero. */ pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { spinlock_t *ptl; pmd_t pmdval; pte_t *pte; again: pte = __pte_offset_map(pmd, addr, &pmdval); if (unlikely(!pte)) return pte; ptl = pte_lockptr(mm, &pmdval); spin_lock(ptl); if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) { *ptlp = ptl; return pte; } pte_unmap_unlock(pte, ptl); goto again; } |
| 32 32 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * * File: ima_iint.c * - implements the IMA hook: ima_inode_free * - cache integrity information in the inode security blob */ #include <linux/slab.h> #include "ima.h" static struct kmem_cache *ima_iint_cache __ro_after_init; /** * ima_iint_find - Return the iint associated with an inode * @inode: Pointer to the inode * * Return the IMA integrity information (iint) associated with an inode, if the * inode was processed by IMA. * * Return: Found iint or NULL. */ struct ima_iint_cache *ima_iint_find(struct inode *inode) { if (!IS_IMA(inode)) return NULL; return ima_inode_get_iint(inode); } #define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH + 1) /* * It is not clear that IMA should be nested at all, but as long is it measures * files both on overlayfs and on underlying fs, we need to annotate the iint * mutex to avoid lockdep false positives related to IMA + overlayfs. * See ovl_lockdep_annotate_inode_mutex_key() for more details. */ static inline void ima_iint_lockdep_annotate(struct ima_iint_cache *iint, struct inode *inode) { #ifdef CONFIG_LOCKDEP static struct lock_class_key ima_iint_mutex_key[IMA_MAX_NESTING]; int depth = inode->i_sb->s_stack_depth; if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING)) depth = 0; lockdep_set_class(&iint->mutex, &ima_iint_mutex_key[depth]); #endif } static void ima_iint_init_always(struct ima_iint_cache *iint, struct inode *inode) { iint->ima_hash = NULL; iint->real_inode.version = 0; iint->flags = 0UL; iint->atomic_flags = 0UL; iint->ima_file_status = INTEGRITY_UNKNOWN; iint->ima_mmap_status = INTEGRITY_UNKNOWN; iint->ima_bprm_status = INTEGRITY_UNKNOWN; iint->ima_read_status = INTEGRITY_UNKNOWN; iint->ima_creds_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; mutex_init(&iint->mutex); ima_iint_lockdep_annotate(iint, inode); } static void ima_iint_free(struct ima_iint_cache *iint) { kfree(iint->ima_hash); mutex_destroy(&iint->mutex); kmem_cache_free(ima_iint_cache, iint); } /** * ima_inode_get - Find or allocate an iint associated with an inode * @inode: Pointer to the inode * * Find an iint associated with an inode, and allocate a new one if not found. * Caller must lock i_mutex. * * Return: An iint on success, NULL on error. */ struct ima_iint_cache *ima_inode_get(struct inode *inode) { struct ima_iint_cache *iint; iint = ima_iint_find(inode); if (iint) return iint; iint = kmem_cache_alloc(ima_iint_cache, GFP_NOFS); if (!iint) return NULL; ima_iint_init_always(iint, inode); inode->i_flags |= S_IMA; ima_inode_set_iint(inode, iint); return iint; } /** * ima_inode_free - Called on inode free * @inode: Pointer to the inode * * Free the iint associated with an inode. */ void ima_inode_free(struct inode *inode) { struct ima_iint_cache *iint; if (!IS_IMA(inode)) return; iint = ima_iint_find(inode); ima_inode_set_iint(inode, NULL); ima_iint_free(iint); } static void ima_iint_init_once(void *foo) { struct ima_iint_cache *iint = (struct ima_iint_cache *)foo; memset(iint, 0, sizeof(*iint)); } void __init ima_iintcache_init(void) { ima_iint_cache = kmem_cache_create("ima_iint_cache", sizeof(struct ima_iint_cache), 0, SLAB_PANIC, ima_iint_init_once); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * NOHZ implementation for low and high resolution timers * * Started by: Thomas Gleixner and Ingo Molnar */ #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/percpu.h> #include <linux/nmi.h> #include <linux/profile.h> #include <linux/sched/signal.h> #include <linux/sched/clock.h> #include <linux/sched/stat.h> #include <linux/sched/nohz.h> #include <linux/sched/loadavg.h> #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> #include <linux/context_tracking.h> #include <linux/mm.h> #include <asm/irq_regs.h> #include "tick-internal.h" #include <trace/events/timer.h> /* * Per-CPU nohz control structure */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } /* * The time when the last jiffy update happened. Write access must hold * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a * consistent view of jiffies and last_jiffies_update. */ static ktime_t last_jiffies_update; /* * Must be called with interrupts disabled ! */ static void tick_do_update_jiffies64(ktime_t now) { unsigned long ticks = 1; ktime_t delta, nextp; /* * 64-bit can do a quick check without holding the jiffies lock and * without looking at the sequence count. The smp_load_acquire() * pairs with the update done later in this function. * * 32-bit cannot do that because the store of 'tick_next_period' * consists of two 32-bit stores, and the first store could be * moved by the CPU to a random point in the future. */ if (IS_ENABLED(CONFIG_64BIT)) { if (ktime_before(now, smp_load_acquire(&tick_next_period))) return; } else { unsigned int seq; /* * Avoid contention on 'jiffies_lock' and protect the quick * check with the sequence count. */ do { seq = read_seqcount_begin(&jiffies_seq); nextp = tick_next_period; } while (read_seqcount_retry(&jiffies_seq, seq)); if (ktime_before(now, nextp)) return; } /* Quick check failed, i.e. update is required. */ raw_spin_lock(&jiffies_lock); /* * Re-evaluate with the lock held. Another CPU might have done the * update already. */ if (ktime_before(now, tick_next_period)) { raw_spin_unlock(&jiffies_lock); return; } write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, tick_next_period); if (unlikely(delta >= TICK_NSEC)) { /* Slow path for long idle sleep times */ s64 incr = TICK_NSEC; ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); } else { last_jiffies_update = ktime_add_ns(last_jiffies_update, TICK_NSEC); } /* Advance jiffies to complete the 'jiffies_seq' protected job */ jiffies_64 += ticks; /* Keep the tick_next_period variable up to date */ nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC); if (IS_ENABLED(CONFIG_64BIT)) { /* * Pairs with smp_load_acquire() in the lockless quick * check above, and ensures that the update to 'jiffies_64' is * not reordered vs. the store to 'tick_next_period', neither * by the compiler nor by the CPU. */ smp_store_release(&tick_next_period, nextp); } else { /* * A plain store is good enough on 32-bit, as the quick check * above is protected by the sequence count. */ tick_next_period = nextp; } /* * Release the sequence count. calc_global_load() below is not * protected by it, but 'jiffies_lock' needs to be held to prevent * concurrent invocations. */ write_seqcount_end(&jiffies_seq); calc_global_load(); raw_spin_unlock(&jiffies_lock); update_wall_time(); } /* * Initialize and return retrieve the jiffies update. */ static ktime_t tick_init_jiffy_update(void) { ktime_t period; raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Have we started the jiffies update yet ? */ if (last_jiffies_update == 0) { u32 rem; /* * Ensure that the tick is aligned to a multiple of * TICK_NSEC. */ div_u64_rem(tick_next_period, TICK_NSEC, &rem); if (rem) tick_next_period += TICK_NSEC - rem; last_jiffies_update = tick_next_period; } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); return period; } static inline int tick_sched_flag_test(struct tick_sched *ts, unsigned long flag) { return !!(ts->flags & flag); } static inline void tick_sched_flag_set(struct tick_sched *ts, unsigned long flag) { lockdep_assert_irqs_disabled(); ts->flags |= flag; } static inline void tick_sched_flag_clear(struct tick_sched *ts, unsigned long flag) { lockdep_assert_irqs_disabled(); ts->flags &= ~flag; } #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int tick_cpu, cpu = smp_processor_id(); /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * 'jiffies_lock'. * * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ tick_cpu = READ_ONCE(tick_do_timer_cpu); if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif WRITE_ONCE(tick_do_timer_cpu, cpu); tick_cpu = cpu; } /* Check if jiffies need an update */ if (tick_cpu == cpu) tick_do_update_jiffies64(now); /* * If the jiffies update stalled for too long (timekeeper in stop_machine() * or VMEXIT'ed for several msecs), force an update. */ if (ts->last_tick_jiffies != jiffies) { ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } else { if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) { tick_do_update_jiffies64(now); ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } } if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long * time. This happens on completely idle SMP systems while * waiting on the login prompt. We also increment the "start of * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too many ticks. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; /* * In case the current tick fired too early past its expected * expiration, make sure we don't bypass the next clock reprogramming * to the same deadline. */ ts->next_tick = 0; } update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } /* * We rearm the timer until we get disabled by the idle code. * Called with interrupts disabled. */ static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer) { struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); tick_sched_do_timer(ts, now); /* * Do not call when we are not in IRQ context and have * no valid 'regs' pointer */ if (regs) tick_sched_handle(ts, regs); else ts->next_tick = 0; /* * In dynticks mode, tick reprogram is deferred: * - to the idle task if in dynticks-idle * - to IRQ exit if in full-dynticks. */ if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED))) return HRTIMER_NORESTART; hrtimer_forward(timer, now, TICK_NSEC); return HRTIMER_RESTART; } static void tick_sched_timer_cancel(struct tick_sched *ts) { if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) hrtimer_cancel(&ts->sched_timer); else if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) tick_program_event(KTIME_MAX, 1); } #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; EXPORT_SYMBOL_GPL(tick_nohz_full_mask); bool tick_nohz_full_running; EXPORT_SYMBOL_GPL(tick_nohz_full_running); static atomic_t tick_dep_mask; static bool check_tick_dependency(atomic_t *dep) { int val = atomic_read(dep); if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); return true; } if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); return true; } if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); return true; } if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); return true; } if (val & TICK_DEP_MASK_RCU) { trace_tick_stop(0, TICK_DEP_MASK_RCU); return true; } if (val & TICK_DEP_MASK_RCU_EXP) { trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP); return true; } return false; } static bool can_stop_full_tick(int cpu, struct tick_sched *ts) { lockdep_assert_irqs_disabled(); if (unlikely(!cpu_online(cpu))) return false; if (check_tick_dependency(&tick_dep_mask)) return false; if (check_tick_dependency(&ts->tick_dep_mask)) return false; if (check_tick_dependency(¤t->tick_dep_mask)) return false; if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; return true; } static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = IRQ_WORK_INIT_HARD(nohz_full_kick_func); /* * Kick this CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; irq_work_queue(this_cpu_ptr(&nohz_full_kick_work)); } /* * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ void tick_nohz_full_kick_cpu(int cpu) { if (!tick_nohz_full_cpu(cpu)) return; irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } static void tick_nohz_kick_task(struct task_struct *tsk) { int cpu; /* * If the task is not running, run_posix_cpu_timers() * has nothing to elapse, and an IPI can then be optimized out. * * activate_task() STORE p->tick_dep_mask * STORE p->on_rq * __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or()) * LOCK rq->lock LOAD p->on_rq * smp_mb__after_spin_lock() * tick_nohz_task_switch() * LOAD p->tick_dep_mask */ if (!sched_task_on_rq(tsk)) return; /* * If the task concurrently migrates to another CPU, * we guarantee it sees the new tick dependency upon * schedule. * * set_task_cpu(p, cpu); * STORE p->cpu = @cpu * __schedule() (switch to task 'p') * LOCK rq->lock * smp_mb__after_spin_lock() STORE p->tick_dep_mask * tick_nohz_task_switch() smp_mb() (atomic_fetch_or()) * LOAD p->tick_dep_mask LOAD p->cpu */ cpu = task_cpu(tsk); preempt_disable(); if (cpu_online(cpu)) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ static void tick_nohz_full_kick_all(void) { int cpu; if (!tick_nohz_full_running) return; preempt_disable(); for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { int prev; prev = atomic_fetch_or(BIT(bit), dep); if (!prev) tick_nohz_full_kick_all(); } /* * Set a global tick dependency. Used by perf events that rely on freq and * unstable clocks. */ void tick_nohz_dep_set(enum tick_dep_bits bit) { tick_nohz_dep_set_all(&tick_dep_mask, bit); } void tick_nohz_dep_clear(enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tick_dep_mask); } /* * Set per-CPU tick dependency. Used by scheduler and perf events in order to * manage event-throttling. */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ if (cpu == smp_processor_id()) { tick_nohz_full_kick(); } else { /* Remote IRQ work not NMI-safe */ if (!WARN_ON_ONCE(in_nmi())) tick_nohz_full_kick_cpu(cpu); } preempt_enable(); } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); atomic_andnot(BIT(bit), &ts->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. RCU needs this. Also posix CPU timers * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) tick_nohz_kick_task(tsk); } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task); /* * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse * per process timers. */ void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { int prev; struct signal_struct *sig = tsk->signal; prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask); if (!prev) { struct task_struct *t; lockdep_assert_held(&tsk->sighand->siglock); __for_each_thread(sig, t) tick_nohz_kick_task(t); } } void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: * perf events, posix CPU timers, ... */ void __tick_nohz_task_switch(void) { struct tick_sched *ts; if (!tick_nohz_full_cpu(smp_processor_id())) return; ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } } /* Get the boot-time nohz CPU list from the kernel parameters. */ void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; } bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu) return false; return true; } static int tick_nohz_cpu_down(unsigned int cpu) { return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) { int cpu, ret; if (!tick_nohz_full_running) return; /* * Full dynticks uses IRQ work to drive the tick rescheduling on safe * locking contexts. But then we need IRQ work to raise its own * interrupts to avoid circular dependency on the tick. */ if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); tick_nohz_full_running = false; return; } if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { pr_warn("NO_HZ: Clearing %d from nohz_full range " "for timekeeping\n", cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } } for_each_cpu(cpu, tick_nohz_full_mask) ct_cpu_track_user(cpu); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "kernel/nohz:predown", NULL, tick_nohz_cpu_down); WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } #endif /* #ifdef CONFIG_NO_HZ_FULL */ /* * NOHZ - aka dynamic tick functionality */ #ifdef CONFIG_NO_HZ_COMMON /* * NO HZ enabled ? */ bool tick_nohz_enabled __read_mostly = true; unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * * In case the sched_tick was stopped on this CPU, we have to check if jiffies * must be updated. Otherwise an interrupt handler could use a stale jiffy * value. We do this unconditionally on any CPU, as we don't know whether the * CPU, which has the update task assigned, is in a long sleep. */ static void tick_nohz_update_jiffies(ktime_t now) { unsigned long flags; __this_cpu_write(tick_cpu_sched.idle_waketime, now); local_irq_save(flags); tick_do_update_jiffies64(now); local_irq_restore(flags); touch_softlockup_watchdog_sched(); } static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { ktime_t delta; if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))) return; delta = ktime_sub(now, ts->idle_entrytime); write_seqcount_begin(&ts->idle_sleeptime_seq); if (nr_iowait_cpu(smp_processor_id()) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); else ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_wakeup_event(); } static void tick_nohz_start_idle(struct tick_sched *ts) { write_seqcount_begin(&ts->idle_sleeptime_seq); ts->idle_entrytime = ktime_get(); tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_sleep_event(); } static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, bool compute_delta, u64 *last_update_time) { ktime_t now, idle; unsigned int seq; if (!tick_nohz_active) return -1; now = ktime_get(); if (last_update_time) *last_update_time = ktime_to_us(now); do { seq = read_seqcount_begin(&ts->idle_sleeptime_seq); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(*sleeptime, delta); } else { idle = *sleeptime; } } while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq)); return ktime_to_us(idle); } /** * get_cpu_idle_time_us - get the total idle time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative idle time (since boot) for a given * CPU, in microseconds. Note that this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime, !nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); /** * get_cpu_iowait_time_us - get the total iowait time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative iowait time (since boot) for a given * CPU, in microseconds. Note this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime, nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); hrtimer_set_expires(&ts->sched_timer, ts->last_tick); /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); } else { tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } /* * Reset to make sure the next tick stop doesn't get fooled by past * cached clock deadline. */ ts->next_tick = 0; } static inline bool local_timer_softirq_pending(void) { return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } /* * Read jiffies and the time when jiffies were updated last */ u64 get_jiffies_update(unsigned long *basej) { unsigned long basejiff; unsigned int seq; u64 basemono; do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); *basej = basejiff; return basemono; } /** * tick_nohz_next_event() - return the clock monotonic based next event * @ts: pointer to tick_sched struct * @cpu: CPU number * * Return: * *%0 - When the next event is a maximum of TICK_NSEC in the future * and the tick is not stopped yet * *%next_event - Next event based on clock monotonic */ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, delta, expires; unsigned long basejiff; int tick_cpu; basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work * requests it. * Aside of that, check whether the local timer softirq is * pending. If so, its a bad idea to call get_next_timer_interrupt(), * because there is an already expired timer, so it will request * immediate expiry, which rearms the hardware timer with a * minimal delta, which brings us back to this place * immediately. Lather, rinse and repeat... */ if (rcu_needs_cpu() || arch_needs_cpu() || irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* * Get the next pending timer. If high resolution * timers are enabled this only takes the timer wheel * timers into account. If high resolution timers are * disabled this also looks at the next expiring * hrtimer. */ next_tick = get_next_timer_interrupt(basejiff, basemono); ts->next_timer = next_tick; } /* Make sure next_tick is never before basemono! */ if (WARN_ON_ONCE(basemono > next_tick)) next_tick = basemono; /* * If the tick is due in the next period, keep it ticking or * force prod the timer. */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->timer_expires = 0; goto out; } } /* * If this CPU is the one which had the do_timer() duty last, we limit * the sleep time to the timekeeping 'max_deferment' value. * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); tick_cpu = READ_ONCE(tick_do_timer_cpu); if (tick_cpu != cpu && (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta; else expires = KTIME_MAX; ts->timer_expires = min_t(u64, expires, next_tick); out: return ts->timer_expires; } static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); int tick_cpu; u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* * Now the tick should be stopped definitely - so the timer base needs * to be marked idle as well to not miss a newly queued timer. */ expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle); if (expires > ts->timer_expires) { /* * This path could only happen when the first timer was removed * between calculating the possible sleep length and now (when * high resolution mode is not active, timer could also be a * hrtimer). * * We have to stick to the original calculated expiry value to * not stop the tick for too long with a shallow C-state (which * was programmed by cpuidle because of an early next expiration * value). */ expires = ts->timer_expires; } /* If the timer base is not idle, retain the not yet stopped tick. */ if (!timer_idle) return; /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we * don't drop this here, the jiffies might be stale and * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ tick_cpu = READ_ONCE(tick_do_timer_cpu); if (tick_cpu == cpu) { WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE); tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); } else if (tick_cpu != TICK_DO_TIMER_NONE) { tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } /* Skip reprogram of event if it's not changed */ if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; WARN_ON_ONCE(1); printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick, dev->next_event, hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); } /* * tick_nohz_stop_tick() can be called several times before * tick_nohz_restart_sched_tick() is called. This happens when * interrupts arrive which do not cause a reschedule. In the first * call we save the current tick time, so we can restart the * scheduler tick in tick_nohz_restart_sched_tick(). */ if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); tick_sched_flag_set(ts, TS_FLAG_STOPPED); trace_tick_stop(1, TICK_DEP_MASK_NONE); } ts->next_tick = expires; /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { tick_sched_timer_cancel(ts); return; } if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, expires); tick_program_event(expires, 1); } } static void tick_nohz_retain_tick(struct tick_sched *ts) { ts->timer_expires_base = 0; } #ifdef CONFIG_NO_HZ_FULL static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); else tick_nohz_retain_tick(ts); } #endif /* CONFIG_NO_HZ_FULL */ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); /* * Clear the timer idle flag, so we avoid IPIs on remote queueing and * the clock forward checks in the enqueue path: */ timer_clear_idle(); calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* Cancel the scheduled timer and restore the tick: */ tick_sched_flag_clear(ts, TS_FLAG_STOPPED); tick_nohz_restart(ts, now); } static void __tick_nohz_full_update_tick(struct tick_sched *ts, ktime_t now) { #ifdef CONFIG_NO_HZ_FULL int cpu = smp_processor_id(); if (can_stop_full_tick(cpu, ts)) tick_nohz_full_stop_tick(ts, cpu); else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_restart_sched_tick(ts, now); #endif } static void tick_nohz_full_update_tick(struct tick_sched *ts) { if (!tick_nohz_full_cpu(smp_processor_id())) return; if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return; __tick_nohz_full_update_tick(ts, ktime_get()); } /* * A pending softirq outside an IRQ (or softirq disabled section) context * should be waiting for ksoftirqd to handle it. Therefore we shouldn't * reach this code due to the need_resched() early check in can_stop_idle_tick(). * * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the * cpu_down() process, softirqs can still be raised while ksoftirqd is parked, * triggering the code below, since wakep_softirqd() is ignored. * */ static bool report_idle_softirq(void) { static int ratelimit; unsigned int pending = local_softirq_pending(); if (likely(!pending)) return false; /* Some softirqs claim to be safe against hotplug and ksoftirqd parking */ if (!cpu_active(smp_processor_id())) { pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK; if (!pending) return false; } if (ratelimit >= 10) return false; /* On RT, softirq handling may be waiting on some lock */ if (local_bh_blocked()) return false; pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", pending); ratelimit++; return true; } static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { WARN_ON_ONCE(cpu_is_offline(cpu)); if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ))) return false; if (need_resched()) return false; if (unlikely(report_idle_softirq())) return false; if (tick_nohz_full_enabled()) { int tick_cpu = READ_ONCE(tick_do_timer_cpu); /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ if (tick_cpu == cpu) return false; /* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE)) return false; } return true; } /** * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick */ void tick_nohz_idle_stop_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); ktime_t expires; /* * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the * tick timer expiration time is known already. */ if (ts->timer_expires_base) expires = ts->timer_expires; else if (can_stop_idle_tick(cpu, ts)) expires = tick_nohz_next_event(ts, cpu); else return; ts->idle_calls++; if (expires > 0LL) { int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } } else { tick_nohz_retain_tick(ts); } } void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); } /** * tick_nohz_idle_enter - prepare for entering idle on the current CPU * * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { struct tick_sched *ts; lockdep_assert_irqs_enabled(); local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_set(ts, TS_FLAG_INIDLE); tick_nohz_start_idle(ts); local_irq_enable(); } /** * tick_nohz_irq_exit - Notify the tick about IRQ exit * * A timer may have been added/modified/deleted either by the current IRQ, * or by another place using this IRQ as a notification. This IRQ may have * also updated the RCU callback list. These events may require a * re-evaluation of the next tick. Depending on the context: * * 1) If the CPU is idle and no resched is pending, just proceed with idle * time accounting. The next tick will be re-evaluated on the next idle * loop iteration. * * 2) If the CPU is nohz_full: * * 2.1) If there is any tick dependency, restart the tick if stopped. * * 2.2) If there is no tick dependency, (re-)evaluate the next tick and * stop/update it accordingly. */ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run * * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->got_idle_tick) { ts->got_idle_tick = 0; return true; } return false; } /** * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer * or the tick, whichever expires first. Note that, if the tick has been * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled * * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { return __this_cpu_read(tick_cpu_device.evtdev)->next_event; } /** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled. * * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. * * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); /* * The idle entry time is expected to be a sufficient approximation of * the current time at this point. */ ktime_t now = ts->idle_entrytime; ktime_t next_event; WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); *delta_next = ktime_sub(dev->next_event, now); if (!can_stop_idle_tick(cpu, ts)) return *delta_next; next_event = tick_nohz_next_event(ts, cpu); if (!next_event) return *delta_next; /* * If the next highres timer to expire is earlier than 'next_event', the * idle governor needs to know that. */ next_event = min_t(u64, next_event, hrtimer_next_event_without(&ts->sched_timer)); return ktime_sub(next_event, now); } /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. * * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { struct tick_sched *ts = tick_get_tick_sched(cpu); return ts->idle_calls; } /** * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. * * Return: the current idle calls counter value for the current CPU */ unsigned long tick_nohz_get_idle_calls(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return ts->idle_calls; } static void tick_nohz_account_idle_time(struct tick_sched *ts, ktime_t now) { unsigned long ticks; ts->idle_exittime = now; if (vtime_accounting_enabled_this_cpu()) return; /* * We stopped the tick in idle. update_process_times() would miss the * time we slept, as it does only a 1 tick accounting. * Enforce that this is accounted to idle ! */ ticks = jiffies - ts->idle_jiffies; /* * We might be one off. Do not randomly account a huge number of ticks! */ if (ticks && ticks < LONG_MAX) account_idle_ticks(ticks); } void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ktime_t now = ktime_get(); tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } } static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now) { if (tick_nohz_full_cpu(smp_processor_id())) __tick_nohz_full_update_tick(ts, now); else tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } /** * tick_nohz_idle_exit - Update the tick upon idle task exit * * When the idle task exits, update the tick depending on the * following situations: * * 1) If the CPU is not in nohz_full mode (most cases), then * restart the tick. * * 2) If the CPU is in nohz_full mode (corner case): * 2.1) If the tick can be kept stopped (no tick dependencies) * then re-evaluate the next tick and try to keep it stopped * as long as possible. * 2.2) If the tick has dependencies, restart the tick. * */ void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_clear(ts, TS_FLAG_INIDLE); idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE); tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); if (idle_active || tick_stopped) now = ktime_get(); if (idle_active) tick_nohz_stop_idle(ts, now); if (tick_stopped) tick_nohz_idle_update_tick(ts, now); local_irq_enable(); } /* * In low-resolution mode, the tick handler must be implemented directly * at the clockevent level. hrtimer can't be used instead, because its * infrastructure actually relies on the tick itself as a backend in * low-resolution mode (see hrtimer_run_queues()). */ static void tick_nohz_lowres_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); dev->next_event = KTIME_MAX; if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART)) tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } static inline void tick_nohz_activate(struct tick_sched *ts) { if (!tick_nohz_enabled) return; tick_sched_flag_set(ts, TS_FLAG_NOHZ); /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); } /** * tick_nohz_switch_to_nohz - switch to NOHZ mode */ static void tick_nohz_switch_to_nohz(void) { if (!tick_nohz_enabled) return; if (tick_switch_to_oneshot(tick_nohz_lowres_handler)) return; /* * Recycle the hrtimer in 'ts', so we can share the * highres code. */ tick_setup_sched_timer(false); } static inline void tick_nohz_irq_enter(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE)) return; now = ktime_get(); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) tick_nohz_stop_idle(ts, now); /* * If all CPUs are idle we may need to update a stale jiffies value. * Note nohz_full is a special case: a timekeeper is guaranteed to stay * alive but it might be busy looping with interrupts disabled in some * rare case (typically stop machine). So we must make sure we have a * last resort. */ if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_update_jiffies(now); } #else static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } static inline void tick_nohz_activate(struct tick_sched *ts) { } #endif /* CONFIG_NO_HZ_COMMON */ /* * Called from irq_enter() to notify about the possible interruption of idle() */ void tick_irq_enter(void) { tick_check_oneshot_broadcast_this_cpu(); tick_nohz_irq_enter(); } static int sched_skew_tick; static int __init skew_tick(char *str) { get_option(&str, &sched_skew_tick); return 0; } early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer * @hrtimer: whether to use the hrtimer or not */ void tick_setup_sched_timer(bool hrtimer) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); /* Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) { tick_sched_flag_set(ts, TS_FLAG_HIGHRES); ts->sched_timer.function = tick_nohz_handler; } /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); /* Offset the tick to avert 'jiffies_lock' contention. */ if (sched_skew_tick) { u64 offset = TICK_NSEC >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); hrtimer_add_expires_ns(&ts->sched_timer, offset); } hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); else tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts); } /* * Shut down the tick and make sure the CPU won't try to retake the timekeeping * duty before disabling IRQs in idle for the last time. */ void tick_sched_timer_dying(int cpu) { struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); struct clock_event_device *dev = td->evtdev; ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; /* This must happen before hrtimers are migrated! */ tick_sched_timer_cancel(ts); /* * If the clockevents doesn't support CLOCK_EVT_STATE_ONESHOT_STOPPED, * make sure not to call low-res tick handler. */ if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) dev->event_handler = clockevents_handle_noop; idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; idle_calls = ts->idle_calls; idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); ts->idle_sleeptime = idle_sleeptime; ts->iowait_sleeptime = iowait_sleeptime; ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } /* * Async notification about clocksource changes */ void tick_clock_notify(void) { int cpu; for_each_possible_cpu(cpu) set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks); } /* * Async notification about clock event changes */ void tick_oneshot_notify(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); set_bit(0, &ts->check_clocks); } /* * Check if a change happened, which makes oneshot possible. * * Called cyclically from the hrtimer softirq (driven by the timer * softirq). 'allow_nohz' signals that we can switch into low-res NOHZ * mode, because high resolution timers are disabled (either compile * or runtime). Called with interrupts disabled. */ int tick_check_oneshot_change(int allow_nohz) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) return 0; if (!allow_nohz) return 1; tick_nohz_switch_to_nohz(); return 0; } |
| 121 118 121 121 121 288 288 121 120 119 89 120 121 265 265 264 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /* * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock). * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @fast_path determine the * tracepoints being added, allowing us to diagnose "flush" related * operations without handling high-frequency fast-path "update" events. */ static __always_inline unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, const bool fast_path) { unsigned long flags; bool contended; /* * The _irqsave() is needed because cgroup_rstat_lock is * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring * this lock with the _irq() suffix only disables interrupts on * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables * interrupts on both configurations. The _irqsave() ensures * that interrupts are always disabled and later restored. */ contended = !raw_spin_trylock_irqsave(cpu_lock, flags); if (contended) { if (fast_path) trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended); raw_spin_lock_irqsave(cpu_lock, flags); } if (fast_path) trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended); return flags; } static __always_inline void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, unsigned long flags, const bool fast_path) { if (fast_path) trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false); else trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false); raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = cgrp; break; } prstatc = cgroup_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; cgrp = parent; } _cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true); } /** * cgroup_rstat_push_children - push children cgroups into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of cgroups to be flush * * Iteratively traverse down the cgroup_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list built from the tail backward like "pushing" * cgroups into a stack. The root is pushed by the caller. */ static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, struct cgroup *child, int cpu) { struct cgroup *chead = child; /* Head of child cgroup level */ struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ struct cgroup *parent, *grandchild; struct cgroup_rstat_cpu *crstatc; child->rstat_flush_next = NULL; next_level: while (chead) { child = chead; chead = child->rstat_flush_next; parent = cgroup_parent(child); /* updated_next is parent cgroup terminated */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = cgroup_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { chead = ghead; ghead = NULL; goto next_level; } return head; } /** * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed * @root: root of the cgroup subtree to traverse * @cpu: target cpu * Return: A singly linked list of cgroups to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child cgroups if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent cgroup. An exception * here is the cgroup root whose updated_next can be self terminated. */ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); struct cgroup *head = NULL, *parent, *child; unsigned long flags; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) goto unlock_ret; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = cgroup_rstat_push_children(head, child, cpu); unlock_ret: _cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for cgroup_rstat_updated() and * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking cgroup_rstat_lock. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop) __acquires(&cgroup_rstat_lock) { bool contended; contended = !spin_trylock_irq(&cgroup_rstat_lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(&cgroup_rstat_lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop) __releases(&cgroup_rstat_lock) { trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(&cgroup_rstat_lock); } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu); for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); bpf_rstat_flush(pos, cgroup_parent(pos), cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { __cgroup_rstat_unlock(cgrp, cpu); if (!cond_resched()) cpu_relax(); __cgroup_rstat_lock(cgrp, cpu); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); __cgroup_rstat_unlock(cgrp, -1); } /** * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() * @cgrp: cgroup used by tracepoint */ void cgroup_rstat_flush_release(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) { __cgroup_rstat_unlock(cgrp, -1); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); delta = rstatc->bstat; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); cgroup_base_stat_add(&rstatc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatc->subtree_bstat; prstatc = cgroup_rstat_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat); cgroup_base_stat_add(&prstatc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif } } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; struct cgroup_base_stat bstat; #ifdef CONFIG_SCHED_CORE u64 forceidle_time; #endif if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); #ifdef CONFIG_SCHED_CORE forceidle_time = cgrp->bstat.forceidle_sum; #endif cgroup_rstat_flush_release(cgrp); } else { root_cgroup_cputime(&bstat); usage = bstat.cputime.sum_exec_runtime; utime = bstat.cputime.utime; stime = bstat.cputime.stime; #ifdef CONFIG_SCHED_CORE forceidle_time = bstat.forceidle_sum; #endif } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); #ifdef CONFIG_SCHED_CORE do_div(forceidle_time, NSEC_PER_USEC); #endif seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); #ifdef CONFIG_SCHED_CORE seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 126 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * A 'generic' spinlock implementation that is based on MCS locks. For an * architecture that's looking for a 'generic' spinlock, please first consider * ticket-lock.h and only come looking here when you've considered all the * constraints below and can show your hardware does actually perform better * with qspinlock. * * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no * weaker than RCtso if you're power), where regular code only expects atomic_t * to be RCpc. * * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set * of atomic operations to behave well together, please audit them carefully to * ensure they all have forward progress. Many atomic operations may default to * cmpxchg() loops which will not have good forward progress properties on * LL/SC architectures. * * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) * do. Carefully read the patches that introduced * queued_fetch_set_pending_acquire(). * * qspinlock also heavily relies on mixed size atomic operations, in specific * it requires architectures to have xchg16; something which many LL/SC * architectures need to implement as a 32bit and+or in order to satisfy the * forward progress guarantees mentioned above. * * Further reading on mixed size atomics that might be relevant: * * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { int val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { int val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 107 107 107 107 107 36 36 36 36 107 134 134 134 107 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rcuwait writer; wait_queue_head_t waiters; atomic_t block; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }, #else #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) #endif #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \ .block = ATOMIC_INIT(0), \ __PERCPU_RWSEM_DEP_MAP_INIT(name) \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool); static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); preempt_disable(); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); } static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked * writer. */ smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); } extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) { return atomic_read(&sem->block); } extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_held(sem) lockdep_is_held(sem) #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_release(&sem->dep_map, ip); } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip); } #endif |
| 58 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Descending-priority-sorted double-linked list * * (C) 2002-2003 Intel Corp * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>. * * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * * (C) 2005 Thomas Gleixner <tglx@linutronix.de> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> * * Based on simple lists (include/linux/list.h). * * This is a priority-sorted list of nodes; each node has a * priority from INT_MIN (highest) to INT_MAX (lowest). * * Addition is O(K), removal is O(1), change of priority of a node is * O(K) and K is the number of RT priority levels used in the system. * (1 <= K <= 99) * * This list is really a list of lists: * * - The tier 1 list is the prio_list, different priority nodes. * * - The tier 2 list is the node_list, serialized nodes. * * Simple ASCII art explanation: * * pl:prio_list (only for plist_node) * nl:node_list * HEAD| NODE(S) * | * ||------------------------------------| * ||->|pl|<->|pl|<--------------->|pl|<-| * | |10| |21| |21| |21| |40| (prio) * | | | | | | | | | | | * | | | | | | | | | | | * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-| * |-------------------------------------------| * * The nodes on the prio_list list are sorted by priority to simplify * the insertion of new nodes. There are no nodes with duplicate * priorites on the list. * * The nodes on the node_list are ordered by priority and can contain * entries which have the same priority. Those entries are ordered * FIFO * * Addition means: look for the prio_list node in the prio_list * for the priority of the node and insert it before the node_list * entry of the next prio_list node. If it is the first node of * that priority, add it to the prio_list in the right position and * insert it into the serialized node_list list * * Removal means remove it from the node_list and remove it from * the prio_list if the node_list list_head is non empty. In case * of removal from the prio_list it must be checked whether other * entries of the same priority are on the list or not. If there * is another entry of the same priority then this entry has to * replace the removed entry on the prio_list. If the entry which * is removed is the only entry of this priority then a simple * remove from both list is sufficient. * * INT_MIN is the highest priority, 0 is the medium highest, INT_MAX * is lowest priority. * * No locking is done, up to the caller. */ #ifndef _LINUX_PLIST_H_ #define _LINUX_PLIST_H_ #include <linux/container_of.h> #include <linux/list.h> #include <linux/plist_types.h> #include <asm/bug.h> /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name */ #define PLIST_HEAD_INIT(head) \ { \ .node_list = LIST_HEAD_INIT((head).node_list) \ } /** * PLIST_HEAD - declare and init plist_head * @head: name for struct plist_head variable */ #define PLIST_HEAD(head) \ struct plist_head head = PLIST_HEAD_INIT(head) /** * PLIST_NODE_INIT - static struct plist_node initializer * @node: struct plist_node variable name * @__prio: initial node priority */ #define PLIST_NODE_INIT(node, __prio) \ { \ .prio = (__prio), \ .prio_list = LIST_HEAD_INIT((node).prio_list), \ .node_list = LIST_HEAD_INIT((node).node_list), \ } /** * plist_head_init - dynamic struct plist_head initializer * @head: &struct plist_head pointer */ static inline void plist_head_init(struct plist_head *head) { INIT_LIST_HEAD(&head->node_list); } /** * plist_node_init - Dynamic struct plist_node initializer * @node: &struct plist_node pointer * @prio: initial node priority */ static inline void plist_node_init(struct plist_node *node, int prio) { node->prio = prio; INIT_LIST_HEAD(&node->prio_list); INIT_LIST_HEAD(&node->node_list); } extern void plist_add(struct plist_node *node, struct plist_head *head); extern void plist_del(struct plist_node *node, struct plist_head *head); extern void plist_requeue(struct plist_node *node, struct plist_head *head); /** * plist_for_each - iterate over the plist * @pos: the type * to use as a loop counter * @head: the head for your list */ #define plist_for_each(pos, head) \ list_for_each_entry(pos, &(head)->node_list, node_list) /** * plist_for_each_continue - continue iteration over the plist * @pos: the type * to use as a loop cursor * @head: the head for your list * * Continue to iterate over plist, continuing after the current position. */ #define plist_for_each_continue(pos, head) \ list_for_each_entry_continue(pos, &(head)->node_list, node_list) /** * plist_for_each_safe - iterate safely over a plist of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage * @head: the head for your list * * Iterate over a plist of given type, safe against removal of list entry. */ #define plist_for_each_safe(pos, n, head) \ list_for_each_entry_safe(pos, n, &(head)->node_list, node_list) /** * plist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop counter * @head: the head for your list * @mem: the name of the list_head within the struct */ #define plist_for_each_entry(pos, head, mem) \ list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** * plist_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor * @head: the head for your list * @m: the name of the list_head within the struct * * Continue to iterate over list of given type, continuing after * the current position. */ #define plist_for_each_entry_continue(pos, head, m) \ list_for_each_entry_continue(pos, &(head)->node_list, m.node_list) /** * plist_for_each_entry_safe - iterate safely over list of given type * @pos: the type * to use as a loop counter * @n: another type * to use as temporary storage * @head: the head for your list * @m: the name of the list_head within the struct * * Iterate over list of given type, safe against removal of list entry. */ #define plist_for_each_entry_safe(pos, n, head, m) \ list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list) /** * plist_head_empty - return !0 if a plist_head is empty * @head: &struct plist_head pointer */ static inline int plist_head_empty(const struct plist_head *head) { return list_empty(&head->node_list); } /** * plist_node_empty - return !0 if plist_node is not on a list * @node: &struct plist_node pointer */ static inline int plist_node_empty(const struct plist_node *node) { return list_empty(&node->node_list); } /* All functions below assume the plist_head is not empty. */ /** * plist_first_entry - get the struct for the first entry * @head: the &struct plist_head pointer * @type: the type of the struct this is embedded in * @member: the name of the list_head within the struct */ #ifdef CONFIG_DEBUG_PLIST # define plist_first_entry(head, type, member) \ ({ \ WARN_ON(plist_head_empty(head)); \ container_of(plist_first(head), type, member); \ }) #else # define plist_first_entry(head, type, member) \ container_of(plist_first(head), type, member) #endif /** * plist_last_entry - get the struct for the last entry * @head: the &struct plist_head pointer * @type: the type of the struct this is embedded in * @member: the name of the list_head within the struct */ #ifdef CONFIG_DEBUG_PLIST # define plist_last_entry(head, type, member) \ ({ \ WARN_ON(plist_head_empty(head)); \ container_of(plist_last(head), type, member); \ }) #else # define plist_last_entry(head, type, member) \ container_of(plist_last(head), type, member) #endif /** * plist_next - get the next entry in list * @pos: the type * to cursor */ #define plist_next(pos) \ list_next_entry(pos, node_list) /** * plist_prev - get the prev entry in list * @pos: the type * to cursor */ #define plist_prev(pos) \ list_prev_entry(pos, node_list) /** * plist_first - return the first node (and thus, highest priority) * @head: the &struct plist_head pointer * * Assumes the plist is _not_ empty. */ static inline struct plist_node *plist_first(const struct plist_head *head) { return list_entry(head->node_list.next, struct plist_node, node_list); } /** * plist_last - return the last node (and thus, lowest priority) * @head: the &struct plist_head pointer * * Assumes the plist is _not_ empty. */ static inline struct plist_node *plist_last(const struct plist_head *head) { return list_entry(head->node_list.prev, struct plist_node, node_list); } #endif |
| 83 3 3 3 3 2 3 17 2 2 2 2 2 2 2 2 2 2 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Author: Alex Bennée <alex.bennee@linaro.org> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include "trace.h" /* These are the bits of MDSCR_EL1 we may manipulate */ #define MDSCR_EL1_DEBUG_MASK (DBG_MDSCR_SS | \ DBG_MDSCR_KDE | \ DBG_MDSCR_MDE) static DEFINE_PER_CPU(u64, mdcr_el2); /* * save/restore_guest_debug_regs * * For some debug operations we need to tweak some guest registers. As * a result we need to save the state of those registers before we * make those modifications. * * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled * after we have restored the preserved value to the main context. * * When single-step is enabled by userspace, we tweak PSTATE.SS on every * guest entry. Preserve PSTATE.SS so we can restore the original value * for the vcpu after the single-step is disabled. */ static void save_guest_debug_regs(struct kvm_vcpu *vcpu) { u64 val = vcpu_read_sys_reg(vcpu, MDSCR_EL1); vcpu->arch.guest_debug_preserved.mdscr_el1 = val; trace_kvm_arm_set_dreg32("Saved MDSCR_EL1", vcpu->arch.guest_debug_preserved.mdscr_el1); vcpu->arch.guest_debug_preserved.pstate_ss = (*vcpu_cpsr(vcpu) & DBG_SPSR_SS); } static void restore_guest_debug_regs(struct kvm_vcpu *vcpu) { u64 val = vcpu->arch.guest_debug_preserved.mdscr_el1; vcpu_write_sys_reg(vcpu, val, MDSCR_EL1); trace_kvm_arm_set_dreg32("Restored MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); if (vcpu->arch.guest_debug_preserved.pstate_ss) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /** * kvm_arm_init_debug - grab what we need for debug * * Currently the sole task of this function is to retrieve the initial * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has * presumably been set-up by some knowledgeable bootcode. * * It is called once per-cpu during CPU hyp initialisation. */ void kvm_arm_init_debug(void) { __this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2)); } /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug register access when one of the following is true: * - Userspace is using the hardware to debug the guest * (KVM_GUESTDBG_USE_HW is set). * - The guest is not using debug (DEBUG_DIRTY clear). * - The guest has enabled the OS Lock (debug exceptions are blocked). */ if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) || !vcpu_get_flag(vcpu, DEBUG_DIRTY) || kvm_vcpu_os_lock_enabled(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); } /** * kvm_arm_vcpu_init_debug - setup vcpu debug traps * * @vcpu: the vcpu pointer * * Set vcpu initial mdcr_el2 value. */ void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arm_setup_mdcr_el2(vcpu); preempt_enable(); } /** * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state * @vcpu: the vcpu pointer */ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) { vcpu->arch.debug_ptr = &vcpu->arch.vcpu_debug_state; } /** * kvm_arm_setup_debug - set up debug related stuff * * @vcpu: the vcpu pointer * * This is called before each entry into the hypervisor to setup any * debug related registers. * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the DEBUG_DIRTY * flag on vcpu->arch.iflags). Since the guest must not interfere * with the hardware state when debugging the guest, we must ensure that * trapping is enabled whenever we are debugging the guest using the * debug registers. */ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) { unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2; trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); kvm_arm_setup_mdcr_el2(vcpu); /* Check if we need to use the debug registers. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { /* Save guest debug state */ save_guest_debug_regs(vcpu); /* * Single Step (ARM ARM D2.12.3 The software step state * machine) * * If we are doing Single Step we need to manipulate * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the * step has occurred the hypervisor will trap the * debug exception and we return to userspace. * * If the guest attempts to single step its userspace * we would have to deal with a trapped exception * while in the guest kernel. Because this would be * hard to unwind we suppress the guest's ability to * do so by masking MDSCR_EL.SS. * * This confuses guest debuggers which use * single-step behind the scenes but everything * returns to normal once the host is no longer * debugging the system. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { /* * If the software step state at the last guest exit * was Active-pending, we don't set DBG_SPSR_SS so * that the state is maintained (to not run another * single-step until the pending Software Step * exception is taken). */ if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr |= DBG_MDSCR_SS; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr &= ~DBG_MDSCR_SS; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); } trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu)); /* * HW Breakpoints and watchpoints * * We simply switch the debug_ptr to point to our new * external_debug_state which has been populated by the * debug ioctl. The existing DEBUG_DIRTY mechanism ensures * the registers are updated on the world switch. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { /* Enable breakpoints/watchpoints */ mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr |= DBG_MDSCR_MDE; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; vcpu_set_flag(vcpu, DEBUG_DIRTY); trace_kvm_arm_set_regset("BKPTS", get_num_brps(), &vcpu->arch.debug_ptr->dbg_bcr[0], &vcpu->arch.debug_ptr->dbg_bvr[0]); trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), &vcpu->arch.debug_ptr->dbg_wcr[0], &vcpu->arch.debug_ptr->dbg_wvr[0]); /* * The OS Lock blocks debug exceptions in all ELs when it is * enabled. If the guest has enabled the OS Lock, constrain its * effects to the guest. Emulate the behavior by clearing * MDSCR_EL1.MDE. In so doing, we ensure that host debug * exceptions are unaffected by guest configuration of the OS * Lock. */ } else if (kvm_vcpu_os_lock_enabled(vcpu)) { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); mdscr &= ~DBG_MDSCR_MDE; vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); } } BUG_ON(!vcpu->guest_debug && vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state); /* If KDE or MDE are set, perform a full save/restore cycle. */ if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) vcpu_set_flag(vcpu, DEBUG_DIRTY); /* Write mdcr_el2 changes since vcpu_load on VHE systems */ if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); } void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) { trace_kvm_arm_clear_debug(vcpu->guest_debug); /* * Restore the guest's debug registers if we were using them. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) /* * Mark the vcpu as ACTIVE_PENDING * until Software Step exception is taken. */ vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING); } restore_guest_debug_regs(vcpu); /* * If we were using HW debug we need to restore the * debug_ptr to the guest debug state. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { kvm_arm_reset_debug_ptr(vcpu); trace_kvm_arm_set_regset("BKPTS", get_num_brps(), &vcpu->arch.debug_ptr->dbg_bcr[0], &vcpu->arch.debug_ptr->dbg_bvr[0]); trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), &vcpu->arch.debug_ptr->dbg_wcr[0], &vcpu->arch.debug_ptr->dbg_wvr[0]); } } } void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu) { u64 dfr0; /* For VHE, there is nothing to do */ if (has_vhe()) return; dfr0 = read_sysreg(id_aa64dfr0_el1); /* * If SPE is present on this CPU and is available at current EL, * we may need to check if the host state needs to be saved. */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT))) vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE); /* Check if we have TRBE implemented and available at the host */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_TRBE); } void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu) { vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE); vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE); } |
| 120 120 150 150 81 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2002 Richard Henderson * Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM. * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org> */ #define INCLUDE_VERMAGIC #include <linux/export.h> #include <linux/extable.h> #include <linux/moduleloader.h> #include <linux/module_signature.h> #include <linux/trace_events.h> #include <linux/init.h> #include <linux/kallsyms.h> #include <linux/buildid.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/elf.h> #include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/rcupdate.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/moduleparam.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/vermagic.h> #include <linux/notifier.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <linux/set_memory.h> #include <asm/mmu_context.h> #include <linux/license.h> #include <asm/sections.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/livepatch.h> #include <linux/async.h> #include <linux/percpu.h> #include <linux/kmemleak.h> #include <linux/jump_label.h> #include <linux/pfn.h> #include <linux/bsearch.h> #include <linux/dynamic_debug.h> #include <linux/audit.h> #include <linux/cfi.h> #include <linux/codetag.h> #include <linux/debugfs.h> #include <linux/execmem.h> #include <uapi/linux/module.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/module.h> /* * Mutex protects: * 1) List of modules (also safely readable with preempt_disable), * 2) module_use links, * 3) mod_tree.addr_min/mod_tree.addr_max. * (delete and add uses RCU list operations). */ DEFINE_MUTEX(module_mutex); LIST_HEAD(modules); /* Work queue for freeing init sections in success case */ static void do_free_init(struct work_struct *w); static DECLARE_WORK(init_free_wq, do_free_init); static LLIST_HEAD(init_free_list); struct mod_tree_root mod_tree __cacheline_aligned = { .addr_min = -1UL, }; struct symsearch { const struct kernel_symbol *start, *stop; const s32 *crcs; enum mod_license license; }; /* * Bounds of module memory, for speeding up __module_address. * Protected by module_mutex. */ static void __mod_update_bounds(enum mod_mem_type type __maybe_unused, void *base, unsigned int size, struct mod_tree_root *tree) { unsigned long min = (unsigned long)base; unsigned long max = min + size; #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC if (mod_mem_type_is_core_data(type)) { if (min < tree->data_addr_min) tree->data_addr_min = min; if (max > tree->data_addr_max) tree->data_addr_max = max; return; } #endif if (min < tree->addr_min) tree->addr_min = min; if (max > tree->addr_max) tree->addr_max = max; } static void mod_update_bounds(struct module *mod) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; if (mod_mem->size) __mod_update_bounds(type, mod_mem->base, mod_mem->size, &mod_tree); } } /* Block module loading/unloading? */ int modules_disabled; core_param(nomodule, modules_disabled, bint, 0); /* Waiting for a module to finish initializing? */ static DECLARE_WAIT_QUEUE_HEAD(module_wq); static BLOCKING_NOTIFIER_HEAD(module_notify_list); int register_module_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&module_notify_list, nb); } EXPORT_SYMBOL(register_module_notifier); int unregister_module_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&module_notify_list, nb); } EXPORT_SYMBOL(unregister_module_notifier); /* * We require a truly strong try_module_get(): 0 means success. * Otherwise an error is returned due to ongoing or failed * initialization etc. */ static inline int strong_try_module_get(struct module *mod) { BUG_ON(mod && mod->state == MODULE_STATE_UNFORMED); if (mod && mod->state == MODULE_STATE_COMING) return -EBUSY; if (try_module_get(mod)) return 0; else return -ENOENT; } static inline void add_taint_module(struct module *mod, unsigned flag, enum lockdep_ok lockdep_ok) { add_taint(flag, lockdep_ok); set_bit(flag, &mod->taints); } /* * A thread that wants to hold a reference to a module only while it * is running can call this to safely exit. */ void __noreturn __module_put_and_kthread_exit(struct module *mod, long code) { module_put(mod); kthread_exit(code); } EXPORT_SYMBOL(__module_put_and_kthread_exit); /* Find a module section: 0 means not found. */ static unsigned int find_sec(const struct load_info *info, const char *name) { unsigned int i; for (i = 1; i < info->hdr->e_shnum; i++) { Elf_Shdr *shdr = &info->sechdrs[i]; /* Alloc bit cleared means "ignore it." */ if ((shdr->sh_flags & SHF_ALLOC) && strcmp(info->secstrings + shdr->sh_name, name) == 0) return i; } return 0; } /* Find a module section, or NULL. */ static void *section_addr(const struct load_info *info, const char *name) { /* Section 0 has sh_addr 0. */ return (void *)info->sechdrs[find_sec(info, name)].sh_addr; } /* Find a module section, or NULL. Fill in number of "objects" in section. */ static void *section_objs(const struct load_info *info, const char *name, size_t object_size, unsigned int *num) { unsigned int sec = find_sec(info, name); /* Section 0 has sh_addr 0 and sh_size 0. */ *num = info->sechdrs[sec].sh_size / object_size; return (void *)info->sechdrs[sec].sh_addr; } /* Find a module section: 0 means not found. Ignores SHF_ALLOC flag. */ static unsigned int find_any_sec(const struct load_info *info, const char *name) { unsigned int i; for (i = 1; i < info->hdr->e_shnum; i++) { Elf_Shdr *shdr = &info->sechdrs[i]; if (strcmp(info->secstrings + shdr->sh_name, name) == 0) return i; } return 0; } /* * Find a module section, or NULL. Fill in number of "objects" in section. * Ignores SHF_ALLOC flag. */ static __maybe_unused void *any_section_objs(const struct load_info *info, const char *name, size_t object_size, unsigned int *num) { unsigned int sec = find_any_sec(info, name); /* Section 0 has sh_addr 0 and sh_size 0. */ *num = info->sechdrs[sec].sh_size / object_size; return (void *)info->sechdrs[sec].sh_addr; } #ifndef CONFIG_MODVERSIONS #define symversion(base, idx) NULL #else #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif static const char *kernel_symbol_name(const struct kernel_symbol *sym) { #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS return offset_to_ptr(&sym->name_offset); #else return sym->name; #endif } static const char *kernel_symbol_namespace(const struct kernel_symbol *sym) { #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS if (!sym->namespace_offset) return NULL; return offset_to_ptr(&sym->namespace_offset); #else return sym->namespace; #endif } int cmp_name(const void *name, const void *sym) { return strcmp(name, kernel_symbol_name(sym)); } static bool find_exported_symbol_in_section(const struct symsearch *syms, struct module *owner, struct find_symbol_arg *fsa) { struct kernel_symbol *sym; if (!fsa->gplok && syms->license == GPL_ONLY) return false; sym = bsearch(fsa->name, syms->start, syms->stop - syms->start, sizeof(struct kernel_symbol), cmp_name); if (!sym) return false; fsa->owner = owner; fsa->crc = symversion(syms->crcs, sym - syms->start); fsa->sym = sym; fsa->license = syms->license; return true; } /* * Find an exported symbol and return it, along with, (optional) crc and * (optional) module which owns it. Needs preempt disabled or module_mutex. */ bool find_symbol(struct find_symbol_arg *fsa) { static const struct symsearch arr[] = { { __start___ksymtab, __stop___ksymtab, __start___kcrctab, NOT_GPL_ONLY }, { __start___ksymtab_gpl, __stop___ksymtab_gpl, __start___kcrctab_gpl, GPL_ONLY }, }; struct module *mod; unsigned int i; module_assert_mutex_or_preempt(); for (i = 0; i < ARRAY_SIZE(arr); i++) if (find_exported_symbol_in_section(&arr[i], NULL, fsa)) return true; list_for_each_entry_rcu(mod, &modules, list, lockdep_is_held(&module_mutex)) { struct symsearch arr[] = { { mod->syms, mod->syms + mod->num_syms, mod->crcs, NOT_GPL_ONLY }, { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms, mod->gpl_crcs, GPL_ONLY }, }; if (mod->state == MODULE_STATE_UNFORMED) continue; for (i = 0; i < ARRAY_SIZE(arr); i++) if (find_exported_symbol_in_section(&arr[i], mod, fsa)) return true; } pr_debug("Failed to find symbol %s\n", fsa->name); return false; } /* * Search for module by name: must hold module_mutex (or preempt disabled * for read-only access). */ struct module *find_module_all(const char *name, size_t len, bool even_unformed) { struct module *mod; module_assert_mutex_or_preempt(); list_for_each_entry_rcu(mod, &modules, list, lockdep_is_held(&module_mutex)) { if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) continue; if (strlen(mod->name) == len && !memcmp(mod->name, name, len)) return mod; } return NULL; } struct module *find_module(const char *name) { return find_module_all(name, strlen(name), false); } #ifdef CONFIG_SMP static inline void __percpu *mod_percpu(struct module *mod) { return mod->percpu; } static int percpu_modalloc(struct module *mod, struct load_info *info) { Elf_Shdr *pcpusec = &info->sechdrs[info->index.pcpu]; unsigned long align = pcpusec->sh_addralign; if (!pcpusec->sh_size) return 0; if (align > PAGE_SIZE) { pr_warn("%s: per-cpu alignment %li > %li\n", mod->name, align, PAGE_SIZE); align = PAGE_SIZE; } mod->percpu = __alloc_reserved_percpu(pcpusec->sh_size, align); if (!mod->percpu) { pr_warn("%s: Could not allocate %lu bytes percpu data\n", mod->name, (unsigned long)pcpusec->sh_size); return -ENOMEM; } mod->percpu_size = pcpusec->sh_size; return 0; } static void percpu_modfree(struct module *mod) { free_percpu(mod->percpu); } static unsigned int find_pcpusec(struct load_info *info) { return find_sec(info, ".data..percpu"); } static void percpu_modcopy(struct module *mod, const void *from, unsigned long size) { int cpu; for_each_possible_cpu(cpu) memcpy(per_cpu_ptr(mod->percpu, cpu), from, size); } bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) { struct module *mod; unsigned int cpu; preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; if (!mod->percpu_size) continue; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(mod->percpu, cpu); void *va = (void *)addr; if (va >= start && va < start + mod->percpu_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(mod->percpu, get_boot_cpu_id()); } preempt_enable(); return true; } } } preempt_enable(); return false; } /** * is_module_percpu_address() - test whether address is from module static percpu * @addr: address to test * * Test whether @addr belongs to module static percpu area. * * Return: %true if @addr is from module static percpu area */ bool is_module_percpu_address(unsigned long addr) { return __is_module_percpu_address(addr, NULL); } #else /* ... !CONFIG_SMP */ static inline void __percpu *mod_percpu(struct module *mod) { return NULL; } static int percpu_modalloc(struct module *mod, struct load_info *info) { /* UP modules shouldn't have this section: ENOMEM isn't quite right */ if (info->sechdrs[info->index.pcpu].sh_size != 0) return -ENOMEM; return 0; } static inline void percpu_modfree(struct module *mod) { } static unsigned int find_pcpusec(struct load_info *info) { return 0; } static inline void percpu_modcopy(struct module *mod, const void *from, unsigned long size) { /* pcpusec should be 0, and size of that section should be 0. */ BUG_ON(size != 0); } bool is_module_percpu_address(unsigned long addr) { return false; } bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) { return false; } #endif /* CONFIG_SMP */ #define MODINFO_ATTR(field) \ static void setup_modinfo_##field(struct module *mod, const char *s) \ { \ mod->field = kstrdup(s, GFP_KERNEL); \ } \ static ssize_t show_modinfo_##field(struct module_attribute *mattr, \ struct module_kobject *mk, char *buffer) \ { \ return scnprintf(buffer, PAGE_SIZE, "%s\n", mk->mod->field); \ } \ static int modinfo_##field##_exists(struct module *mod) \ { \ return mod->field != NULL; \ } \ static void free_modinfo_##field(struct module *mod) \ { \ kfree(mod->field); \ mod->field = NULL; \ } \ static struct module_attribute modinfo_##field = { \ .attr = { .name = __stringify(field), .mode = 0444 }, \ .show = show_modinfo_##field, \ .setup = setup_modinfo_##field, \ .test = modinfo_##field##_exists, \ .free = free_modinfo_##field, \ }; MODINFO_ATTR(version); MODINFO_ATTR(srcversion); static struct { char name[MODULE_NAME_LEN + 1]; char taints[MODULE_FLAGS_BUF_SIZE]; } last_unloaded_module; #ifdef CONFIG_MODULE_UNLOAD EXPORT_TRACEPOINT_SYMBOL(module_get); /* MODULE_REF_BASE is the base reference count by kmodule loader. */ #define MODULE_REF_BASE 1 /* Init the unload section of the module. */ static int module_unload_init(struct module *mod) { /* * Initialize reference counter to MODULE_REF_BASE. * refcnt == 0 means module is going. */ atomic_set(&mod->refcnt, MODULE_REF_BASE); INIT_LIST_HEAD(&mod->source_list); INIT_LIST_HEAD(&mod->target_list); /* Hold reference count during initialization. */ atomic_inc(&mod->refcnt); return 0; } /* Does a already use b? */ static int already_uses(struct module *a, struct module *b) { struct module_use *use; list_for_each_entry(use, &b->source_list, source_list) { if (use->source == a) return 1; } pr_debug("%s does not use %s!\n", a->name, b->name); return 0; } /* * Module a uses b * - we add 'a' as a "source", 'b' as a "target" of module use * - the module_use is added to the list of 'b' sources (so * 'b' can walk the list to see who sourced them), and of 'a' * targets (so 'a' can see what modules it targets). */ static int add_module_usage(struct module *a, struct module *b) { struct module_use *use; pr_debug("Allocating new usage for %s.\n", a->name); use = kmalloc(sizeof(*use), GFP_ATOMIC); if (!use) return -ENOMEM; use->source = a; use->target = b; list_add(&use->source_list, &b->source_list); list_add(&use->target_list, &a->target_list); return 0; } /* Module a uses b: caller needs module_mutex() */ static int ref_module(struct module *a, struct module *b) { int err; if (b == NULL || already_uses(a, b)) return 0; /* If module isn't available, we fail. */ err = strong_try_module_get(b); if (err) return err; err = add_module_usage(a, b); if (err) { module_put(b); return err; } return 0; } /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) { struct module_use *use, *tmp; mutex_lock(&module_mutex); list_for_each_entry_safe(use, tmp, &mod->target_list, target_list) { struct module *i = use->target; pr_debug("%s unusing %s\n", mod->name, i->name); module_put(i); list_del(&use->source_list); list_del(&use->target_list); kfree(use); } mutex_unlock(&module_mutex); } #ifdef CONFIG_MODULE_FORCE_UNLOAD static inline int try_force_unload(unsigned int flags) { int ret = (flags & O_TRUNC); if (ret) add_taint(TAINT_FORCED_RMMOD, LOCKDEP_NOW_UNRELIABLE); return ret; } #else static inline int try_force_unload(unsigned int flags) { return 0; } #endif /* CONFIG_MODULE_FORCE_UNLOAD */ /* Try to release refcount of module, 0 means success. */ static int try_release_module_ref(struct module *mod) { int ret; /* Try to decrement refcnt which we set at loading */ ret = atomic_sub_return(MODULE_REF_BASE, &mod->refcnt); BUG_ON(ret < 0); if (ret) /* Someone can put this right now, recover with checking */ ret = atomic_add_unless(&mod->refcnt, MODULE_REF_BASE, 0); return ret; } static int try_stop_module(struct module *mod, int flags, int *forced) { /* If it's not unused, quit unless we're forcing. */ if (try_release_module_ref(mod) != 0) { *forced = try_force_unload(flags); if (!(*forced)) return -EWOULDBLOCK; } /* Mark it as dying. */ mod->state = MODULE_STATE_GOING; return 0; } /** * module_refcount() - return the refcount or -1 if unloading * @mod: the module we're checking * * Return: * -1 if the module is in the process of unloading * otherwise the number of references in the kernel to the module */ int module_refcount(struct module *mod) { return atomic_read(&mod->refcnt) - MODULE_REF_BASE; } EXPORT_SYMBOL(module_refcount); /* This exists whether we can unload or not */ static void free_module(struct module *mod); SYSCALL_DEFINE2(delete_module, const char __user *, name_user, unsigned int, flags) { struct module *mod; char name[MODULE_NAME_LEN]; char buf[MODULE_FLAGS_BUF_SIZE]; int ret, forced = 0; if (!capable(CAP_SYS_MODULE) || modules_disabled) return -EPERM; if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0) return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; audit_log_kern_module(name); if (mutex_lock_interruptible(&module_mutex) != 0) return -EINTR; mod = find_module(name); if (!mod) { ret = -ENOENT; goto out; } if (!list_empty(&mod->source_list)) { /* Other modules depend on us: get rid of them first. */ ret = -EWOULDBLOCK; goto out; } /* Doing init or already dying? */ if (mod->state != MODULE_STATE_LIVE) { /* FIXME: if (force), slam module count damn the torpedoes */ pr_debug("%s already dying\n", mod->name); ret = -EBUSY; goto out; } /* If it has an init func, it must have an exit func to unload */ if (mod->init && !mod->exit) { forced = try_force_unload(flags); if (!forced) { /* This module can't be removed */ ret = -EBUSY; goto out; } } ret = try_stop_module(mod, flags, &forced); if (ret != 0) goto out; mutex_unlock(&module_mutex); /* Final destruction now no one is using it. */ if (mod->exit != NULL) mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); klp_module_going(mod); ftrace_release_mod(mod); async_synchronize_full(); /* Store the name and taints of the last unloaded module for diagnostic purposes */ strscpy(last_unloaded_module.name, mod->name, sizeof(last_unloaded_module.name)); strscpy(last_unloaded_module.taints, module_flags(mod, buf, false), sizeof(last_unloaded_module.taints)); free_module(mod); /* someone could wait for the module in add_unformed_module() */ wake_up_all(&module_wq); return 0; out: mutex_unlock(&module_mutex); return ret; } void __symbol_put(const char *symbol) { struct find_symbol_arg fsa = { .name = symbol, .gplok = true, }; preempt_disable(); BUG_ON(!find_symbol(&fsa)); module_put(fsa.owner); preempt_enable(); } EXPORT_SYMBOL(__symbol_put); /* Note this assumes addr is a function, which it currently always is. */ void symbol_put_addr(void *addr) { struct module *modaddr; unsigned long a = (unsigned long)dereference_function_descriptor(addr); if (core_kernel_text(a)) return; /* * Even though we hold a reference on the module; we still need to * disable preemption in order to safely traverse the data structure. */ preempt_disable(); modaddr = __module_text_address(a); BUG_ON(!modaddr); module_put(modaddr); preempt_enable(); } EXPORT_SYMBOL_GPL(symbol_put_addr); static ssize_t show_refcnt(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { return sprintf(buffer, "%i\n", module_refcount(mk->mod)); } static struct module_attribute modinfo_refcnt = __ATTR(refcnt, 0444, show_refcnt, NULL); void __module_get(struct module *module) { if (module) { atomic_inc(&module->refcnt); trace_module_get(module, _RET_IP_); } } EXPORT_SYMBOL(__module_get); bool try_module_get(struct module *module) { bool ret = true; if (module) { /* Note: here, we can fail to get a reference */ if (likely(module_is_live(module) && atomic_inc_not_zero(&module->refcnt) != 0)) trace_module_get(module, _RET_IP_); else ret = false; } return ret; } EXPORT_SYMBOL(try_module_get); void module_put(struct module *module) { int ret; if (module) { ret = atomic_dec_if_positive(&module->refcnt); WARN_ON(ret < 0); /* Failed to put refcount */ trace_module_put(module, _RET_IP_); } } EXPORT_SYMBOL(module_put); #else /* !CONFIG_MODULE_UNLOAD */ static inline void module_unload_free(struct module *mod) { } static int ref_module(struct module *a, struct module *b) { return strong_try_module_get(b); } static inline int module_unload_init(struct module *mod) { return 0; } #endif /* CONFIG_MODULE_UNLOAD */ size_t module_flags_taint(unsigned long taints, char *buf) { size_t l = 0; int i; for (i = 0; i < TAINT_FLAGS_COUNT; i++) { if (taint_flags[i].module && test_bit(i, &taints)) buf[l++] = taint_flags[i].c_true; } return l; } static ssize_t show_initstate(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { const char *state = "unknown"; switch (mk->mod->state) { case MODULE_STATE_LIVE: state = "live"; break; case MODULE_STATE_COMING: state = "coming"; break; case MODULE_STATE_GOING: state = "going"; break; default: BUG(); } return sprintf(buffer, "%s\n", state); } static struct module_attribute modinfo_initstate = __ATTR(initstate, 0444, show_initstate, NULL); static ssize_t store_uevent(struct module_attribute *mattr, struct module_kobject *mk, const char *buffer, size_t count) { int rc; rc = kobject_synth_uevent(&mk->kobj, buffer, count); return rc ? rc : count; } struct module_attribute module_uevent = __ATTR(uevent, 0200, NULL, store_uevent); static ssize_t show_coresize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { unsigned int size = mk->mod->mem[MOD_TEXT].size; if (!IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC)) { for_class_mod_mem_type(type, core_data) size += mk->mod->mem[type].size; } return sprintf(buffer, "%u\n", size); } static struct module_attribute modinfo_coresize = __ATTR(coresize, 0444, show_coresize, NULL); #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC static ssize_t show_datasize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { unsigned int size = 0; for_class_mod_mem_type(type, core_data) size += mk->mod->mem[type].size; return sprintf(buffer, "%u\n", size); } static struct module_attribute modinfo_datasize = __ATTR(datasize, 0444, show_datasize, NULL); #endif static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { unsigned int size = 0; for_class_mod_mem_type(type, init) size += mk->mod->mem[type].size; return sprintf(buffer, "%u\n", size); } static struct module_attribute modinfo_initsize = __ATTR(initsize, 0444, show_initsize, NULL); static ssize_t show_taint(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { size_t l; l = module_flags_taint(mk->mod->taints, buffer); buffer[l++] = '\n'; return l; } static struct module_attribute modinfo_taint = __ATTR(taint, 0444, show_taint, NULL); struct module_attribute *modinfo_attrs[] = { &module_uevent, &modinfo_version, &modinfo_srcversion, &modinfo_initstate, &modinfo_coresize, #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC &modinfo_datasize, #endif &modinfo_initsize, &modinfo_taint, #ifdef CONFIG_MODULE_UNLOAD &modinfo_refcnt, #endif NULL, }; size_t modinfo_attrs_count = ARRAY_SIZE(modinfo_attrs); static const char vermagic[] = VERMAGIC_STRING; int try_to_force_load(struct module *mod, const char *reason) { #ifdef CONFIG_MODULE_FORCE_LOAD if (!test_taint(TAINT_FORCED_MODULE)) pr_warn("%s: %s: kernel tainted.\n", mod->name, reason); add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_NOW_UNRELIABLE); return 0; #else return -ENOEXEC; #endif } /* Parse tag=value strings from .modinfo section */ char *module_next_tag_pair(char *string, unsigned long *secsize) { /* Skip non-zero chars */ while (string[0]) { string++; if ((*secsize)-- <= 1) return NULL; } /* Skip any zero padding. */ while (!string[0]) { string++; if ((*secsize)-- <= 1) return NULL; } return string; } static char *get_next_modinfo(const struct load_info *info, const char *tag, char *prev) { char *p; unsigned int taglen = strlen(tag); Elf_Shdr *infosec = &info->sechdrs[info->index.info]; unsigned long size = infosec->sh_size; /* * get_modinfo() calls made before rewrite_section_headers() * must use sh_offset, as sh_addr isn't set! */ char *modinfo = (char *)info->hdr + infosec->sh_offset; if (prev) { size -= prev - modinfo; modinfo = module_next_tag_pair(prev, &size); } for (p = modinfo; p; p = module_next_tag_pair(p, &size)) { if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') return p + taglen + 1; } return NULL; } static char *get_modinfo(const struct load_info *info, const char *tag) { return get_next_modinfo(info, tag, NULL); } static int verify_namespace_is_imported(const struct load_info *info, const struct kernel_symbol *sym, struct module *mod) { const char *namespace; char *imported_namespace; namespace = kernel_symbol_namespace(sym); if (namespace && namespace[0]) { for_each_modinfo_entry(imported_namespace, info, "import_ns") { if (strcmp(namespace, imported_namespace) == 0) return 0; } #ifdef CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS pr_warn( #else pr_err( #endif "%s: module uses symbol (%s) from namespace %s, but does not import it.\n", mod->name, kernel_symbol_name(sym), namespace); #ifndef CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS return -EINVAL; #endif } return 0; } static bool inherit_taint(struct module *mod, struct module *owner, const char *name) { if (!owner || !test_bit(TAINT_PROPRIETARY_MODULE, &owner->taints)) return true; if (mod->using_gplonly_symbols) { pr_err("%s: module using GPL-only symbols uses symbols %s from proprietary module %s.\n", mod->name, name, owner->name); return false; } if (!test_bit(TAINT_PROPRIETARY_MODULE, &mod->taints)) { pr_warn("%s: module uses symbols %s from proprietary module %s, inheriting taint.\n", mod->name, name, owner->name); set_bit(TAINT_PROPRIETARY_MODULE, &mod->taints); } return true; } /* Resolve a symbol for this module. I.e. if we find one, record usage. */ static const struct kernel_symbol *resolve_symbol(struct module *mod, const struct load_info *info, const char *name, char ownername[]) { struct find_symbol_arg fsa = { .name = name, .gplok = !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), .warn = true, }; int err; /* * The module_mutex should not be a heavily contended lock; * if we get the occasional sleep here, we'll go an extra iteration * in the wait_event_interruptible(), which is harmless. */ sched_annotate_sleep(); mutex_lock(&module_mutex); if (!find_symbol(&fsa)) goto unlock; if (fsa.license == GPL_ONLY) mod->using_gplonly_symbols = true; if (!inherit_taint(mod, fsa.owner, name)) { fsa.sym = NULL; goto getname; } if (!check_version(info, name, mod, fsa.crc)) { fsa.sym = ERR_PTR(-EINVAL); goto getname; } err = verify_namespace_is_imported(info, fsa.sym, mod); if (err) { fsa.sym = ERR_PTR(err); goto getname; } err = ref_module(mod, fsa.owner); if (err) { fsa.sym = ERR_PTR(err); goto getname; } getname: /* We must make copy under the lock if we failed to get ref. */ strncpy(ownername, module_name(fsa.owner), MODULE_NAME_LEN); unlock: mutex_unlock(&module_mutex); return fsa.sym; } static const struct kernel_symbol * resolve_symbol_wait(struct module *mod, const struct load_info *info, const char *name) { const struct kernel_symbol *ksym; char owner[MODULE_NAME_LEN]; if (wait_event_interruptible_timeout(module_wq, !IS_ERR(ksym = resolve_symbol(mod, info, name, owner)) || PTR_ERR(ksym) != -EBUSY, 30 * HZ) <= 0) { pr_warn("%s: gave up waiting for init of module %s.\n", mod->name, owner); } return ksym; } void __weak module_arch_cleanup(struct module *mod) { } void __weak module_arch_freeing_init(struct module *mod) { } static int module_memory_alloc(struct module *mod, enum mod_mem_type type) { unsigned int size = PAGE_ALIGN(mod->mem[type].size); enum execmem_type execmem_type; void *ptr; mod->mem[type].size = size; if (mod_mem_type_is_data(type)) execmem_type = EXECMEM_MODULE_DATA; else execmem_type = EXECMEM_MODULE_TEXT; ptr = execmem_alloc(execmem_type, size); if (!ptr) return -ENOMEM; /* * The pointer to these blocks of memory are stored on the module * structure and we keep that around so long as the module is * around. We only free that memory when we unload the module. * Just mark them as not being a leak then. The .init* ELF * sections *do* get freed after boot so we *could* treat them * slightly differently with kmemleak_ignore() and only grey * them out as they work as typical memory allocations which * *do* eventually get freed, but let's just keep things simple * and avoid *any* false positives. */ kmemleak_not_leak(ptr); memset(ptr, 0, size); mod->mem[type].base = ptr; return 0; } static void module_memory_free(struct module *mod, enum mod_mem_type type, bool unload_codetags) { void *ptr = mod->mem[type].base; if (!unload_codetags && mod_mem_type_is_core_data(type)) return; execmem_free(ptr); } static void free_mod_mem(struct module *mod, bool unload_codetags) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; if (type == MOD_DATA) continue; /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod_mem->base, mod_mem->size); if (mod_mem->size) module_memory_free(mod, type, unload_codetags); } /* MOD_DATA hosts mod, so free it at last */ lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); module_memory_free(mod, MOD_DATA, unload_codetags); } /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { bool unload_codetags; trace_module_free(mod); unload_codetags = codetag_unload_module(mod); if (!unload_codetags) pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n", mod->name); mod_sysfs_teardown(mod); /* * We leave it in list to prevent duplicate loads, but make sure * that noone uses it while it's being deconstructed. */ mutex_lock(&module_mutex); mod->state = MODULE_STATE_UNFORMED; mutex_unlock(&module_mutex); /* Arch-specific cleanup. */ module_arch_cleanup(mod); /* Module unload stuff */ module_unload_free(mod); /* Free any allocated parameters. */ destroy_params(mod->kp, mod->num_kp); if (is_livepatch_module(mod)) free_module_elf(mod); /* Now we can delete it from the lists */ mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); mod_tree_remove(mod); /* Remove this module from bug list, this uses list_del_rcu */ module_bug_cleanup(mod); /* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */ synchronize_rcu(); if (try_add_tainted_module(mod)) pr_err("%s: adding tainted module to the unloaded tainted modules list failed.\n", mod->name); mutex_unlock(&module_mutex); /* This may be empty, but that's OK */ module_arch_freeing_init(mod); kfree(mod->args); percpu_modfree(mod); free_mod_mem(mod, unload_codetags); } void *__symbol_get(const char *symbol) { struct find_symbol_arg fsa = { .name = symbol, .gplok = true, .warn = true, }; preempt_disable(); if (!find_symbol(&fsa)) goto fail; if (fsa.license != GPL_ONLY) { pr_warn("failing symbol_get of non-GPLONLY symbol %s.\n", symbol); goto fail; } if (strong_try_module_get(fsa.owner)) goto fail; preempt_enable(); return (void *)kernel_symbol_value(fsa.sym); fail: preempt_enable(); return NULL; } EXPORT_SYMBOL_GPL(__symbol_get); /* * Ensure that an exported symbol [global namespace] does not already exist * in the kernel or in some other module's exported symbol table. * * You must hold the module_mutex. */ static int verify_exported_symbols(struct module *mod) { unsigned int i; const struct kernel_symbol *s; struct { const struct kernel_symbol *sym; unsigned int num; } arr[] = { { mod->syms, mod->num_syms }, { mod->gpl_syms, mod->num_gpl_syms }, }; for (i = 0; i < ARRAY_SIZE(arr); i++) { for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { struct find_symbol_arg fsa = { .name = kernel_symbol_name(s), .gplok = true, }; if (find_symbol(&fsa)) { pr_err("%s: exports duplicate symbol %s" " (owned by %s)\n", mod->name, kernel_symbol_name(s), module_name(fsa.owner)); return -ENOEXEC; } } } return 0; } static bool ignore_undef_symbol(Elf_Half emachine, const char *name) { /* * On x86, PIC code and Clang non-PIC code may have call foo@PLT. GNU as * before 2.37 produces an unreferenced _GLOBAL_OFFSET_TABLE_ on x86-64. * i386 has a similar problem but may not deserve a fix. * * If we ever have to ignore many symbols, consider refactoring the code to * only warn if referenced by a relocation. */ if (emachine == EM_386 || emachine == EM_X86_64) return !strcmp(name, "_GLOBAL_OFFSET_TABLE_"); return false; } /* Change all symbols so that st_value encodes the pointer directly. */ static int simplify_symbols(struct module *mod, const struct load_info *info) { Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; Elf_Sym *sym = (void *)symsec->sh_addr; unsigned long secbase; unsigned int i; int ret = 0; const struct kernel_symbol *ksym; for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { const char *name = info->strtab + sym[i].st_name; switch (sym[i].st_shndx) { case SHN_COMMON: /* Ignore common symbols */ if (!strncmp(name, "__gnu_lto", 9)) break; /* * We compiled with -fno-common. These are not * supposed to happen. */ pr_debug("Common symbol: %s\n", name); pr_warn("%s: please compile with -fno-common\n", mod->name); ret = -ENOEXEC; break; case SHN_ABS: /* Don't need to do anything */ pr_debug("Absolute symbol: 0x%08lx %s\n", (long)sym[i].st_value, name); break; case SHN_LIVEPATCH: /* Livepatch symbols are resolved by livepatch */ break; case SHN_UNDEF: ksym = resolve_symbol_wait(mod, info, name); /* Ok if resolved. */ if (ksym && !IS_ERR(ksym)) { sym[i].st_value = kernel_symbol_value(ksym); break; } /* Ok if weak or ignored. */ if (!ksym && (ELF_ST_BIND(sym[i].st_info) == STB_WEAK || ignore_undef_symbol(info->hdr->e_machine, name))) break; ret = PTR_ERR(ksym) ?: -ENOENT; pr_warn("%s: Unknown symbol %s (err %d)\n", mod->name, name, ret); break; default: /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } } return ret; } static int apply_relocations(struct module *mod, const struct load_info *info) { unsigned int i; int err = 0; /* Now do relocations. */ for (i = 1; i < info->hdr->e_shnum; i++) { unsigned int infosec = info->sechdrs[i].sh_info; /* Not a valid relocation section? */ if (infosec >= info->hdr->e_shnum) continue; /* Don't bother with non-allocated sections */ if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC)) continue; if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH) err = klp_apply_section_relocs(mod, info->sechdrs, info->secstrings, info->strtab, info->index.sym, i, NULL); else if (info->sechdrs[i].sh_type == SHT_REL) err = apply_relocate(info->sechdrs, info->strtab, info->index.sym, i, mod); else if (info->sechdrs[i].sh_type == SHT_RELA) err = apply_relocate_add(info->sechdrs, info->strtab, info->index.sym, i, mod); if (err < 0) break; } return err; } /* Additional bytes needed by arch in front of individual sections */ unsigned int __weak arch_mod_section_prepend(struct module *mod, unsigned int section) { /* default implementation just returns zero */ return 0; } long module_get_offset_and_type(struct module *mod, enum mod_mem_type type, Elf_Shdr *sechdr, unsigned int section) { long offset; long mask = ((unsigned long)(type) & SH_ENTSIZE_TYPE_MASK) << SH_ENTSIZE_TYPE_SHIFT; mod->mem[type].size += arch_mod_section_prepend(mod, section); offset = ALIGN(mod->mem[type].size, sechdr->sh_addralign ?: 1); mod->mem[type].size = offset + sechdr->sh_size; WARN_ON_ONCE(offset & mask); return offset | mask; } bool module_init_layout_section(const char *sname) { #ifndef CONFIG_MODULE_UNLOAD if (module_exit_section(sname)) return true; #endif return module_init_section(sname); } static void __layout_sections(struct module *mod, struct load_info *info, bool is_init) { unsigned int m, i; static const unsigned long masks[][2] = { /* * NOTE: all executable code must be the first section * in this array; otherwise modify the text_size * finder in the two loops below */ { SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL }, { SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL }, { SHF_RO_AFTER_INIT | SHF_ALLOC, ARCH_SHF_SMALL }, { SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL }, { ARCH_SHF_SMALL | SHF_ALLOC, 0 } }; static const int core_m_to_mem_type[] = { MOD_TEXT, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_DATA, MOD_DATA, }; static const int init_m_to_mem_type[] = { MOD_INIT_TEXT, MOD_INIT_RODATA, MOD_INVALID, MOD_INIT_DATA, MOD_INIT_DATA, }; for (m = 0; m < ARRAY_SIZE(masks); ++m) { enum mod_mem_type type = is_init ? init_m_to_mem_type[m] : core_m_to_mem_type[m]; for (i = 0; i < info->hdr->e_shnum; ++i) { Elf_Shdr *s = &info->sechdrs[i]; const char *sname = info->secstrings + s->sh_name; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL || is_init != module_init_layout_section(sname)) continue; if (WARN_ON_ONCE(type == MOD_INVALID)) continue; s->sh_entsize = module_get_offset_and_type(mod, type, s, i); pr_debug("\t%s\n", sname); } } } /* * Lay out the SHF_ALLOC sections in a way not dissimilar to how ld * might -- code, read-only data, read-write data, small data. Tally * sizes, and place the offsets into sh_entsize fields: high bit means it * belongs in init. */ static void layout_sections(struct module *mod, struct load_info *info) { unsigned int i; for (i = 0; i < info->hdr->e_shnum; i++) info->sechdrs[i].sh_entsize = ~0UL; pr_debug("Core section allocation order for %s:\n", mod->name); __layout_sections(mod, info, false); pr_debug("Init section allocation order for %s:\n", mod->name); __layout_sections(mod, info, true); } static void module_license_taint_check(struct module *mod, const char *license) { if (!license) license = "unspecified"; if (!license_is_gpl_compatible(license)) { if (!test_taint(TAINT_PROPRIETARY_MODULE)) pr_warn("%s: module license '%s' taints kernel.\n", mod->name, license); add_taint_module(mod, TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); } } static void setup_modinfo(struct module *mod, struct load_info *info) { struct module_attribute *attr; int i; for (i = 0; (attr = modinfo_attrs[i]); i++) { if (attr->setup) attr->setup(mod, get_modinfo(info, attr->attr.name)); } } static void free_modinfo(struct module *mod) { struct module_attribute *attr; int i; for (i = 0; (attr = modinfo_attrs[i]); i++) { if (attr->free) attr->free(mod); } } bool __weak module_init_section(const char *name) { return strstarts(name, ".init"); } bool __weak module_exit_section(const char *name) { return strstarts(name, ".exit"); } static int validate_section_offset(struct load_info *info, Elf_Shdr *shdr) { #if defined(CONFIG_64BIT) unsigned long long secend; #else unsigned long secend; #endif /* * Check for both overflow and offset/size being * too large. */ secend = shdr->sh_offset + shdr->sh_size; if (secend < shdr->sh_offset || secend > info->len) return -ENOEXEC; return 0; } /* * Check userspace passed ELF module against our expectations, and cache * useful variables for further processing as we go. * * This does basic validity checks against section offsets and sizes, the * section name string table, and the indices used for it (sh_name). * * As a last step, since we're already checking the ELF sections we cache * useful variables which will be used later for our convenience: * * o pointers to section headers * o cache the modinfo symbol section * o cache the string symbol section * o cache the module section * * As a last step we set info->mod to the temporary copy of the module in * info->hdr. The final one will be allocated in move_module(). Any * modifications we make to our copy of the module will be carried over * to the final minted module. */ static int elf_validity_cache_copy(struct load_info *info, int flags) { unsigned int i; Elf_Shdr *shdr, *strhdr; int err; unsigned int num_mod_secs = 0, mod_idx; unsigned int num_info_secs = 0, info_idx; unsigned int num_sym_secs = 0, sym_idx; if (info->len < sizeof(*(info->hdr))) { pr_err("Invalid ELF header len %lu\n", info->len); goto no_exec; } if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0) { pr_err("Invalid ELF header magic: != %s\n", ELFMAG); goto no_exec; } if (info->hdr->e_type != ET_REL) { pr_err("Invalid ELF header type: %u != %u\n", info->hdr->e_type, ET_REL); goto no_exec; } if (!elf_check_arch(info->hdr)) { pr_err("Invalid architecture in ELF header: %u\n", info->hdr->e_machine); goto no_exec; } if (!module_elf_check_arch(info->hdr)) { pr_err("Invalid module architecture in ELF header: %u\n", info->hdr->e_machine); goto no_exec; } if (info->hdr->e_shentsize != sizeof(Elf_Shdr)) { pr_err("Invalid ELF section header size\n"); goto no_exec; } /* * e_shnum is 16 bits, and sizeof(Elf_Shdr) is * known and small. So e_shnum * sizeof(Elf_Shdr) * will not overflow unsigned long on any platform. */ if (info->hdr->e_shoff >= info->len || (info->hdr->e_shnum * sizeof(Elf_Shdr) > info->len - info->hdr->e_shoff)) { pr_err("Invalid ELF section header overflow\n"); goto no_exec; } info->sechdrs = (void *)info->hdr + info->hdr->e_shoff; /* * Verify if the section name table index is valid. */ if (info->hdr->e_shstrndx == SHN_UNDEF || info->hdr->e_shstrndx >= info->hdr->e_shnum) { pr_err("Invalid ELF section name index: %d || e_shstrndx (%d) >= e_shnum (%d)\n", info->hdr->e_shstrndx, info->hdr->e_shstrndx, info->hdr->e_shnum); goto no_exec; } strhdr = &info->sechdrs[info->hdr->e_shstrndx]; err = validate_section_offset(info, strhdr); if (err < 0) { pr_err("Invalid ELF section hdr(type %u)\n", strhdr->sh_type); return err; } /* * The section name table must be NUL-terminated, as required * by the spec. This makes strcmp and pr_* calls that access * strings in the section safe. */ info->secstrings = (void *)info->hdr + strhdr->sh_offset; if (strhdr->sh_size == 0) { pr_err("empty section name table\n"); goto no_exec; } if (info->secstrings[strhdr->sh_size - 1] != '\0') { pr_err("ELF Spec violation: section name table isn't null terminated\n"); goto no_exec; } /* * The code assumes that section 0 has a length of zero and * an addr of zero, so check for it. */ if (info->sechdrs[0].sh_type != SHT_NULL || info->sechdrs[0].sh_size != 0 || info->sechdrs[0].sh_addr != 0) { pr_err("ELF Spec violation: section 0 type(%d)!=SH_NULL or non-zero len or addr\n", info->sechdrs[0].sh_type); goto no_exec; } for (i = 1; i < info->hdr->e_shnum; i++) { shdr = &info->sechdrs[i]; switch (shdr->sh_type) { case SHT_NULL: case SHT_NOBITS: continue; case SHT_SYMTAB: if (shdr->sh_link == SHN_UNDEF || shdr->sh_link >= info->hdr->e_shnum) { pr_err("Invalid ELF sh_link!=SHN_UNDEF(%d) or (sh_link(%d) >= hdr->e_shnum(%d)\n", shdr->sh_link, shdr->sh_link, info->hdr->e_shnum); goto no_exec; } num_sym_secs++; sym_idx = i; fallthrough; default: err = validate_section_offset(info, shdr); if (err < 0) { pr_err("Invalid ELF section in module (section %u type %u)\n", i, shdr->sh_type); return err; } if (strcmp(info->secstrings + shdr->sh_name, ".gnu.linkonce.this_module") == 0) { num_mod_secs++; mod_idx = i; } else if (strcmp(info->secstrings + shdr->sh_name, ".modinfo") == 0) { num_info_secs++; info_idx = i; } if (shdr->sh_flags & SHF_ALLOC) { if (shdr->sh_name >= strhdr->sh_size) { pr_err("Invalid ELF section name in module (section %u type %u)\n", i, shdr->sh_type); return -ENOEXEC; } } break; } } if (num_info_secs > 1) { pr_err("Only one .modinfo section must exist.\n"); goto no_exec; } else if (num_info_secs == 1) { /* Try to find a name early so we can log errors with a module name */ info->index.info = info_idx; info->name = get_modinfo(info, "name"); } if (num_sym_secs != 1) { pr_warn("%s: module has no symbols (stripped?)\n", info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } /* Sets internal symbols and strings. */ info->index.sym = sym_idx; shdr = &info->sechdrs[sym_idx]; info->index.str = shdr->sh_link; info->strtab = (char *)info->hdr + info->sechdrs[info->index.str].sh_offset; /* * The ".gnu.linkonce.this_module" ELF section is special. It is * what modpost uses to refer to __this_module and let's use rely * on THIS_MODULE to point to &__this_module properly. The kernel's * modpost declares it on each modules's *.mod.c file. If the struct * module of the kernel changes a full kernel rebuild is required. * * We have a few expectaions for this special section, the following * code validates all this for us: * * o Only one section must exist * o We expect the kernel to always have to allocate it: SHF_ALLOC * o The section size must match the kernel's run time's struct module * size */ if (num_mod_secs != 1) { pr_err("module %s: Only one .gnu.linkonce.this_module section must exist.\n", info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } shdr = &info->sechdrs[mod_idx]; /* * This is already implied on the switch above, however let's be * pedantic about it. */ if (shdr->sh_type == SHT_NOBITS) { pr_err("module %s: .gnu.linkonce.this_module section must have a size set\n", info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } if (!(shdr->sh_flags & SHF_ALLOC)) { pr_err("module %s: .gnu.linkonce.this_module must occupy memory during process execution\n", info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } if (shdr->sh_size != sizeof(struct module)) { pr_err("module %s: .gnu.linkonce.this_module section size must match the kernel's built struct module size at run time\n", info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } info->index.mod = mod_idx; /* This is temporary: point mod into copy of data. */ info->mod = (void *)info->hdr + shdr->sh_offset; /* * If we didn't load the .modinfo 'name' field earlier, fall back to * on-disk struct mod 'name' field. */ if (!info->name) info->name = info->mod->name; if (flags & MODULE_INIT_IGNORE_MODVERSIONS) info->index.vers = 0; /* Pretend no __versions section! */ else info->index.vers = find_sec(info, "__versions"); info->index.pcpu = find_pcpusec(info); return 0; no_exec: return -ENOEXEC; } #define COPY_CHUNK_SIZE (16*PAGE_SIZE) static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned long len) { do { unsigned long n = min(len, COPY_CHUNK_SIZE); if (copy_from_user(dst, usrc, n) != 0) return -EFAULT; cond_resched(); dst += n; usrc += n; len -= n; } while (len); return 0; } static int check_modinfo_livepatch(struct module *mod, struct load_info *info) { if (!get_modinfo(info, "livepatch")) /* Nothing more to do */ return 0; if (set_livepatch_module(mod)) return 0; pr_err("%s: module is marked as livepatch module, but livepatch support is disabled", mod->name); return -ENOEXEC; } static void check_modinfo_retpoline(struct module *mod, struct load_info *info) { if (retpoline_module_ok(get_modinfo(info, "retpoline"))) return; pr_warn("%s: loading module not compiled with retpoline compiler.\n", mod->name); } /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) { int err; info->len = len; if (info->len < sizeof(*(info->hdr))) return -ENOEXEC; err = security_kernel_load_data(LOADING_MODULE, true); if (err) return err; /* Suck in entire file: we'll want most of it. */ info->hdr = __vmalloc(info->len, GFP_KERNEL | __GFP_NOWARN); if (!info->hdr) return -ENOMEM; if (copy_chunked_from_user(info->hdr, umod, info->len) != 0) { err = -EFAULT; goto out; } err = security_kernel_post_load_data((char *)info->hdr, info->len, LOADING_MODULE, "init_module"); out: if (err) vfree(info->hdr); return err; } static void free_copy(struct load_info *info, int flags) { if (flags & MODULE_INIT_COMPRESSED_FILE) module_decompress_cleanup(info); else vfree(info->hdr); } static int rewrite_section_headers(struct load_info *info, int flags) { unsigned int i; /* This should always be true, but let's be sure. */ info->sechdrs[0].sh_addr = 0; for (i = 1; i < info->hdr->e_shnum; i++) { Elf_Shdr *shdr = &info->sechdrs[i]; /* * Mark all sections sh_addr with their address in the * temporary image. */ shdr->sh_addr = (size_t)info->hdr + shdr->sh_offset; } /* Track but don't keep modinfo and version sections. */ info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; return 0; } /* * These calls taint the kernel depending certain module circumstances */ static void module_augment_kernel_taints(struct module *mod, struct load_info *info) { int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE); if (!get_modinfo(info, "intree")) { if (!test_taint(TAINT_OOT_MODULE)) pr_warn("%s: loading out-of-tree module taints kernel.\n", mod->name); add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); } check_modinfo_retpoline(mod, info); if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); pr_warn("%s: module is from the staging directory, the quality " "is unknown, you have been warned.\n", mod->name); } if (is_livepatch_module(mod)) { add_taint_module(mod, TAINT_LIVEPATCH, LOCKDEP_STILL_OK); pr_notice_once("%s: tainting kernel with TAINT_LIVEPATCH\n", mod->name); } module_license_taint_check(mod, get_modinfo(info, "license")); if (get_modinfo(info, "test")) { if (!test_taint(TAINT_TEST)) pr_warn("%s: loading test module taints kernel.\n", mod->name); add_taint_module(mod, TAINT_TEST, LOCKDEP_STILL_OK); } #ifdef CONFIG_MODULE_SIG mod->sig_ok = info->sig_ok; if (!mod->sig_ok) { pr_notice_once("%s: module verification failed: signature " "and/or required key missing - tainting " "kernel\n", mod->name); add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); } #endif /* * ndiswrapper is under GPL by itself, but loads proprietary modules. * Don't use add_taint_module(), as it would prevent ndiswrapper from * using GPL-only symbols it needs. */ if (strcmp(mod->name, "ndiswrapper") == 0) add_taint(TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); /* driverloader was caught wrongly pretending to be under GPL */ if (strcmp(mod->name, "driverloader") == 0) add_taint_module(mod, TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); /* lve claims to be GPL but upstream won't provide source */ if (strcmp(mod->name, "lve") == 0) add_taint_module(mod, TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE)) pr_warn("%s: module license taints kernel.\n", mod->name); } static int check_modinfo(struct module *mod, struct load_info *info, int flags) { const char *modmagic = get_modinfo(info, "vermagic"); int err; if (flags & MODULE_INIT_IGNORE_VERMAGIC) modmagic = NULL; /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { err = try_to_force_load(mod, "bad vermagic"); if (err) return err; } else if (!same_magic(modmagic, vermagic, info->index.vers)) { pr_err("%s: version magic '%s' should be '%s'\n", info->name, modmagic, vermagic); return -ENOEXEC; } err = check_modinfo_livepatch(mod, info); if (err) return err; return 0; } static int find_module_sections(struct module *mod, struct load_info *info) { mod->kp = section_objs(info, "__param", sizeof(*mod->kp), &mod->num_kp); mod->syms = section_objs(info, "__ksymtab", sizeof(*mod->syms), &mod->num_syms); mod->crcs = section_addr(info, "__kcrctab"); mod->gpl_syms = section_objs(info, "__ksymtab_gpl", sizeof(*mod->gpl_syms), &mod->num_gpl_syms); mod->gpl_crcs = section_addr(info, "__kcrctab_gpl"); #ifdef CONFIG_CONSTRUCTORS mod->ctors = section_objs(info, ".ctors", sizeof(*mod->ctors), &mod->num_ctors); if (!mod->ctors) mod->ctors = section_objs(info, ".init_array", sizeof(*mod->ctors), &mod->num_ctors); else if (find_sec(info, ".init_array")) { /* * This shouldn't happen with same compiler and binutils * building all parts of the module. */ pr_warn("%s: has both .ctors and .init_array.\n", mod->name); return -EINVAL; } #endif mod->noinstr_text_start = section_objs(info, ".noinstr.text", 1, &mod->noinstr_text_size); #ifdef CONFIG_TRACEPOINTS mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", sizeof(*mod->tracepoints_ptrs), &mod->num_tracepoints); #endif #ifdef CONFIG_TREE_SRCU mod->srcu_struct_ptrs = section_objs(info, "___srcu_struct_ptrs", sizeof(*mod->srcu_struct_ptrs), &mod->num_srcu_structs); #endif #ifdef CONFIG_BPF_EVENTS mod->bpf_raw_events = section_objs(info, "__bpf_raw_tp_map", sizeof(*mod->bpf_raw_events), &mod->num_bpf_raw_events); #endif #ifdef CONFIG_DEBUG_INFO_BTF_MODULES mod->btf_data = any_section_objs(info, ".BTF", 1, &mod->btf_data_size); #endif #ifdef CONFIG_JUMP_LABEL mod->jump_entries = section_objs(info, "__jump_table", sizeof(*mod->jump_entries), &mod->num_jump_entries); #endif #ifdef CONFIG_EVENT_TRACING mod->trace_events = section_objs(info, "_ftrace_events", sizeof(*mod->trace_events), &mod->num_trace_events); mod->trace_evals = section_objs(info, "_ftrace_eval_map", sizeof(*mod->trace_evals), &mod->num_trace_evals); #endif #ifdef CONFIG_TRACING mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt", sizeof(*mod->trace_bprintk_fmt_start), &mod->num_trace_bprintk_fmt); #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* sechdrs[0].sh_size is always zero */ mod->ftrace_callsites = section_objs(info, FTRACE_CALLSITE_SECTION, sizeof(*mod->ftrace_callsites), &mod->num_ftrace_callsites); #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION mod->ei_funcs = section_objs(info, "_error_injection_whitelist", sizeof(*mod->ei_funcs), &mod->num_ei_funcs); #endif #ifdef CONFIG_KPROBES mod->kprobes_text_start = section_objs(info, ".kprobes.text", 1, &mod->kprobes_text_size); mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist", sizeof(unsigned long), &mod->num_kprobe_blacklist); #endif #ifdef CONFIG_PRINTK_INDEX mod->printk_index_start = section_objs(info, ".printk_index", sizeof(*mod->printk_index_start), &mod->printk_index_size); #endif #ifdef CONFIG_HAVE_STATIC_CALL_INLINE mod->static_call_sites = section_objs(info, ".static_call_sites", sizeof(*mod->static_call_sites), &mod->num_static_call_sites); #endif #if IS_ENABLED(CONFIG_KUNIT) mod->kunit_suites = section_objs(info, ".kunit_test_suites", sizeof(*mod->kunit_suites), &mod->num_kunit_suites); mod->kunit_init_suites = section_objs(info, ".kunit_init_test_suites", sizeof(*mod->kunit_init_suites), &mod->num_kunit_init_suites); #endif mod->extable = section_objs(info, "__ex_table", sizeof(*mod->extable), &mod->num_exentries); if (section_addr(info, "__obsparm")) pr_warn("%s: Ignoring obsolete parameters\n", mod->name); #ifdef CONFIG_DYNAMIC_DEBUG_CORE mod->dyndbg_info.descs = section_objs(info, "__dyndbg", sizeof(*mod->dyndbg_info.descs), &mod->dyndbg_info.num_descs); mod->dyndbg_info.classes = section_objs(info, "__dyndbg_classes", sizeof(*mod->dyndbg_info.classes), &mod->dyndbg_info.num_classes); #endif return 0; } static int move_module(struct module *mod, struct load_info *info) { int i; enum mod_mem_type t = 0; int ret = -ENOMEM; for_each_mod_mem_type(type) { if (!mod->mem[type].size) { mod->mem[type].base = NULL; continue; } ret = module_memory_alloc(mod, type); if (ret) { t = type; goto out_enomem; } } /* Transfer each section which specifies SHF_ALLOC */ pr_debug("Final section addresses for %s:\n", mod->name); for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; if (!(shdr->sh_flags & SHF_ALLOC)) continue; dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK); if (shdr->sh_type != SHT_NOBITS) { /* * Our ELF checker already validated this, but let's * be pedantic and make the goal clearer. We actually * end up copying over all modifications made to the * userspace copy of the entire struct module. */ if (i == info->index.mod && (WARN_ON_ONCE(shdr->sh_size != sizeof(struct module)))) { ret = -ENOEXEC; goto out_enomem; } memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); } /* * Update the userspace copy's ELF section address to point to * our newly allocated memory as a pure convenience so that * users of info can keep taking advantage and using the newly * minted official memory area. */ shdr->sh_addr = (unsigned long)dest; pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr, (long)shdr->sh_size, info->secstrings + shdr->sh_name); } return 0; out_enomem: for (t--; t >= 0; t--) module_memory_free(mod, t, true); return ret; } static int check_export_symbol_versions(struct module *mod) { #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs)) { return try_to_force_load(mod, "no versions for exported symbols"); } #endif return 0; } static void flush_module_icache(const struct module *mod) { /* * Flush the instruction cache, since we've played with text. * Do it before processing of module parameters, so the module * can provide parameter accessor functions of its own. */ for_each_mod_mem_type(type) { const struct module_memory *mod_mem = &mod->mem[type]; if (mod_mem->size) { flush_icache_range((unsigned long)mod_mem->base, (unsigned long)mod_mem->base + mod_mem->size); } } } bool __weak module_elf_check_arch(Elf_Ehdr *hdr) { return true; } int __weak module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { return 0; } /* module_blacklist is a comma-separated list of module names */ static char *module_blacklist; static bool blacklisted(const char *module_name) { const char *p; size_t len; if (!module_blacklist) return false; for (p = module_blacklist; *p; p += len) { len = strcspn(p, ","); if (strlen(module_name) == len && !memcmp(module_name, p, len)) return true; if (p[len] == ',') len++; } return false; } core_param(module_blacklist, module_blacklist, charp, 0400); static struct module *layout_and_allocate(struct load_info *info, int flags) { struct module *mod; unsigned int ndx; int err; /* Allow arches to frob section contents and sizes. */ err = module_frob_arch_sections(info->hdr, info->sechdrs, info->secstrings, info->mod); if (err < 0) return ERR_PTR(err); err = module_enforce_rwx_sections(info->hdr, info->sechdrs, info->secstrings, info->mod); if (err < 0) return ERR_PTR(err); /* We will do a special allocation for per-cpu sections later. */ info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC; /* * Mark ro_after_init section with SHF_RO_AFTER_INIT so that * layout_sections() can put it in the right place. * Note: ro_after_init sections also have SHF_{WRITE,ALLOC} set. */ ndx = find_sec(info, ".data..ro_after_init"); if (ndx) info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT; /* * Mark the __jump_table section as ro_after_init as well: these data * structures are never modified, with the exception of entries that * refer to code in the __init section, which are annotated as such * at module load time. */ ndx = find_sec(info, "__jump_table"); if (ndx) info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT; /* * Determine total sizes, and put offsets in sh_entsize. For now * this is done generically; there doesn't appear to be any * special cases for the architectures. */ layout_sections(info->mod, info); layout_symtab(info->mod, info); /* Allocate and move to the final place */ err = move_module(info->mod, info); if (err) return ERR_PTR(err); /* Module has been copied to its final place now: return it. */ mod = (void *)info->sechdrs[info->index.mod].sh_addr; kmemleak_load_module(mod, info); return mod; } /* mod is no longer valid after this! */ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); free_mod_mem(mod, true); } int __weak module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { return 0; } static int post_relocation(struct module *mod, const struct load_info *info) { /* Sort exception table now relocations are done. */ sort_extable(mod->extable, mod->extable + mod->num_exentries); /* Copy relocated percpu area over. */ percpu_modcopy(mod, (void *)info->sechdrs[info->index.pcpu].sh_addr, info->sechdrs[info->index.pcpu].sh_size); /* Setup kallsyms-specific fields. */ add_kallsyms(mod, info); /* Arch-specific module finalizing. */ return module_finalize(info->hdr, info->sechdrs, mod); } /* Call module constructors. */ static void do_mod_ctors(struct module *mod) { #ifdef CONFIG_CONSTRUCTORS unsigned long i; for (i = 0; i < mod->num_ctors; i++) mod->ctors[i](); #endif } /* For freeing module_init on success, in case kallsyms traversing */ struct mod_initfree { struct llist_node node; void *init_text; void *init_data; void *init_rodata; }; static void do_free_init(struct work_struct *w) { struct llist_node *pos, *n, *list; struct mod_initfree *initfree; list = llist_del_all(&init_free_list); synchronize_rcu(); llist_for_each_safe(pos, n, list) { initfree = container_of(pos, struct mod_initfree, node); execmem_free(initfree->init_text); execmem_free(initfree->init_data); execmem_free(initfree->init_rodata); kfree(initfree); } } void flush_module_init_free_work(void) { flush_work(&init_free_wq); } #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "module." /* Default value for module->async_probe_requested */ static bool async_probe; module_param(async_probe, bool, 0644); /* * This is where the real work happens. * * Keep it uninlined to provide a reliable breakpoint target, e.g. for the gdb * helper command 'lx-symbols'. */ static noinline int do_init_module(struct module *mod) { int ret = 0; struct mod_initfree *freeinit; #if defined(CONFIG_MODULE_STATS) unsigned int text_size = 0, total_size = 0; for_each_mod_mem_type(type) { const struct module_memory *mod_mem = &mod->mem[type]; if (mod_mem->size) { total_size += mod_mem->size; if (type == MOD_TEXT || type == MOD_INIT_TEXT) text_size += mod_mem->size; } } #endif freeinit = kmalloc(sizeof(*freeinit), GFP_KERNEL); if (!freeinit) { ret = -ENOMEM; goto fail; } freeinit->init_text = mod->mem[MOD_INIT_TEXT].base; freeinit->init_data = mod->mem[MOD_INIT_DATA].base; freeinit->init_rodata = mod->mem[MOD_INIT_RODATA].base; do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) ret = do_one_initcall(mod->init); if (ret < 0) { goto fail_free_freeinit; } if (ret > 0) { pr_warn("%s: '%s'->init suspiciously returned %d, it should " "follow 0/-E convention\n" "%s: loading module anyway...\n", __func__, mod->name, ret, __func__); dump_stack(); } /* Now it's a first class citizen! */ mod->state = MODULE_STATE_LIVE; blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_LIVE, mod); /* Delay uevent until module has finished its init routine */ kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); /* * We need to finish all async code before the module init sequence * is done. This has potential to deadlock if synchronous module * loading is requested from async (which is not allowed!). * * See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous * request_module() from async workers") for more details. */ if (!mod->async_probe_requested) async_synchronize_full(); ftrace_free_mem(mod, mod->mem[MOD_INIT_TEXT].base, mod->mem[MOD_INIT_TEXT].base + mod->mem[MOD_INIT_TEXT].size); mutex_lock(&module_mutex); /* Drop initial reference. */ module_put(mod); trim_init_extable(mod); #ifdef CONFIG_KALLSYMS /* Switch to core kallsyms now init is done: kallsyms may be walking! */ rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif ret = module_enable_rodata_ro(mod, true); if (ret) goto fail_mutex_unlock; mod_tree_remove_init(mod); module_arch_freeing_init(mod); for_class_mod_mem_type(type, init) { mod->mem[type].base = NULL; mod->mem[type].size = 0; } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */ mod->btf_data = NULL; #endif /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we * call synchronize_rcu(), but we don't want to slow down the success * path. execmem_free() cannot be called in an interrupt, so do the * work and call synchronize_rcu() in a work queue. * * Note that execmem_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to * be cleaned up needs to sync with the queued work by invoking * flush_module_init_free_work(). */ if (llist_add(&freeinit->node, &init_free_list)) schedule_work(&init_free_wq); mutex_unlock(&module_mutex); wake_up_all(&module_wq); mod_stat_add_long(text_size, &total_text_size); mod_stat_add_long(total_size, &total_mod_size); mod_stat_inc(&modcount); return 0; fail_mutex_unlock: mutex_unlock(&module_mutex); fail_free_freeinit: kfree(freeinit); fail: /* Try to protect us from buggy refcounters. */ mod->state = MODULE_STATE_GOING; synchronize_rcu(); module_put(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); klp_module_going(mod); ftrace_release_mod(mod); free_module(mod); wake_up_all(&module_wq); return ret; } static int may_init_module(void) { if (!capable(CAP_SYS_MODULE) || modules_disabled) return -EPERM; return 0; } /* Is this module of this name done loading? No locks held. */ static bool finished_loading(const char *name) { struct module *mod; bool ret; /* * The module_mutex should not be a heavily contended lock; * if we get the occasional sleep here, we'll go an extra iteration * in the wait_event_interruptible(), which is harmless. */ sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); ret = !mod || mod->state == MODULE_STATE_LIVE || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; } /* Must be called with module_mutex held */ static int module_patient_check_exists(const char *name, enum fail_dup_mod_reason reason) { struct module *old; int err = 0; old = find_module_all(name, strlen(name), true); if (old == NULL) return 0; if (old->state == MODULE_STATE_COMING || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(name)); mutex_lock(&module_mutex); if (err) return err; /* The module might have gone in the meantime. */ old = find_module_all(name, strlen(name), true); } if (try_add_failed_module(name, reason)) pr_warn("Could not add fail-tracking for module: %s\n", name); /* * We are here only when the same module was being loaded. Do * not try to load it again right now. It prevents long delays * caused by serialized module load failures. It might happen * when more devices of the same type trigger load of * a particular module. */ if (old && old->state == MODULE_STATE_LIVE) return -EEXIST; return -EBUSY; } /* * We try to place it in the list now to make sure it's unique before * we dedicate too many resources. In particular, temporary percpu * memory exhaustion. */ static int add_unformed_module(struct module *mod) { int err; mod->state = MODULE_STATE_UNFORMED; mutex_lock(&module_mutex); err = module_patient_check_exists(mod->name, FAIL_DUP_MOD_LOAD); if (err) goto out; mod_update_bounds(mod); list_add_rcu(&mod->list, &modules); mod_tree_insert(mod); err = 0; out: mutex_unlock(&module_mutex); return err; } static int complete_formation(struct module *mod, struct load_info *info) { int err; mutex_lock(&module_mutex); /* Find duplicate symbols (must be called under lock). */ err = verify_exported_symbols(mod); if (err < 0) goto out; /* These rely on module_mutex for list integrity. */ module_bug_finalize(info->hdr, info->sechdrs, mod); module_cfi_finalize(info->hdr, info->sechdrs, mod); err = module_enable_rodata_ro(mod, false); if (err) goto out_strict_rwx; err = module_enable_data_nx(mod); if (err) goto out_strict_rwx; err = module_enable_text_rox(mod); if (err) goto out_strict_rwx; /* * Mark state as coming so strong_try_module_get() ignores us, * but kallsyms etc. can see us. */ mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); return 0; out_strict_rwx: module_bug_cleanup(mod); out: mutex_unlock(&module_mutex); return err; } static int prepare_coming_module(struct module *mod) { int err; ftrace_module_enable(mod); err = klp_module_coming(mod); if (err) return err; err = blocking_notifier_call_chain_robust(&module_notify_list, MODULE_STATE_COMING, MODULE_STATE_GOING, mod); err = notifier_to_errno(err); if (err) klp_module_going(mod); return err; } static int unknown_module_param_cb(char *param, char *val, const char *modname, void *arg) { struct module *mod = arg; int ret; if (strcmp(param, "async_probe") == 0) { if (kstrtobool(val, &mod->async_probe_requested)) mod->async_probe_requested = true; return 0; } /* Check for magic 'dyndbg' arg */ ret = ddebug_dyndbg_module_param_cb(param, val, modname); if (ret != 0) pr_warn("%s: unknown parameter '%s' ignored\n", modname, param); return 0; } /* Module within temporary copy, this doesn't do any allocation */ static int early_mod_check(struct load_info *info, int flags) { int err; /* * Now that we know we have the correct module name, check * if it's blacklisted. */ if (blacklisted(info->name)) { pr_err("Module %s is blacklisted\n", info->name); return -EPERM; } err = rewrite_section_headers(info, flags); if (err) return err; /* Check module struct version now, before we try to use module. */ if (!check_modstruct_version(info, info->mod)) return -ENOEXEC; err = check_modinfo(info->mod, info, flags); if (err) return err; mutex_lock(&module_mutex); err = module_patient_check_exists(info->mod->name, FAIL_DUP_MOD_BECOMING); mutex_unlock(&module_mutex); return err; } /* * Allocate and load the module: note that size of section 0 is always * zero, and we rely on this for optional sections. */ static int load_module(struct load_info *info, const char __user *uargs, int flags) { struct module *mod; bool module_allocated = false; long err = 0; char *after_dashes; /* * Do the signature check (if any) first. All that * the signature check needs is info->len, it does * not need any of the section info. That can be * set up later. This will minimize the chances * of a corrupt module causing problems before * we even get to the signature check. * * The check will also adjust info->len by stripping * off the sig length at the end of the module, making * checks against info->len more correct. */ err = module_sig_check(info, flags); if (err) goto free_copy; /* * Do basic sanity checks against the ELF header and * sections. Cache useful sections and set the * info->mod to the userspace passed struct module. */ err = elf_validity_cache_copy(info, flags); if (err) goto free_copy; err = early_mod_check(info, flags); if (err) goto free_copy; /* Figure out module layout, and allocate all the memory. */ mod = layout_and_allocate(info, flags); if (IS_ERR(mod)) { err = PTR_ERR(mod); goto free_copy; } module_allocated = true; audit_log_kern_module(mod->name); /* Reserve our place in the list. */ err = add_unformed_module(mod); if (err) goto free_module; /* * We are tainting your kernel if your module gets into * the modules linked list somehow. */ module_augment_kernel_taints(mod, info); /* To avoid stressing percpu allocator, do this once we're unique. */ err = percpu_modalloc(mod, info); if (err) goto unlink_mod; /* Now module is in final location, initialize linked lists, etc. */ err = module_unload_init(mod); if (err) goto unlink_mod; init_param_lock(mod); /* * Now we've got everything in the final locations, we can * find optional sections. */ err = find_module_sections(mod, info); if (err) goto free_unload; err = check_export_symbol_versions(mod); if (err) goto free_unload; /* Set up MODINFO_ATTR fields */ setup_modinfo(mod, info); /* Fix up syms, so that st_value is a pointer to location. */ err = simplify_symbols(mod, info); if (err < 0) goto free_modinfo; err = apply_relocations(mod, info); if (err < 0) goto free_modinfo; err = post_relocation(mod, info); if (err < 0) goto free_modinfo; flush_module_icache(mod); /* Now copy in args */ mod->args = strndup_user(uargs, ~0UL >> 1); if (IS_ERR(mod->args)) { err = PTR_ERR(mod->args); goto free_arch_cleanup; } init_build_id(mod, info); /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */ ftrace_module_init(mod); /* Finally it's fully formed, ready to start executing. */ err = complete_formation(mod, info); if (err) goto ddebug_cleanup; err = prepare_coming_module(mod); if (err) goto bug_cleanup; mod->async_probe_requested = async_probe; /* Module is ready to execute: parsing args may do that. */ after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, -32768, 32767, mod, unknown_module_param_cb); if (IS_ERR(after_dashes)) { err = PTR_ERR(after_dashes); goto coming_cleanup; } else if (after_dashes) { pr_warn("%s: parameters '%s' after `--' ignored\n", mod->name, after_dashes); } /* Link in to sysfs. */ err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp); if (err < 0) goto coming_cleanup; if (is_livepatch_module(mod)) { err = copy_module_elf(mod, info); if (err < 0) goto sysfs_cleanup; } /* Get rid of temporary copy. */ free_copy(info, flags); codetag_load_module(mod); /* Done! */ trace_module_load(mod); return do_init_module(mod); sysfs_cleanup: mod_sysfs_teardown(mod); coming_cleanup: mod->state = MODULE_STATE_GOING; destroy_params(mod->kp, mod->num_kp); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); klp_module_going(mod); bug_cleanup: mod->state = MODULE_STATE_GOING; /* module_bug_cleanup needs module_mutex protection */ mutex_lock(&module_mutex); module_bug_cleanup(mod); mutex_unlock(&module_mutex); ddebug_cleanup: ftrace_release_mod(mod); synchronize_rcu(); kfree(mod->args); free_arch_cleanup: module_arch_cleanup(mod); free_modinfo: free_modinfo(mod); free_unload: module_unload_free(mod); unlink_mod: mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); mod_tree_remove(mod); wake_up_all(&module_wq); /* Wait for RCU-sched synchronizing before releasing mod->list. */ synchronize_rcu(); mutex_unlock(&module_mutex); free_module: mod_stat_bump_invalid(info, flags); /* Free lock-classes; relies on the preceding sync_rcu() */ for_class_mod_mem_type(type, core_data) { lockdep_free_key_range(mod->mem[type].base, mod->mem[type].size); } module_deallocate(mod, info); free_copy: /* * The info->len is always set. We distinguish between * failures once the proper module was allocated and * before that. */ if (!module_allocated) mod_stat_bump_becoming(info, flags); free_copy(info, flags); return err; } SYSCALL_DEFINE3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs) { int err; struct load_info info = { }; err = may_init_module(); if (err) return err; pr_debug("init_module: umod=%p, len=%lu, uargs=%p\n", umod, len, uargs); err = copy_module_from_user(umod, len, &info); if (err) { mod_stat_inc(&failed_kreads); mod_stat_add_long(len, &invalid_kread_bytes); return err; } return load_module(&info, uargs, 0); } struct idempotent { const void *cookie; struct hlist_node entry; struct completion complete; int ret; }; #define IDEM_HASH_BITS 8 static struct hlist_head idem_hash[1 << IDEM_HASH_BITS]; static DEFINE_SPINLOCK(idem_lock); static bool idempotent(struct idempotent *u, const void *cookie) { int hash = hash_ptr(cookie, IDEM_HASH_BITS); struct hlist_head *head = idem_hash + hash; struct idempotent *existing; bool first; u->ret = 0; u->cookie = cookie; init_completion(&u->complete); spin_lock(&idem_lock); first = true; hlist_for_each_entry(existing, head, entry) { if (existing->cookie != cookie) continue; first = false; break; } hlist_add_head(&u->entry, idem_hash + hash); spin_unlock(&idem_lock); return !first; } /* * We were the first one with 'cookie' on the list, and we ended * up completing the operation. We now need to walk the list, * remove everybody - which includes ourselves - fill in the return * value, and then complete the operation. */ static int idempotent_complete(struct idempotent *u, int ret) { const void *cookie = u->cookie; int hash = hash_ptr(cookie, IDEM_HASH_BITS); struct hlist_head *head = idem_hash + hash; struct hlist_node *next; struct idempotent *pos; spin_lock(&idem_lock); hlist_for_each_entry_safe(pos, next, head, entry) { if (pos->cookie != cookie) continue; hlist_del(&pos->entry); pos->ret = ret; complete(&pos->complete); } spin_unlock(&idem_lock); return ret; } static int init_module_from_file(struct file *f, const char __user * uargs, int flags) { struct load_info info = { }; void *buf = NULL; int len; len = kernel_read_file(f, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); return len; } if (flags & MODULE_INIT_COMPRESSED_FILE) { int err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); mod_stat_add_long(len, &invalid_decompress_bytes); return err; } } else { info.hdr = buf; info.len = len; } return load_module(&info, uargs, flags); } static int idempotent_init_module(struct file *f, const char __user * uargs, int flags) { struct idempotent idem; if (!f || !(f->f_mode & FMODE_READ)) return -EBADF; /* See if somebody else is doing the operation? */ if (idempotent(&idem, file_inode(f))) { wait_for_completion(&idem.complete); return idem.ret; } /* Otherwise, we'll do it and complete others */ return idempotent_complete(&idem, init_module_from_file(f, uargs, flags)); } SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { int err; struct fd f; err = may_init_module(); if (err) return err; pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS |MODULE_INIT_IGNORE_VERMAGIC |MODULE_INIT_COMPRESSED_FILE)) return -EINVAL; f = fdget(fd); err = idempotent_init_module(f.file, uargs, flags); fdput(f); return err; } /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { int bx = 0; BUG_ON(mod->state == MODULE_STATE_UNFORMED); if (!mod->taints && !show_state) goto out; if (mod->taints || mod->state == MODULE_STATE_GOING || mod->state == MODULE_STATE_COMING) { buf[bx++] = '('; bx += module_flags_taint(mod->taints, buf + bx); /* Show a - for module-is-being-unloaded */ if (mod->state == MODULE_STATE_GOING && show_state) buf[bx++] = '-'; /* Show a + for module-is-being-loaded */ if (mod->state == MODULE_STATE_COMING && show_state) buf[bx++] = '+'; buf[bx++] = ')'; } out: buf[bx] = '\0'; return buf; } /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct module *mod; preempt_disable(); mod = __module_address(addr); if (!mod) goto out; if (!mod->num_exentries) goto out; e = search_extable(mod->extable, mod->num_exentries, addr); out: preempt_enable(); /* * Now, if we found one, we are running inside it now, hence * we cannot unload the module, hence no refcnt needed. */ return e; } /** * is_module_address() - is this address inside a module? * @addr: the address to check. * * See is_module_text_address() if you simply want to see if the address * is code (not data). */ bool is_module_address(unsigned long addr) { bool ret; preempt_disable(); ret = __module_address(addr) != NULL; preempt_enable(); return ret; } /** * __module_address() - get the module which contains an address. * @addr: the address. * * Must be called with preempt disabled or module mutex held so that * module doesn't get freed during this. */ struct module *__module_address(unsigned long addr) { struct module *mod; if (addr >= mod_tree.addr_min && addr <= mod_tree.addr_max) goto lookup; #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC if (addr >= mod_tree.data_addr_min && addr <= mod_tree.data_addr_max) goto lookup; #endif return NULL; lookup: module_assert_mutex_or_preempt(); mod = mod_find(addr, &mod_tree); if (mod) { BUG_ON(!within_module(addr, mod)); if (mod->state == MODULE_STATE_UNFORMED) mod = NULL; } return mod; } /** * is_module_text_address() - is this address inside module code? * @addr: the address to check. * * See is_module_address() if you simply want to see if the address is * anywhere in a module. See kernel_text_address() for testing if an * address corresponds to kernel or module code. */ bool is_module_text_address(unsigned long addr) { bool ret; preempt_disable(); ret = __module_text_address(addr) != NULL; preempt_enable(); return ret; } /** * __module_text_address() - get the module whose code contains an address. * @addr: the address. * * Must be called with preempt disabled or module mutex held so that * module doesn't get freed during this. */ struct module *__module_text_address(unsigned long addr) { struct module *mod = __module_address(addr); if (mod) { /* Make sure it's within the text section. */ if (!within_module_mem_type(addr, mod, MOD_TEXT) && !within_module_mem_type(addr, mod, MOD_INIT_TEXT)) mod = NULL; } return mod; } /* Don't grab lock, we're oopsing. */ void print_modules(void) { struct module *mod; char buf[MODULE_FLAGS_BUF_SIZE]; printk(KERN_DEFAULT "Modules linked in:"); /* Most callers should already have preempt disabled, but make sure */ preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; pr_cont(" %s%s", mod->name, module_flags(mod, buf, true)); } print_unloaded_tainted_modules(); preempt_enable(); if (last_unloaded_module.name[0]) pr_cont(" [last unloaded: %s%s]", last_unloaded_module.name, last_unloaded_module.taints); pr_cont("\n"); } #ifdef CONFIG_MODULE_DEBUGFS struct dentry *mod_debugfs_root; static int module_debugfs_init(void) { mod_debugfs_root = debugfs_create_dir("modules", NULL); return 0; } module_init(module_debugfs_init); #endif |
| 2 2 102 102 102 102 102 102 102 258 149 149 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; DEFINE_RAW_SPINLOCK(timekeeper_lock); /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the timekeeper_lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) { u64 max_cycles = tk->tkr_mono.clock->max_cycles; const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", offset, name, max_cycles); printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } } if (tk->underflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->underflow_seen = 0; } if (tk->overflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->overflow_seen = 0; } } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; unsigned int seq; /* * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; } while (read_seqcount_retry(&tk_core.seq, seq)); delta = clocksource_delta(now, last, mask); /* * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) tk->underflow_seen = 1; /* Check for multiplication overflows */ if (unlikely(delta > max)) tk->overflow_seen = 1; /* timekeeping_cycles_to_ns() handles both under and overflow */ return timekeeping_cycles_to_ns(tkr, now); } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { BUG(); } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) return timekeeping_debug_get_ns(tkr); return __timekeeping_get_ns(tkr); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update(tk, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; u64 basem, baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) *mono = basem + delta; return baser + delta; } /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * ktime_get_fast_timestamps: - NMI safe timestamps * @snapshot: Pointer to timestamp storage * * Stores clock monotonic, boottime and realtime timestamps. * * Boot time is a racy access on 32bit systems if the sleep time injection * happens late during resume and not in timekeeping_resume(). That could * be avoided by expanding struct tk_read_base with boot offset for 32bit * and adding more overhead to the update. As this is a hard to observe * once per resume event which can be filtered with reasonable effort using * the accurate mono/real timestamps, it's probably not worth the trouble. * * Aside of that it might be possible on 32 and 64 bit to observe the * following when the sleep time injection happens late: * * CPU 0 CPU 1 * timekeeping_resume() * ktime_get_fast_timestamps() * mono, real = __ktime_get_real_fast() * inject_sleep_time() * update boot offset * boot = mono + bootoffset; * * That means that boot time already has the sleep time adjustment, but * real time does not. On the next readout both are in sync again. * * Preventing this for 64bit is not really feasible without destroying the * careful cache layout of the timekeeper because the sequence count and * struct tk_read_base would then need two cache lines instead of one. * * Access to the time keeper clock source is disabled across the innermost * steps of suspend/resume. The accessors still work, but the timestamps * are frozen until time keeping is resumed which happens very early. * * For regular suspend/resume there is no observable difference vs. sched * clock, but it might affect some of the nasty low level debug printks. * * OTOH, access to sched clock is not guaranteed across suspend/resume on * all systems either so it depends on the hardware in use. * * If that turns out to be a real problem then this could be mitigated by * using sched clock in a similar way as during early boot. But it's not as * trivial as on early boot because it needs some careful protection * against the clock monotonic timestamp jumping backwards on resume. */ void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) { struct timekeeper *tk = &tk_core.timekeeper; snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); } /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * The mirroring of the data to the shadow-timekeeper needs * to happen last here to ensure we don't over-write the * timekeeper structure on the next update with stale data */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || tk->tkr_mono.clock->id != system_counterval.cs_id) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); xt = tk_xtime(tk); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; goto out; } tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); if (!ret) { audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); } return ret; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 tmp; int ret = 0; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old = NULL; unsigned long flags; bool change = false; new = (struct clocksource *) data; /* * If the cs is in module, get a module reference. Succeeds * for built-in code (owner == NULL) as well. */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) change = true; else module_put(new->owner); } raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); if (change) { old = tk->tkr_mono.clock; tk_setup_internals(tk, new); } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tk, clock); tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); suspend_timing_needed = false; timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tk->tkr_mono.clock; cycle_now = tk->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update(tk, TK_MIRROR); halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tick_length())) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tick_length(); mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; u64 offset; int shift = 0, maxshift; unsigned int clock_set = 0; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * * We could avoid this memcpy by switching pointers, but that * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this * memcpy under the tk_core.seq against one before we start * updating. */ timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return !!clock_set; } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; bool clock_set = false; struct timespec64 ts; unsigned long flags; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); clock_set = true; } tk_update_leap_state(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) clock_was_set(CLOCK_REALTIME); ntp_notify_cmos_timer(); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | // SPDX-License-Identifier: GPL-2.0 /* * lib/smp_processor_id.c * * DEBUG_PREEMPT variant of smp_processor_id(). */ #include <linux/export.h> #include <linux/kprobes.h> #include <linux/sched.h> noinstr static unsigned int check_preemption_disabled(const char *what1, const char *what2) { int this_cpu = raw_smp_processor_id(); if (likely(preempt_count())) goto out; if (irqs_disabled()) goto out; if (is_percpu_thread()) goto out; #ifdef CONFIG_SMP if (current->migration_disabled) goto out; #endif /* * It is valid to assume CPU-locality during early bootup: */ if (system_state < SYSTEM_SCHEDULING) goto out; /* * Avoid recursion: */ preempt_disable_notrace(); instrumentation_begin(); if (!printk_ratelimit()) goto out_enable; printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", what1, what2, preempt_count() - 1, current->comm, current->pid); printk("caller is %pS\n", __builtin_return_address(0)); dump_stack(); out_enable: instrumentation_end(); preempt_enable_no_resched_notrace(); out: return this_cpu; } noinstr unsigned int debug_smp_processor_id(void) { return check_preemption_disabled("smp_processor_id", ""); } EXPORT_SYMBOL(debug_smp_processor_id); noinstr void __this_cpu_preempt_check(const char *op) { check_preemption_disabled("__this_cpu_", op); } EXPORT_SYMBOL(__this_cpu_preempt_check); |
| 338 334 336 336 338 336 337 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/kernel/return_address.c * * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> */ #include <linux/export.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/stacktrace.h> #include <asm/stack_pointer.h> struct return_address_data { unsigned int level; void *addr; }; static bool save_return_addr(void *d, unsigned long pc) { struct return_address_data *data = d; if (!data->level) { data->addr = (void *)pc; return false; } else { --data->level; return true; } } NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { struct return_address_data data; data.level = level + 2; data.addr = NULL; arch_stack_walk(save_return_addr, &data, current, NULL); if (!data.level) return data.addr; else return NULL; } EXPORT_SYMBOL_GPL(return_address); NOKPROBE_SYMBOL(return_address); |
| 24 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/traps.c * * Copyright (C) 1995-2009 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/bug.h> #include <linux/context_tracking.h> #include <linux/signal.h> #include <linux/kallsyms.h> #include <linux/kprobes.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kdebug.h> #include <linux/module.h> #include <linux/kexec.h> #include <linux/delay.h> #include <linux/efi.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/sizes.h> #include <linux/syscalls.h> #include <linux/mm_types.h> #include <linux/kasan.h> #include <linux/ubsan.h> #include <linux/cfi.h> #include <asm/atomic.h> #include <asm/bug.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/efi.h> #include <asm/esr.h> #include <asm/exception.h> #include <asm/extable.h> #include <asm/insn.h> #include <asm/kprobes.h> #include <asm/patching.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> #include <asm/system_misc.h> #include <asm/sysreg.h> static bool __kprobes __check_eq(unsigned long pstate) { return (pstate & PSR_Z_BIT) != 0; } static bool __kprobes __check_ne(unsigned long pstate) { return (pstate & PSR_Z_BIT) == 0; } static bool __kprobes __check_cs(unsigned long pstate) { return (pstate & PSR_C_BIT) != 0; } static bool __kprobes __check_cc(unsigned long pstate) { return (pstate & PSR_C_BIT) == 0; } static bool __kprobes __check_mi(unsigned long pstate) { return (pstate & PSR_N_BIT) != 0; } static bool __kprobes __check_pl(unsigned long pstate) { return (pstate & PSR_N_BIT) == 0; } static bool __kprobes __check_vs(unsigned long pstate) { return (pstate & PSR_V_BIT) != 0; } static bool __kprobes __check_vc(unsigned long pstate) { return (pstate & PSR_V_BIT) == 0; } static bool __kprobes __check_hi(unsigned long pstate) { pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ return (pstate & PSR_C_BIT) != 0; } static bool __kprobes __check_ls(unsigned long pstate) { pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ return (pstate & PSR_C_BIT) == 0; } static bool __kprobes __check_ge(unsigned long pstate) { pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ return (pstate & PSR_N_BIT) == 0; } static bool __kprobes __check_lt(unsigned long pstate) { pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ return (pstate & PSR_N_BIT) != 0; } static bool __kprobes __check_gt(unsigned long pstate) { /*PSR_N_BIT ^= PSR_V_BIT */ unsigned long temp = pstate ^ (pstate << 3); temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ return (temp & PSR_N_BIT) == 0; } static bool __kprobes __check_le(unsigned long pstate) { /*PSR_N_BIT ^= PSR_V_BIT */ unsigned long temp = pstate ^ (pstate << 3); temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ return (temp & PSR_N_BIT) != 0; } static bool __kprobes __check_al(unsigned long pstate) { return true; } /* * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that * it behaves identically to 0b1110 ("al"). */ pstate_check_t * const aarch32_opcode_cond_checks[16] = { __check_eq, __check_ne, __check_cs, __check_cc, __check_mi, __check_pl, __check_vs, __check_vc, __check_hi, __check_ls, __check_ge, __check_lt, __check_gt, __check_le, __check_al, __check_al }; int show_unhandled_signals = 0; static void dump_kernel_instr(const char *lvl, struct pt_regs *regs) { unsigned long addr = instruction_pointer(regs); char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str; int i; if (user_mode(regs)) return; for (i = -4; i < 1; i++) { unsigned int val, bad; bad = aarch64_insn_read(&((u32 *)addr)[i], &val); if (!bad) p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val); else p += sprintf(p, i == 0 ? "(????????) " : "???????? "); } printk("%sCode: %s\n", lvl, str); } #ifdef CONFIG_PREEMPT #define S_PREEMPT " PREEMPT" #elif defined(CONFIG_PREEMPT_RT) #define S_PREEMPT " PREEMPT_RT" #else #define S_PREEMPT "" #endif #define S_SMP " SMP" static int __die(const char *str, long err, struct pt_regs *regs) { static int die_counter; int ret; pr_emerg("Internal error: %s: %016lx [#%d]" S_PREEMPT S_SMP "\n", str, err, ++die_counter); /* trap and error numbers are mostly meaningless on ARM */ ret = notify_die(DIE_OOPS, str, regs, err, 0, SIGSEGV); if (ret == NOTIFY_STOP) return ret; print_modules(); show_regs(regs); dump_kernel_instr(KERN_EMERG, regs); return ret; } static DEFINE_RAW_SPINLOCK(die_lock); /* * This function is protected against re-entrancy. */ void die(const char *str, struct pt_regs *regs, long err) { int ret; unsigned long flags; raw_spin_lock_irqsave(&die_lock, flags); oops_enter(); console_verbose(); bust_spinlocks(1); ret = __die(str, err, regs); if (regs && kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); oops_exit(); if (in_interrupt()) panic("%s: Fatal exception in interrupt", str); if (panic_on_oops) panic("%s: Fatal exception", str); raw_spin_unlock_irqrestore(&die_lock, flags); if (ret != NOTIFY_STOP) make_task_dead(SIGSEGV); } static void arm64_show_signal(int signo, const char *str) { static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); struct task_struct *tsk = current; unsigned long esr = tsk->thread.fault_code; struct pt_regs *regs = task_pt_regs(tsk); /* Leave if the signal won't be shown */ if (!show_unhandled_signals || !unhandled_signal(tsk, signo) || !__ratelimit(&rs)) return; pr_info("%s[%d]: unhandled exception: ", tsk->comm, task_pid_nr(tsk)); if (esr) pr_cont("%s, ESR 0x%016lx, ", esr_get_class_string(esr), esr); pr_cont("%s", str); print_vma_addr(KERN_CONT " in ", regs->pc); pr_cont("\n"); __show_regs(regs); } void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str) { arm64_show_signal(signo, str); if (signo == SIGKILL) force_sig(SIGKILL); else force_sig_fault(signo, code, (void __user *)far); } void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str) { arm64_show_signal(SIGBUS, str); force_sig_mceerr(code, (void __user *)far, lsb); } void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str) { arm64_show_signal(SIGTRAP, str); force_sig_ptrace_errno_trap(errno, (void __user *)far); } void arm64_notify_die(const char *str, struct pt_regs *regs, int signo, int sicode, unsigned long far, unsigned long err) { if (user_mode(regs)) { WARN_ON(regs != current_pt_regs()); current->thread.fault_address = 0; current->thread.fault_code = err; arm64_force_sig_fault(signo, sicode, far, str); } else { die(str, regs, err); } } #ifdef CONFIG_COMPAT #define PSTATE_IT_1_0_SHIFT 25 #define PSTATE_IT_1_0_MASK (0x3 << PSTATE_IT_1_0_SHIFT) #define PSTATE_IT_7_2_SHIFT 10 #define PSTATE_IT_7_2_MASK (0x3f << PSTATE_IT_7_2_SHIFT) static u32 compat_get_it_state(struct pt_regs *regs) { u32 it, pstate = regs->pstate; it = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT; it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2; return it; } static void compat_set_it_state(struct pt_regs *regs, u32 it) { u32 pstate_it; pstate_it = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK; pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK; regs->pstate &= ~PSR_AA32_IT_MASK; regs->pstate |= pstate_it; } static void advance_itstate(struct pt_regs *regs) { u32 it; /* ARM mode */ if (!(regs->pstate & PSR_AA32_T_BIT) || !(regs->pstate & PSR_AA32_IT_MASK)) return; it = compat_get_it_state(regs); /* * If this is the last instruction of the block, wipe the IT * state. Otherwise advance it. */ if (!(it & 7)) it = 0; else it = (it & 0xe0) | ((it << 1) & 0x1f); compat_set_it_state(regs, it); } #else static void advance_itstate(struct pt_regs *regs) { } #endif void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size) { regs->pc += size; /* * If we were single stepping, we want to get the step exception after * we return from the trap. */ if (user_mode(regs)) user_fastforward_single_step(current); if (compat_user_mode(regs)) advance_itstate(regs); else regs->pstate &= ~PSR_BTYPE_MASK; } static int user_insn_read(struct pt_regs *regs, u32 *insnp) { u32 instr; unsigned long pc = instruction_pointer(regs); if (compat_thumb_mode(regs)) { /* 16-bit Thumb instruction */ __le16 instr_le; if (get_user(instr_le, (__le16 __user *)pc)) return -EFAULT; instr = le16_to_cpu(instr_le); if (aarch32_insn_is_wide(instr)) { u32 instr2; if (get_user(instr_le, (__le16 __user *)(pc + 2))) return -EFAULT; instr2 = le16_to_cpu(instr_le); instr = (instr << 16) | instr2; } } else { /* 32-bit ARM instruction */ __le32 instr_le; if (get_user(instr_le, (__le32 __user *)pc)) return -EFAULT; instr = le32_to_cpu(instr_le); } *insnp = instr; return 0; } void force_signal_inject(int signal, int code, unsigned long address, unsigned long err) { const char *desc; struct pt_regs *regs = current_pt_regs(); if (WARN_ON(!user_mode(regs))) return; switch (signal) { case SIGILL: desc = "undefined instruction"; break; case SIGSEGV: desc = "illegal memory access"; break; default: desc = "unknown or unrecoverable error"; break; } /* Force signals we don't understand to SIGKILL */ if (WARN_ON(signal != SIGKILL && siginfo_layout(signal, code) != SIL_FAULT)) { signal = SIGKILL; } arm64_notify_die(desc, regs, signal, code, address, err); } /* * Set up process info to signal segmentation fault - called on access error. */ void arm64_notify_segfault(unsigned long addr) { int code; mmap_read_lock(current->mm); if (find_vma(current->mm, untagged_addr(addr)) == NULL) code = SEGV_MAPERR; else code = SEGV_ACCERR; mmap_read_unlock(current->mm); force_signal_inject(SIGSEGV, code, addr, 0); } void do_el0_undef(struct pt_regs *regs, unsigned long esr) { u32 insn; /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) return; if (user_insn_read(regs, &insn)) goto out_err; if (try_emulate_mrs(regs, insn)) return; if (try_emulate_armv8_deprecated(regs, insn)) return; out_err: force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } void do_el1_undef(struct pt_regs *regs, unsigned long esr) { u32 insn; if (aarch64_insn_read((void *)regs->pc, &insn)) goto out_err; if (try_emulate_el1_ssbs(regs, insn)) return; out_err: die("Oops - Undefined instruction", regs, esr); } void do_el0_bti(struct pt_regs *regs) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } void do_el1_bti(struct pt_regs *regs, unsigned long esr) { if (efi_runtime_fixup_exception(regs, "BTI violation")) { regs->pstate &= ~PSR_BTYPE_MASK; return; } die("Oops - BTI", regs, esr); } void do_el0_fpac(struct pt_regs *regs, unsigned long esr) { force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr); } void do_el1_fpac(struct pt_regs *regs, unsigned long esr) { /* * Unexpected FPAC exception in the kernel: kill the task before it * does any more harm. */ die("Oops - FPAC", regs, esr); } void do_el0_mops(struct pt_regs *regs, unsigned long esr) { arm64_mops_reset_regs(®s->user_regs, esr); /* * If single stepping then finish the step before executing the * prologue instruction. */ user_fastforward_single_step(current); } #define __user_cache_maint(insn, address, res) \ if (address >= TASK_SIZE_MAX) { \ res = -EFAULT; \ } else { \ uaccess_ttbr0_enable(); \ asm volatile ( \ "1: " insn ", %1\n" \ " mov %w0, #0\n" \ "2:\n" \ _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0) \ : "=r" (res) \ : "r" (address)); \ uaccess_ttbr0_disable(); \ } static void user_cache_maint_handler(unsigned long esr, struct pt_regs *regs) { unsigned long tagged_address, address; int rt = ESR_ELx_SYS64_ISS_RT(esr); int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; int ret = 0; tagged_address = pt_regs_read_reg(regs, rt); address = untagged_addr(tagged_address); switch (crm) { case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */ __user_cache_maint("dc civac", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */ __user_cache_maint("dc civac", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CVADP: /* DC CVADP */ __user_cache_maint("sys 3, c7, c13, 1", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CVAP: /* DC CVAP */ __user_cache_maint("sys 3, c7, c12, 1", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC: /* DC CIVAC */ __user_cache_maint("dc civac", address, ret); break; case ESR_ELx_SYS64_ISS_CRM_IC_IVAU: /* IC IVAU */ __user_cache_maint("ic ivau", address, ret); break; default: force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } if (ret) arm64_notify_segfault(tagged_address); else arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } static void ctr_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); if (cpus_have_final_cap(ARM64_WORKAROUND_1542419)) { /* Hide DIC so that we can trap the unnecessary maintenance...*/ val &= ~BIT(CTR_EL0_DIC_SHIFT); /* ... and fake IminLine to reduce the number of traps. */ val &= ~CTR_EL0_IminLine_MASK; val |= (PAGE_SHIFT - 2) & CTR_EL0_IminLine_MASK; } pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } static void cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); pt_regs_write_reg(regs, rt, arch_timer_read_counter()); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } static void cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = ESR_ELx_SYS64_ISS_RT(esr); pt_regs_write_reg(regs, rt, arch_timer_get_rate()); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } static void mrs_handler(unsigned long esr, struct pt_regs *regs) { u32 sysreg, rt; rt = ESR_ELx_SYS64_ISS_RT(esr); sysreg = esr_sys64_to_sysreg(esr); if (do_emulate_mrs(regs, sysreg, rt) != 0) force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } static void wfi_handler(unsigned long esr, struct pt_regs *regs) { arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } struct sys64_hook { unsigned long esr_mask; unsigned long esr_val; void (*handler)(unsigned long esr, struct pt_regs *regs); }; static const struct sys64_hook sys64_hooks[] = { { .esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL, .handler = user_cache_maint_handler, }, { /* Trap read access to CTR_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ, .handler = ctr_read_handler, }, { /* Trap read access to CNTVCT_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCT, .handler = cntvct_read_handler, }, { /* Trap read access to CNTVCTSS_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCTSS, .handler = cntvct_read_handler, }, { /* Trap read access to CNTFRQ_EL0 */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ, .handler = cntfrq_read_handler, }, { /* Trap read access to CPUID registers */ .esr_mask = ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL, .handler = mrs_handler, }, { /* Trap WFI instructions executed in userspace */ .esr_mask = ESR_ELx_WFx_MASK, .esr_val = ESR_ELx_WFx_WFI_VAL, .handler = wfi_handler, }, {}, }; #ifdef CONFIG_COMPAT static bool cp15_cond_valid(unsigned long esr, struct pt_regs *regs) { int cond; /* Only a T32 instruction can trap without CV being set */ if (!(esr & ESR_ELx_CV)) { u32 it; it = compat_get_it_state(regs); if (!it) return true; cond = it >> 4; } else { cond = (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; } return aarch32_opcode_cond_checks[cond](regs->pstate); } static void compat_cntfrq_read_handler(unsigned long esr, struct pt_regs *regs) { int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT; pt_regs_write_reg(regs, reg, arch_timer_get_rate()); arm64_skip_faulting_instruction(regs, 4); } static const struct sys64_hook cp15_32_hooks[] = { { .esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ, .handler = compat_cntfrq_read_handler, }, {}, }; static void compat_cntvct_read_handler(unsigned long esr, struct pt_regs *regs) { int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT; int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT; u64 val = arch_timer_read_counter(); pt_regs_write_reg(regs, rt, lower_32_bits(val)); pt_regs_write_reg(regs, rt2, upper_32_bits(val)); arm64_skip_faulting_instruction(regs, 4); } static const struct sys64_hook cp15_64_hooks[] = { { .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT, .handler = compat_cntvct_read_handler, }, { .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCTSS, .handler = compat_cntvct_read_handler, }, {}, }; void do_el0_cp15(unsigned long esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; if (!cp15_cond_valid(esr, regs)) { /* * There is no T16 variant of a CP access, so we * always advance PC by 4 bytes. */ arm64_skip_faulting_instruction(regs, 4); return; } switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_CP15_32: hook_base = cp15_32_hooks; break; case ESR_ELx_EC_CP15_64: hook_base = cp15_64_hooks; break; default: do_el0_undef(regs, esr); return; } for (hook = hook_base; hook->handler; hook++) if ((hook->esr_mask & esr) == hook->esr_val) { hook->handler(esr, regs); return; } /* * New cp15 instructions may previously have been undefined at * EL0. Fall back to our usual undefined instruction handler * so that we handle these consistently. */ do_el0_undef(regs, esr); } #endif void do_el0_sys(unsigned long esr, struct pt_regs *regs) { const struct sys64_hook *hook; for (hook = sys64_hooks; hook->handler; hook++) if ((hook->esr_mask & esr) == hook->esr_val) { hook->handler(esr, regs); return; } /* * New SYS instructions may previously have been undefined at EL0. Fall * back to our usual undefined instruction handler so that we handle * these consistently. */ do_el0_undef(regs, esr); } static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", [ESR_ELx_EC_UNKNOWN] = "Unknown/Uncategorized", [ESR_ELx_EC_WFx] = "WFI/WFE", [ESR_ELx_EC_CP15_32] = "CP15 MCR/MRC", [ESR_ELx_EC_CP15_64] = "CP15 MCRR/MRRC", [ESR_ELx_EC_CP14_MR] = "CP14 MCR/MRC", [ESR_ELx_EC_CP14_LS] = "CP14 LDC/STC", [ESR_ELx_EC_FP_ASIMD] = "ASIMD", [ESR_ELx_EC_CP10_ID] = "CP10 MRC/VMRS", [ESR_ELx_EC_PAC] = "PAC", [ESR_ELx_EC_CP14_64] = "CP14 MCRR/MRRC", [ESR_ELx_EC_BTI] = "BTI", [ESR_ELx_EC_ILL] = "PSTATE.IL", [ESR_ELx_EC_SVC32] = "SVC (AArch32)", [ESR_ELx_EC_HVC32] = "HVC (AArch32)", [ESR_ELx_EC_SMC32] = "SMC (AArch32)", [ESR_ELx_EC_SVC64] = "SVC (AArch64)", [ESR_ELx_EC_HVC64] = "HVC (AArch64)", [ESR_ELx_EC_SMC64] = "SMC (AArch64)", [ESR_ELx_EC_SYS64] = "MSR/MRS (AArch64)", [ESR_ELx_EC_SVE] = "SVE", [ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB", [ESR_ELx_EC_FPAC] = "FPAC", [ESR_ELx_EC_SME] = "SME", [ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF", [ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)", [ESR_ELx_EC_IABT_CUR] = "IABT (current EL)", [ESR_ELx_EC_PC_ALIGN] = "PC Alignment", [ESR_ELx_EC_DABT_LOW] = "DABT (lower EL)", [ESR_ELx_EC_DABT_CUR] = "DABT (current EL)", [ESR_ELx_EC_SP_ALIGN] = "SP Alignment", [ESR_ELx_EC_MOPS] = "MOPS", [ESR_ELx_EC_FP_EXC32] = "FP (AArch32)", [ESR_ELx_EC_FP_EXC64] = "FP (AArch64)", [ESR_ELx_EC_SERROR] = "SError", [ESR_ELx_EC_BREAKPT_LOW] = "Breakpoint (lower EL)", [ESR_ELx_EC_BREAKPT_CUR] = "Breakpoint (current EL)", [ESR_ELx_EC_SOFTSTP_LOW] = "Software Step (lower EL)", [ESR_ELx_EC_SOFTSTP_CUR] = "Software Step (current EL)", [ESR_ELx_EC_WATCHPT_LOW] = "Watchpoint (lower EL)", [ESR_ELx_EC_WATCHPT_CUR] = "Watchpoint (current EL)", [ESR_ELx_EC_BKPT32] = "BKPT (AArch32)", [ESR_ELx_EC_VECTOR32] = "Vector catch (AArch32)", [ESR_ELx_EC_BRK64] = "BRK (AArch64)", }; const char *esr_get_class_string(unsigned long esr) { return esr_class_str[ESR_ELx_EC(esr)]; } /* * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. */ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr) { unsigned long pc = instruction_pointer(regs); current->thread.fault_address = 0; current->thread.fault_code = esr; arm64_force_sig_fault(SIGILL, ILL_ILLOPC, pc, "Bad EL0 synchronous exception"); } #ifdef CONFIG_VMAP_STACK DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); console_verbose(); pr_emerg("Insufficient stack space to handle exception!"); pr_emerg("ESR: 0x%016lx -- %s\n", esr, esr_get_class_string(esr)); pr_emerg("FAR: 0x%016lx\n", far); pr_emerg("Task stack: [0x%016lx..0x%016lx]\n", tsk_stk, tsk_stk + THREAD_SIZE); pr_emerg("IRQ stack: [0x%016lx..0x%016lx]\n", irq_stk, irq_stk + IRQ_STACK_SIZE); pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n", ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE); __show_regs(regs); /* * We use nmi_panic to limit the potential for recusive overflows, and * to get a better stack trace. */ nmi_panic(NULL, "kernel stack overflow"); cpu_park_loop(); } #endif void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) { console_verbose(); pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n", smp_processor_id(), esr, esr_get_class_string(esr)); if (regs) __show_regs(regs); nmi_panic(regs, "Asynchronous SError Interrupt"); cpu_park_loop(); } bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr) { unsigned long aet = arm64_ras_serror_get_severity(esr); switch (aet) { case ESR_ELx_AET_CE: /* corrected error */ case ESR_ELx_AET_UEO: /* restartable, not yet consumed */ /* * The CPU can make progress. We may take UEO again as * a more severe error. */ return false; case ESR_ELx_AET_UEU: /* Uncorrected Unrecoverable */ case ESR_ELx_AET_UER: /* Uncorrected Recoverable */ /* * The CPU can't make progress. The exception may have * been imprecise. * * Neoverse-N1 #1349291 means a non-KVM SError reported as * Unrecoverable should be treated as Uncontainable. We * call arm64_serror_panic() in both cases. */ return true; case ESR_ELx_AET_UC: /* Uncontainable or Uncategorized error */ default: /* Error has been silently propagated */ arm64_serror_panic(regs, esr); } } void do_serror(struct pt_regs *regs, unsigned long esr) { /* non-RAS errors are not containable */ if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr)) arm64_serror_panic(regs, esr); } /* GENERIC_BUG traps */ #ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { /* * bug_handler() only called for BRK #BUG_BRK_IMM. * So the answer is trivial -- any spurious instances with no * bug table entry will be rejected by report_bug() and passed * back to the debug-monitors code and handled as a fatal * unexpected debug exception. */ return 1; } #endif static int bug_handler(struct pt_regs *regs, unsigned long esr) { switch (report_bug(regs->pc, regs)) { case BUG_TRAP_TYPE_BUG: die("Oops - BUG", regs, esr); break; case BUG_TRAP_TYPE_WARN: break; default: /* unknown/unrecognised bug trap type */ return DBG_HOOK_ERROR; } /* If thread survives, skip over the BUG instruction and continue: */ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); return DBG_HOOK_HANDLED; } static struct break_hook bug_break_hook = { .fn = bug_handler, .imm = BUG_BRK_IMM, }; #ifdef CONFIG_CFI_CLANG static int cfi_handler(struct pt_regs *regs, unsigned long esr) { unsigned long target; u32 type; target = pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TARGET, esr)); type = (u32)pt_regs_read_reg(regs, FIELD_GET(CFI_BRK_IMM_TYPE, esr)); switch (report_cfi_failure(regs, regs->pc, &target, type)) { case BUG_TRAP_TYPE_BUG: die("Oops - CFI", regs, esr); break; case BUG_TRAP_TYPE_WARN: break; default: return DBG_HOOK_ERROR; } arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); return DBG_HOOK_HANDLED; } static struct break_hook cfi_break_hook = { .fn = cfi_handler, .imm = CFI_BRK_IMM_BASE, .mask = CFI_BRK_IMM_MASK, }; #endif /* CONFIG_CFI_CLANG */ static int reserved_fault_handler(struct pt_regs *regs, unsigned long esr) { pr_err("%s generated an invalid instruction at %pS!\n", "Kernel text patching", (void *)instruction_pointer(regs)); /* We cannot handle this */ return DBG_HOOK_ERROR; } static struct break_hook fault_break_hook = { .fn = reserved_fault_handler, .imm = FAULT_BRK_IMM, }; #ifdef CONFIG_KASAN_SW_TAGS #define KASAN_ESR_RECOVER 0x20 #define KASAN_ESR_WRITE 0x10 #define KASAN_ESR_SIZE_MASK 0x0f #define KASAN_ESR_SIZE(esr) (1 << ((esr) & KASAN_ESR_SIZE_MASK)) static int kasan_handler(struct pt_regs *regs, unsigned long esr) { bool recover = esr & KASAN_ESR_RECOVER; bool write = esr & KASAN_ESR_WRITE; size_t size = KASAN_ESR_SIZE(esr); void *addr = (void *)regs->regs[0]; u64 pc = regs->pc; kasan_report(addr, size, write, pc); /* * The instrumentation allows to control whether we can proceed after * a crash was detected. This is done by passing the -recover flag to * the compiler. Disabling recovery allows to generate more compact * code. * * Unfortunately disabling recovery doesn't work for the kernel right * now. KASAN reporting is disabled in some contexts (for example when * the allocator accesses slab object metadata; this is controlled by * current->kasan_depth). All these accesses are detected by the tool, * even though the reports for them are not printed. * * This is something that might be fixed at some point in the future. */ if (!recover) die("Oops - KASAN", regs, esr); /* If thread survives, skip over the brk instruction and continue: */ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); return DBG_HOOK_HANDLED; } static struct break_hook kasan_break_hook = { .fn = kasan_handler, .imm = KASAN_BRK_IMM, .mask = KASAN_BRK_MASK, }; #endif #ifdef CONFIG_UBSAN_TRAP static int ubsan_handler(struct pt_regs *regs, unsigned long esr) { die(report_ubsan_failure(regs, esr & UBSAN_BRK_MASK), regs, esr); return DBG_HOOK_HANDLED; } static struct break_hook ubsan_break_hook = { .fn = ubsan_handler, .imm = UBSAN_BRK_IMM, .mask = UBSAN_BRK_MASK, }; #endif /* * Initial handler for AArch64 BRK exceptions * This handler only used until debug_traps_init(). */ int __init early_brk64(unsigned long addr, unsigned long esr, struct pt_regs *regs) { #ifdef CONFIG_CFI_CLANG if (esr_is_cfi_brk(esr)) return cfi_handler(regs, esr) != DBG_HOOK_HANDLED; #endif #ifdef CONFIG_KASAN_SW_TAGS if ((esr_brk_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM) return kasan_handler(regs, esr) != DBG_HOOK_HANDLED; #endif #ifdef CONFIG_UBSAN_TRAP if ((esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM) return ubsan_handler(regs, esr) != DBG_HOOK_HANDLED; #endif return bug_handler(regs, esr) != DBG_HOOK_HANDLED; } void __init trap_init(void) { register_kernel_break_hook(&bug_break_hook); #ifdef CONFIG_CFI_CLANG register_kernel_break_hook(&cfi_break_hook); #endif register_kernel_break_hook(&fault_break_hook); #ifdef CONFIG_KASAN_SW_TAGS register_kernel_break_hook(&kasan_break_hook); #endif #ifdef CONFIG_UBSAN_TRAP register_kernel_break_hook(&ubsan_break_hook); #endif debug_traps_init(); } |
| 44 42 121 121 86 85 49 7 49 7 117 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_bit(IMA_MUST_MEASURE, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); if (inode_is_open_for_write(inode) && must_measure) send_writers = true; } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { struct kstat stat; update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if ((iint->flags & IMA_NEW_FILE) || vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) || stat.change_cookie != iint->real_inode.version) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, u32 secid, char *buf, loff_t size, int mask, enum ima_hooks func) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, secid, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE)); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* reset appraisal flags if ima_inode_post_setattr was called */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { u32 secid; int ret; if (!file) return 0; security_current_getsecid_subj(&secid); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; int result = 0; int action; u32 secid; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getsecid_subj(&secid); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { int ret; u32 secid; security_current_getsecid_subj(&secid); ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getsecid(bprm->cred, &secid); return process_measurement(bprm->file, bprm->cred, secid, NULL, 0, MAY_EXEC, CREDS_CHECK); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { u32 secid; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; u32 secid; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; u32 secid; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, buf, size, MAY_READ, func); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_ima_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; u32 secid; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxilary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxilary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getsecid_subj(&secid); action = ima_get_action(idmap, inode, current_cred(), secid, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { struct fd f; if (!buf || !size) return; f = fdget(kernel_fd); if (!f.file) return; process_buffer_measurement(file_mnt_idmap(f.file), file_inode(f.file), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); fdput(f); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1pad(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1pad(rsa,", 20) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security, ima_inode_free), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .name = "ima", .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, }; late_initcall(init_ima); /* Start IMA after the TPM is available */ |
| 49 49 49 49 49 215 215 215 214 215 215 215 214 214 156 156 156 156 71 156 155 37 156 2 156 156 156 155 156 156 156 43 44 44 44 44 44 44 10 44 8 44 44 44 44 44 44 43 34 283 41 7 35 35 283 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/swap.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ static struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __ro_after_init; static struct percpu_counter nr_files __cacheline_aligned_in_smp; /* Container for backing file with optional user path */ struct backing_file { struct file file; struct path user_path; }; static inline struct backing_file *backing_file(struct file *f) { return container_of(f, struct backing_file, file); } struct path *backing_file_user_path(struct file *f) { return &backing_file(f)->user_path; } EXPORT_SYMBOL_GPL(backing_file_user_path); static inline void file_free(struct file *f) { security_file_free(f); if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); put_cred(f->f_cred); if (unlikely(f->f_mode & FMODE_BACKING)) { path_put(backing_file_user_path(f)); kfree(backing_file(f)); } else { kmem_cache_free(filp_cachep, f); } } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Handle nr_files sysctl */ static int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = SYSCTL_LONG_ZERO, .extra2 = SYSCTL_LONG_MAX, }, { .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, }; static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); if (IS_ENABLED(CONFIG_BINFMT_MISC)) { struct ctl_table_header *hdr; hdr = register_sysctl_mount_point("fs/binfmt_misc"); kmemleak_not_leak(hdr); } return 0; } fs_initcall(init_fs_stat_sysctls); #endif static int init_file(struct file *f, int flags, const struct cred *cred) { int error; f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { put_cred(f->f_cred); return error; } rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ /* * We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While * fget-rcu pattern users need to be able to handle spurious * refcount bumps we should reinitialize the reused file first. */ atomic_long_set(&f->f_count, 1); return 0; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; int error; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } f->f_mode |= FMODE_NOACCOUNT; return f; } /* * Variant of alloc_empty_file() that allocates a backing_file container * and doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_backing_file(int flags, const struct cred *cred) { struct backing_file *ff; int error; ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL); if (unlikely(!ff)) return ERR_PTR(-ENOMEM); error = init_file(&ff->file, flags, cred); if (unlikely(error)) { kfree(ff); return ERR_PTR(error); } ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT; return &ff->file; } /** * file_init_path - initialize a 'struct file' based on path * * @file: the file to set up * @path: the (dentry, vfsmount) pair for the new file * @fop: the 'struct file_operations' for the new file */ static void file_init_path(struct file *file, const struct path *path, const struct file_operations *fop) { file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if (fop->llseek) file->f_mode |= FMODE_LSEEK; if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_iocb_flags = iocb_flags(file); file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (!IS_ERR(file)) file_init_path(file, path, fop); return file; } static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { struct qstr this = QSTR_INIT(name, strlen(name)); path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); d_instantiate(path->dentry, inode); return 0; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); } return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_pseudo_noaccount(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_empty_file_noaccount(flags, current_cred()); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } file_init_path(file, &path, fops); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); security_file_release(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); put_pid(file->f_owner.pid); put_file_access(file); dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_task_work)); } /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); void fput(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) { file_free(file); return; } if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_task_work, ____fput); if (!task_work_add(task, &file->f_task_work, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } } /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) __fput(file); } EXPORT_SYMBOL(fput); EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 188 192 188 191 188 189 191 191 191 189 188 189 189 187 188 189 189 188 188 189 188 189 189 189 188 189 189 189 188 188 189 189 188 189 188 189 188 188 189 6 10 10 4 4 6 6 6 6 6 6 6 167 166 168 166 3 3 97 97 97 97 97 97 97 97 97 97 97 97 97 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/fs_struct.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" #include "internal.h" struct prepend_buffer { char *buf; int len; }; #define DECLARE_BUFFER(__name, __buf, __len) \ struct prepend_buffer __name = {.buf = __buf + __len, .len = __len} static char *extract_string(struct prepend_buffer *p) { if (likely(p->len >= 0)) return p->buf; return ERR_PTR(-ENAMETOOLONG); } static bool prepend_char(struct prepend_buffer *p, unsigned char c) { if (likely(p->len > 0)) { p->len--; *--p->buf = c; return true; } p->len = -1; return false; } /* * The source of the prepend data can be an optimistic load * of a dentry name and length. And because we don't hold any * locks, the length and the pointer to the name may not be * in sync if a concurrent rename happens, and the kernel * copy might fault as a result. * * The end result will correct itself when we check the * rename sequence count, but we need to be able to handle * the fault gracefully. */ static bool prepend_copy(void *dst, const void *src, int len) { if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len); return false; } return true; } static bool prepend(struct prepend_buffer *p, const char *str, int namelen) { // Already overflowed? if (p->len < 0) return false; // Will overflow? if (p->len < namelen) { // Fill as much as possible from the end of the name str += namelen - p->len; p->buf -= p->len; prepend_copy(p->buf, str, p->len); p->len = -1; return false; } // Fits fully p->len -= namelen; p->buf -= namelen; return prepend_copy(p->buf, str, namelen); } /** * prepend_name - prepend a pathname in front of current buffer pointer * @p: prepend buffer which contains buffer pointer and allocated length * @name: name string and length qstr structure * * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * But since the length cannot be trusted, we need to copy the name very * carefully when doing the prepend_copy(). It also prepends "/" at * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. * * Load acquire is needed to make sure that we see the new name data even * if we might get the length wrong. */ static bool prepend_name(struct prepend_buffer *p, const struct qstr *name) { const char *dname = smp_load_acquire(&name->name); /* ^^^ */ u32 dlen = READ_ONCE(name->len); return prepend(p, dname, dlen) && prepend_char(p, '/'); } static int __prepend_path(const struct dentry *dentry, const struct mount *mnt, const struct path *root, struct prepend_buffer *p) { while (dentry != root->dentry || &mnt->mnt != root->mnt) { const struct dentry *parent = READ_ONCE(dentry->d_parent); if (dentry == mnt->mnt.mnt_root) { struct mount *m = READ_ONCE(mnt->mnt_parent); struct mnt_namespace *mnt_ns; if (likely(mnt != m)) { dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = m; continue; } /* Global root */ mnt_ns = READ_ONCE(mnt->mnt_ns); /* open-coded is_mounted() to use local mnt_ns */ if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) return 1; // absolute root else return 2; // detached or not attached yet } if (unlikely(dentry == parent)) /* Escaped? */ return 3; prefetch(parent); if (!prepend_name(p, &dentry->d_name)) break; dentry = parent; } return 0; } /** * prepend_path - Prepend path string to a buffer * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @p: prepend buffer which contains buffer pointer and allocated length * * The function will first try to write out the pathname without taking any * lock other than the RCU read lock to make sure that dentries won't go away. * It only checks the sequence number of the global rename_lock as any change * in the dentry's d_seq will be preceded by changes in the rename_lock * sequence number. If the sequence number had been changed, it will restart * the whole pathname back-tracing sequence again by taking the rename_lock. * In this case, there is no need to take the RCU read lock as the recursive * parent pointer references will keep the dentry chain alive as long as no * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, struct prepend_buffer *p) { unsigned seq, m_seq = 0; struct prepend_buffer b; int error; rcu_read_lock(); restart_mnt: read_seqbegin_or_lock(&mount_lock, &m_seq); seq = 0; rcu_read_lock(); restart: b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b); if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (!(m_seq & 1)) rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) { m_seq = 1; goto restart_mnt; } done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/'); *p = b; return error; } /** * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. * * Returns a pointer into the buffer or an error code if the * path was too long. * * "buflen" should be positive. * * If the path is not reachable from the supplied root, return %NULL. */ char *__d_path(const struct path *path, const struct path *root, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, root, &b) > 0)) return NULL; return extract_string(&b); } char *d_absolute_path(const struct path *path, char *buf, int buflen) { struct path root = {}; DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1)) return ERR_PTR(-EINVAL); return extract_string(&b); } static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; } while (read_seqcount_retry(&fs->seq, seq)); } /** * d_path - return the path of a dentry * @path: path to report * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. If the entry has been deleted * the string " (deleted)" is appended. Note that this is ambiguous. * * Returns a pointer into the buffer or an error code if the path was * too long. Note: Callers should use the returned pointer, not the passed * in buffer, to use the name! The implementation often starts at an offset * into the buffer, and may leave 0 bytes at the start. * * "buflen" should be positive. */ char *d_path(const struct path *path, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); struct path root; /* * We have various synthetic filesystems that never get mounted. On * these filesystems dentries are never used for lookup purposes, and * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: * * Some pseudo inodes are mountable. When they are mounted * path->dentry == path->mnt->mnt_root. In that case don't call d_dname * and instead have d_path return the mounted path. */ if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11); else prepend_char(&b, 0); prepend_path(path, &root, &b); rcu_read_unlock(); return extract_string(&b); } EXPORT_SYMBOL(d_path); /* * Helper function for dentry_operations.d_dname() members */ char *dynamic_dname(char *buffer, int buflen, const char *fmt, ...) { va_list args; char temp[64]; int sz; va_start(args, fmt); sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1; va_end(args); if (sz > sizeof(temp) || sz > buflen) return ERR_PTR(-ENAMETOOLONG); buffer += buflen - sz; return memcpy(buffer, temp, sz); } char *simple_dname(struct dentry *dentry, char *buffer, int buflen) { DECLARE_BUFFER(b, buffer, buflen); /* these dentries are never renamed, so d_lock is not needed */ prepend(&b, " (deleted)", 11); prepend(&b, dentry->d_name.name, dentry->d_name.len); prepend_char(&b, '/'); return extract_string(&b); } /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p) { const struct dentry *dentry; struct prepend_buffer b; int seq = 0; rcu_read_lock(); restart: dentry = d; b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { const struct dentry *parent = dentry->d_parent; prefetch(parent); if (!prepend_name(&b, &dentry->d_name)) break; dentry = parent; } if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (b.len == p->len) prepend_char(&b, '/'); return extract_string(&b); } char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); return __dentry_path(dentry, &b); } EXPORT_SYMBOL(dentry_path_raw); char *dentry_path(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); if (unlikely(d_unlinked(dentry))) prepend(&b, "//deleted", 10); else prepend_char(&b, 0); return __dentry_path(dentry, &b); } static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, struct path *pwd) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; *pwd = fs->pwd; } while (read_seqcount_retry(&fs->seq, seq)); } /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just * returns the length of the buffer filled (which * includes the ending '\0' character), or a negative * error value. So libc would do something like * * char *getcwd(char * buf, size_t size) * { * int retval; * * retval = sys_getcwd(buf, size); * if (retval >= 0) * return buf; * errno = -retval; * return NULL; * } */ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; char *page = __getname(); if (!page) return -ENOMEM; rcu_read_lock(); get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); if (unlikely(d_unlinked(pwd.dentry))) { rcu_read_unlock(); error = -ENOENT; } else { unsigned len; DECLARE_BUFFER(b, page, PATH_MAX); prepend_char(&b, 0); if (unlikely(prepend_path(&pwd, &root, &b) > 0)) prepend(&b, "(unreachable)", 13); rcu_read_unlock(); len = PATH_MAX - b.len; if (unlikely(len > PATH_MAX)) error = -ENAMETOOLONG; else if (unlikely(len > size)) error = -ERANGE; else if (copy_to_user(buf, b.buf, len)) error = -EFAULT; else error = len; } __putname(page); return error; } |
| 1 1 1 97 97 97 3 3 3 5 4 4 4 4 5 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | // SPDX-License-Identifier: GPL-2.0 /* * KVM coalesced MMIO * * Copyright (c) 2008 Bull S.A.S. * Copyright 2009 Red Hat, Inc. and/or its affiliates. * * Author: Laurent Vivier <Laurent.Vivier@bull.net> * */ #include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/slab.h> #include <linux/kvm.h> #include "coalesced_mmio.h" static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev) { return container_of(dev, struct kvm_coalesced_mmio_dev, dev); } static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, gpa_t addr, int len) { /* is it in a batchable area ? * (addr,len) is fully included in * (zone->addr, zone->size) */ if (len < 0) return 0; if (addr + len < addr) return 0; if (addr < dev->zone.addr) return 0; if (addr + len > dev->zone.addr + dev->zone.size) return 0; return 1; } static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev, u32 last) { struct kvm_coalesced_mmio_ring *ring; unsigned avail; /* Are we able to batch it ? */ /* last is the first free entry * check if we don't meet the first used entry * there is always one unused entry in the buffer */ ring = dev->kvm->coalesced_mmio_ring; avail = (ring->first - last - 1) % KVM_COALESCED_MMIO_MAX; if (avail == 0) { /* full */ return 0; } return 1; } static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring; __u32 insert; if (!coalesced_mmio_in_range(dev, addr, len)) return -EOPNOTSUPP; spin_lock(&dev->kvm->ring_lock); insert = READ_ONCE(ring->last); if (!coalesced_mmio_has_room(dev, insert) || insert >= KVM_COALESCED_MMIO_MAX) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } /* copy data in first free entry of the ring */ ring->coalesced_mmio[insert].phys_addr = addr; ring->coalesced_mmio[insert].len = len; memcpy(ring->coalesced_mmio[insert].data, val, len); ring->coalesced_mmio[insert].pio = dev->zone.pio; smp_wmb(); ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX; spin_unlock(&dev->kvm->ring_lock); return 0; } static void coalesced_mmio_destructor(struct kvm_io_device *this) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); list_del(&dev->list); kfree(dev); } static const struct kvm_io_device_ops coalesced_mmio_ops = { .write = coalesced_mmio_write, .destructor = coalesced_mmio_destructor, }; int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) return -ENOMEM; kvm->coalesced_mmio_ring = page_address(page); /* * We're using this spinlock to sync access to the coalesced ring. * The list doesn't need its own lock since device registration and * unregistration should only happen when kvm->slots_lock is held. */ spin_lock_init(&kvm->ring_lock); INIT_LIST_HEAD(&kvm->coalesced_zones); return 0; } void kvm_coalesced_mmio_free(struct kvm *kvm) { if (kvm->coalesced_mmio_ring) free_page((unsigned long)kvm->coalesced_mmio_ring); } int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { int ret; struct kvm_coalesced_mmio_dev *dev; if (zone->pio != 1 && zone->pio != 0) return -EINVAL; dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops); dev->kvm = kvm; dev->zone = *zone; mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, zone->addr, zone->size, &dev->dev); if (ret < 0) goto out_free_dev; list_add_tail(&dev->list, &kvm->coalesced_zones); mutex_unlock(&kvm->slots_lock); return 0; out_free_dev: mutex_unlock(&kvm->slots_lock); kfree(dev); return ret; } int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { struct kvm_coalesced_mmio_dev *dev, *tmp; int r; if (zone->pio != 1 && zone->pio != 0) return -EINVAL; mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) { if (zone->pio == dev->zone.pio && coalesced_mmio_in_range(dev, zone->addr, zone->size)) { r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); /* * On failure, unregister destroys all devices on the * bus, including the target device. There's no need * to restart the walk as there aren't any zones left. */ if (r) break; } } mutex_unlock(&kvm->slots_lock); /* * Ignore the result of kvm_io_bus_unregister_dev(), from userspace's * perspective, the coalesced MMIO is most definitely unregistered. */ return 0; } |
| 17 17 122 122 121 3 3 122 122 122 123 246 245 246 116 116 115 244 245 117 244 236 237 122 245 243 2 2 2 244 246 244 247 243 246 245 243 245 246 247 2 2 2 2 261 260 2 2 2 262 262 197 262 263 262 262 263 263 260 262 263 261 263 263 263 263 261 17 261 17 261 261 263 259 246 106 106 263 2 262 262 1 238 116 243 246 244 246 116 116 116 1 116 260 263 263 262 261 247 2 246 262 2 2 2 2 2 263 245 247 1 116 106 245 260 246 263 2 262 2 2 2 241 98 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/sprintf.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #include <linux/notifier.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <asm/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); noinline static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); noinline static long long simple_strntoll(const char *cp, char **endp, unsigned int base, size_t max_chars) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, endp, base, max_chars - 1); return simple_strntoull(cp, endp, base, max_chars); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(SIGN == 1); static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static bool filled_random_ptr_key __read_mostly; static siphash_key_t ptr_key __read_mostly; static int fill_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Pairs with smp_rmb() before reading ptr_key. */ smp_wmb(); WRITE_ONCE(filled_random_ptr_key, true); return NOTIFY_DONE; } static int __init vsprintf_init_hashval(void) { static struct notifier_block fill_ptr_key_nb = { .notifier_call = fill_ptr_key }; execute_with_initialized_rng(&fill_ptr_key_nb); return 0; } subsys_initcall(vsprintf_init_hashval) /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (!READ_ONCE(filled_random_ptr_key)) return -EBUSY; /* Pairs with smp_wmb() after writing ptr_key. */ smp_rmb(); #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_hardirq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev_is_partition(bdev)) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev_partno(bdev), spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = number(p, pend, res->start, *specp); if (res->start != res->end) { *p++ = '-'; p = number(p, pend, res->end, *specp); } } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); bool first = true; int rbot, rtop; if (check_pointer(&buf, end, bitmap, spec)) return buf; for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) { if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rtop == rbot + 1) continue; if (buf < end) *buf = '-'; buf = number(++buf, end, rtop - 1, default_dec_spec); } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; u32 orig, val; if (fmt[1] != 'c' || fmt[2] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); val = orig & ~BIT(31); for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> (i * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } *p++ = ' '; strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian"); p += strlen(p); *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; buf = number(buf, end, flags, default_flag_spec); if (buf < end) *buf = '('; buf++; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } if (buf < end) *buf = ')'; buf++; return buf; } static char *format_page_type(char *buf, char *end, unsigned int page_type) { buf = number(buf, end, page_type, default_flag_spec); if (buf < end) *buf = '('; buf++; if (page_type_has_type(page_type)) buf = format_flags(buf, end, ~page_type, pagetype_names); if (buf < end) *buf = ')'; buf++; return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 't': return format_page_type(buf, end, *(unsigned int *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* Used for Rust formatting ('%pA'). */ char *rust_fmt_argument(char *buf, char *end, void *ptr); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. * * There is also a '%pA' format specifier, but it is only intended to be used * from Rust code to format core::fmt::Arguments. Do *not* use it from C. * See rust/kernel/print.rs for details. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_string(buf, end, ptr, spec, fmt); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'A': if (!IS_ENABLED(CONFIG_RUST)) { WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); return error_string(buf, end, "(%pA?)", spec); } return rust_fmt_argument(buf, end, ptr); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; fallthrough; case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; break; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ fallthrough; default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; if (unlikely(!size)) return 0; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; return size - 1; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); /** * bprintf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of words(u32) written * into @bin_buf. */ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = vbin_printf(bin_buf, size, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL_GPL(bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) __set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ __clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && !isodigit(digit)) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, &next, base, field_width >= 0 ? field_width : INT_MAX); else val.u = simple_strntoull(str, &next, base, field_width >= 0 ? field_width : INT_MAX); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 219 215 214 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> /* percpu_counter batch for local add or sub */ #define PERCPU_COUNTER_LOCAL_BATCH INT_MAX #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key); #define percpu_counter_init_many(fbc, value, gfp, nr_counters) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init_many(fbc, value, gfp, nr_counters,\ &__key); \ }) #define percpu_counter_init(fbc, value, gfp) \ percpu_counter_init_many(fbc, value, gfp, 1) void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters); static inline void percpu_counter_destroy(struct percpu_counter *fbc) { percpu_counter_destroy_many(fbc, 1); } void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline bool percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) { return __percpu_counter_limited_add(fbc, limit, amount, percpu_counter_batch); } /* * With percpu_counter_add_local() and percpu_counter_sub_local(), counts * are accumulated in local per cpu counter and not in fbc->count until * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter * write efficient. * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be * used to add up the counts from each CPU to account for all the local * counts. So percpu_counter_add_local() and percpu_counter_sub_local() * should be used when a counter is updated frequently and read rarely. */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters) { u32 i; for (i = 0; i < nr_counters; i++) fbc[i].count = amount; return 0; } static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { return percpu_counter_init_many(fbc, amount, gfp, 1); } static inline void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { unsigned long flags; local_irq_save(flags); fbc->count += amount; local_irq_restore(flags); } static inline bool percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) { unsigned long flags; bool good = false; s64 count; if (amount == 0) return true; local_irq_save(flags); count = fbc->count + amount; if ((amount > 0 && count <= limit) || (amount < 0 && count >= limit)) { fbc->count = count; good = true; } local_irq_restore(flags); return good; } /* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, amount); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } static inline void percpu_counter_sync(struct percpu_counter *fbc) { } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } static inline void percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_local(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */ |
| 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/signal.c * * Copyright (C) 1995-2009 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/cache.h> #include <linux/compat.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/freezer.h> #include <linux/stddef.h> #include <linux/uaccess.h> #include <linux/sizes.h> #include <linux/string.h> #include <linux/ratelimit.h> #include <linux/rseq.h> #include <linux/syscalls.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/elf.h> #include <asm/exception.h> #include <asm/cacheflush.h> #include <asm/ucontext.h> #include <asm/unistd.h> #include <asm/fpsimd.h> #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/signal32.h> #include <asm/traps.h> #include <asm/vdso.h> /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ struct rt_sigframe { struct siginfo info; struct ucontext uc; }; struct frame_record { u64 fp; u64 lr; }; struct rt_sigframe_user_layout { struct rt_sigframe __user *sigframe; struct frame_record __user *next_frame; unsigned long size; /* size of allocated sigframe data */ unsigned long limit; /* largest allowed size */ unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; unsigned long tpidr2_offset; unsigned long za_offset; unsigned long zt_offset; unsigned long fpmr_offset; unsigned long extra_offset; unsigned long end_offset; }; #define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16) #define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16) #define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16) static void init_user_layout(struct rt_sigframe_user_layout *user) { const size_t reserved_size = sizeof(user->sigframe->uc.uc_mcontext.__reserved); memset(user, 0, sizeof(*user)); user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved); user->limit = user->size + reserved_size; user->limit -= TERMINATOR_SIZE; user->limit -= EXTRA_CONTEXT_SIZE; /* Reserve space for extension and terminator ^ */ } static size_t sigframe_size(struct rt_sigframe_user_layout const *user) { return round_up(max(user->size, sizeof(struct rt_sigframe)), 16); } /* * Sanity limit on the approximate maximum size of signal frame we'll * try to generate. Stack alignment padding and the frame record are * not taken into account. This limit is not a guarantee and is * NOT ABI. */ #define SIGFRAME_MAXSZ SZ_256K static int __sigframe_alloc(struct rt_sigframe_user_layout *user, unsigned long *offset, size_t size, bool extend) { size_t padded_size = round_up(size, 16); if (padded_size > user->limit - user->size && !user->extra_offset && extend) { int ret; user->limit += EXTRA_CONTEXT_SIZE; ret = __sigframe_alloc(user, &user->extra_offset, sizeof(struct extra_context), false); if (ret) { user->limit -= EXTRA_CONTEXT_SIZE; return ret; } /* Reserve space for the __reserved[] terminator */ user->size += TERMINATOR_SIZE; /* * Allow expansion up to SIGFRAME_MAXSZ, ensuring space for * the terminator: */ user->limit = SIGFRAME_MAXSZ - TERMINATOR_SIZE; } /* Still not enough space? Bad luck! */ if (padded_size > user->limit - user->size) return -ENOMEM; *offset = user->size; user->size += padded_size; return 0; } /* * Allocate space for an optional record of <size> bytes in the user * signal frame. The offset from the signal frame base address to the * allocated block is assigned to *offset. */ static int sigframe_alloc(struct rt_sigframe_user_layout *user, unsigned long *offset, size_t size) { return __sigframe_alloc(user, offset, size, true); } /* Allocate the null terminator record and prevent further allocations */ static int sigframe_alloc_end(struct rt_sigframe_user_layout *user) { int ret; /* Un-reserve the space reserved for the terminator: */ user->limit += TERMINATOR_SIZE; ret = sigframe_alloc(user, &user->end_offset, sizeof(struct _aarch64_ctx)); if (ret) return ret; /* Prevent further allocation: */ user->limit = user->size; return 0; } static void __user *apply_user_offset( struct rt_sigframe_user_layout const *user, unsigned long offset) { char __user *base = (char __user *)user->sigframe; return base + offset; } struct user_ctxs { struct fpsimd_context __user *fpsimd; u32 fpsimd_size; struct sve_context __user *sve; u32 sve_size; struct tpidr2_context __user *tpidr2; u32 tpidr2_size; struct za_context __user *za; u32 za_size; struct zt_context __user *zt; u32 zt_size; struct fpmr_context __user *fpmr; u32 fpmr_size; }; static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) { struct user_fpsimd_state const *fpsimd = ¤t->thread.uw.fpsimd_state; int err; /* copy the FP and status/control registers */ err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs)); __put_user_error(fpsimd->fpsr, &ctx->fpsr, err); __put_user_error(fpsimd->fpcr, &ctx->fpcr, err); /* copy the magic/size information */ __put_user_error(FPSIMD_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(struct fpsimd_context), &ctx->head.size, err); return err ? -EFAULT : 0; } static int restore_fpsimd_context(struct user_ctxs *user) { struct user_fpsimd_state fpsimd; int err = 0; /* check the size information */ if (user->fpsimd_size != sizeof(struct fpsimd_context)) return -EINVAL; /* copy the FP and status/control registers */ err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs), sizeof(fpsimd.vregs)); __get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err); __get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err); clear_thread_flag(TIF_SVE); current->thread.fp_type = FP_STATE_FPSIMD; /* load the hardware registers from the fpsimd_state structure */ if (!err) fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } static int preserve_fpmr_context(struct fpmr_context __user *ctx) { int err = 0; current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR); __put_user_error(FPMR_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err); return err; } static int restore_fpmr_context(struct user_ctxs *user) { u64 fpmr; int err = 0; if (user->fpmr_size != sizeof(*user->fpmr)) return -EINVAL; __get_user_error(fpmr, &user->fpmr->fpmr, err); if (!err) write_sysreg_s(fpmr, SYS_FPMR); return err; } #ifdef CONFIG_ARM64_SVE static int preserve_sve_context(struct sve_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; u16 flags = 0; unsigned int vl = task_get_sve_vl(current); unsigned int vq = 0; if (thread_sm_enabled(¤t->thread)) { vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); flags |= SVE_SIG_FLAG_SM; } else if (current->thread.fp_type == FP_STATE_SVE) { vq = sve_vq_from_vl(vl); } memset(reserved, 0, sizeof(reserved)); __put_user_error(SVE_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); __put_user_error(flags, &ctx->flags, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) { /* * This assumes that the SVE state has already been saved to * the task struct by calling the function * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET, current->thread.sve_state, SVE_SIG_REGS_SIZE(vq)); } return err ? -EFAULT : 0; } static int restore_sve_fpsimd_context(struct user_ctxs *user) { int err = 0; unsigned int vl, vq; struct user_fpsimd_state fpsimd; u16 user_vl, flags; if (user->sve_size < sizeof(*user->sve)) return -EINVAL; __get_user_error(user_vl, &(user->sve->vl), err); __get_user_error(flags, &(user->sve->flags), err); if (err) return err; if (flags & SVE_SIG_FLAG_SM) { if (!system_supports_sme()) return -EINVAL; vl = task_get_sme_vl(current); } else { /* * A SME only system use SVE for streaming mode so can * have a SVE formatted context with a zero VL and no * payload data. */ if (!system_supports_sve() && !system_supports_sme()) return -EINVAL; vl = task_get_sve_vl(current); } if (user_vl != vl) return -EINVAL; if (user->sve_size == sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); current->thread.svcr &= ~SVCR_SM_MASK; current->thread.fp_type = FP_STATE_FPSIMD; goto fpsimd_only; } vq = sve_vq_from_vl(vl); if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq)) return -EINVAL; /* * Careful: we are about __copy_from_user() directly into * thread.sve_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ sve_alloc(current, true); if (!current->thread.sve_state) { clear_thread_flag(TIF_SVE); return -ENOMEM; } err = __copy_from_user(current->thread.sve_state, (char __user const *)user->sve + SVE_SIG_REGS_OFFSET, SVE_SIG_REGS_SIZE(vq)); if (err) return -EFAULT; if (flags & SVE_SIG_FLAG_SM) current->thread.svcr |= SVCR_SM_MASK; else set_thread_flag(TIF_SVE); current->thread.fp_type = FP_STATE_SVE; fpsimd_only: /* copy the FP and status/control registers */ /* restore_sigframe() already checked that user->fpsimd != NULL. */ err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs, sizeof(fpsimd.vregs)); __get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err); __get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err); /* load the hardware registers from the fpsimd_state structure */ if (!err) fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } #else /* ! CONFIG_ARM64_SVE */ static int restore_sve_fpsimd_context(struct user_ctxs *user) { WARN_ON_ONCE(1); return -EINVAL; } /* Turn any non-optimised out attempts to use this into a link error: */ extern int preserve_sve_context(void __user *ctx); #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int preserve_tpidr2_context(struct tpidr2_context __user *ctx) { int err = 0; current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); __put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err); return err; } static int restore_tpidr2_context(struct user_ctxs *user) { u64 tpidr2_el0; int err = 0; if (user->tpidr2_size != sizeof(*user->tpidr2)) return -EINVAL; __get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err); if (!err) write_sysreg_s(tpidr2_el0, SYS_TPIDR2_EL0); return err; } static int preserve_za_context(struct za_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; unsigned int vl = task_get_sme_vl(current); unsigned int vq; if (thread_za_enabled(¤t->thread)) vq = sve_vq_from_vl(vl); else vq = 0; memset(reserved, 0, sizeof(reserved)); __put_user_error(ZA_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) { /* * This assumes that the ZA state has already been saved to * the task struct by calling the function * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, current->thread.sme_state, ZA_SIG_REGS_SIZE(vq)); } return err ? -EFAULT : 0; } static int restore_za_context(struct user_ctxs *user) { int err = 0; unsigned int vq; u16 user_vl; if (user->za_size < sizeof(*user->za)) return -EINVAL; __get_user_error(user_vl, &(user->za->vl), err); if (err) return err; if (user_vl != task_get_sme_vl(current)) return -EINVAL; if (user->za_size == sizeof(*user->za)) { current->thread.svcr &= ~SVCR_ZA_MASK; return 0; } vq = sve_vq_from_vl(user_vl); if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq)) return -EINVAL; /* * Careful: we are about __copy_from_user() directly into * thread.sme_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ sme_alloc(current, true); if (!current->thread.sme_state) { current->thread.svcr &= ~SVCR_ZA_MASK; clear_thread_flag(TIF_SME); return -ENOMEM; } err = __copy_from_user(current->thread.sme_state, (char __user const *)user->za + ZA_SIG_REGS_OFFSET, ZA_SIG_REGS_SIZE(vq)); if (err) return -EFAULT; set_thread_flag(TIF_SME); current->thread.svcr |= SVCR_ZA_MASK; return 0; } static int preserve_zt_context(struct zt_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; if (WARN_ON(!thread_za_enabled(¤t->thread))) return -EINVAL; memset(reserved, 0, sizeof(reserved)); __put_user_error(ZT_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16), &ctx->head.size, err); __put_user_error(1, &ctx->nregs, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); /* * This assumes that the ZT state has already been saved to * the task struct by calling the function * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET, thread_zt_state(¤t->thread), ZT_SIG_REGS_SIZE(1)); return err ? -EFAULT : 0; } static int restore_zt_context(struct user_ctxs *user) { int err; u16 nregs; /* ZA must be restored first for this check to be valid */ if (!thread_za_enabled(¤t->thread)) return -EINVAL; if (user->zt_size != ZT_SIG_CONTEXT_SIZE(1)) return -EINVAL; if (__copy_from_user(&nregs, &(user->zt->nregs), sizeof(nregs))) return -EFAULT; if (nregs != 1) return -EINVAL; /* * Careful: we are about __copy_from_user() directly into * thread.zt_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch ZT in thread state */ err = __copy_from_user(thread_zt_state(¤t->thread), (char __user const *)user->zt + ZT_SIG_REGS_OFFSET, ZT_SIG_REGS_SIZE(1)); if (err) return -EFAULT; return 0; } #else /* ! CONFIG_ARM64_SME */ /* Turn any non-optimised out attempts to use these into a link error: */ extern int preserve_tpidr2_context(void __user *ctx); extern int restore_tpidr2_context(struct user_ctxs *user); extern int preserve_za_context(void __user *ctx); extern int restore_za_context(struct user_ctxs *user); extern int preserve_zt_context(void __user *ctx); extern int restore_zt_context(struct user_ctxs *user); #endif /* ! CONFIG_ARM64_SME */ static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) { struct sigcontext __user *const sc = &sf->uc.uc_mcontext; struct _aarch64_ctx __user *head; char __user *base = (char __user *)&sc->__reserved; size_t offset = 0; size_t limit = sizeof(sc->__reserved); bool have_extra_context = false; char const __user *const sfp = (char const __user *)sf; user->fpsimd = NULL; user->sve = NULL; user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; user->fpmr = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; while (1) { int err = 0; u32 magic, size; char const __user *userp; struct extra_context const __user *extra; u64 extra_datap; u32 extra_size; struct _aarch64_ctx const __user *end; u32 end_magic, end_size; if (limit - offset < sizeof(*head)) goto invalid; if (!IS_ALIGNED(offset, 16)) goto invalid; head = (struct _aarch64_ctx __user *)(base + offset); __get_user_error(magic, &head->magic, err); __get_user_error(size, &head->size, err); if (err) return err; if (limit - offset < size) goto invalid; switch (magic) { case 0: if (size) goto invalid; goto done; case FPSIMD_MAGIC: if (!system_supports_fpsimd()) goto invalid; if (user->fpsimd) goto invalid; user->fpsimd = (struct fpsimd_context __user *)head; user->fpsimd_size = size; break; case ESR_MAGIC: /* ignore */ break; case SVE_MAGIC: if (!system_supports_sve() && !system_supports_sme()) goto invalid; if (user->sve) goto invalid; user->sve = (struct sve_context __user *)head; user->sve_size = size; break; case TPIDR2_MAGIC: if (!system_supports_tpidr2()) goto invalid; if (user->tpidr2) goto invalid; user->tpidr2 = (struct tpidr2_context __user *)head; user->tpidr2_size = size; break; case ZA_MAGIC: if (!system_supports_sme()) goto invalid; if (user->za) goto invalid; user->za = (struct za_context __user *)head; user->za_size = size; break; case ZT_MAGIC: if (!system_supports_sme2()) goto invalid; if (user->zt) goto invalid; user->zt = (struct zt_context __user *)head; user->zt_size = size; break; case FPMR_MAGIC: if (!system_supports_fpmr()) goto invalid; if (user->fpmr) goto invalid; user->fpmr = (struct fpmr_context __user *)head; user->fpmr_size = size; break; case EXTRA_MAGIC: if (have_extra_context) goto invalid; if (size < sizeof(*extra)) goto invalid; userp = (char const __user *)head; extra = (struct extra_context const __user *)userp; userp += size; __get_user_error(extra_datap, &extra->datap, err); __get_user_error(extra_size, &extra->size, err); if (err) return err; /* Check for the dummy terminator in __reserved[]: */ if (limit - offset - size < TERMINATOR_SIZE) goto invalid; end = (struct _aarch64_ctx const __user *)userp; userp += TERMINATOR_SIZE; __get_user_error(end_magic, &end->magic, err); __get_user_error(end_size, &end->size, err); if (err) return err; if (end_magic || end_size) goto invalid; /* Prevent looping/repeated parsing of extra_context */ have_extra_context = true; base = (__force void __user *)extra_datap; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; if (!IS_ALIGNED(extra_size, 16)) goto invalid; if (base != userp) goto invalid; /* Reject "unreasonably large" frames: */ if (extra_size > sfp + SIGFRAME_MAXSZ - userp) goto invalid; /* * Ignore trailing terminator in __reserved[] * and start parsing extra data: */ offset = 0; limit = extra_size; if (!access_ok(base, limit)) goto invalid; continue; default: goto invalid; } if (size < sizeof(*head)) goto invalid; if (limit - offset < size) goto invalid; offset += size; } done: return 0; invalid: return -EINVAL; } static int restore_sigframe(struct pt_regs *regs, struct rt_sigframe __user *sf) { sigset_t set; int i, err; struct user_ctxs user; err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set)); if (err == 0) set_current_blocked(&set); for (i = 0; i < 31; i++) __get_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i], err); __get_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err); __get_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err); __get_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err); /* * Avoid sys_rt_sigreturn() restarting. */ forget_syscall(regs); err |= !valid_user_regs(®s->user_regs, current); if (err == 0) err = parse_user_sigframe(&user, sf); if (err == 0 && system_supports_fpsimd()) { if (!user.fpsimd) return -EINVAL; if (user.sve) err = restore_sve_fpsimd_context(&user); else err = restore_fpsimd_context(&user); } if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user); if (err == 0 && system_supports_fpmr() && user.fpmr) err = restore_fpmr_context(&user); if (err == 0 && system_supports_sme() && user.za) err = restore_za_context(&user); if (err == 0 && system_supports_sme2() && user.zt) err = restore_zt_context(&user); return err; } SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; /* * Since we stacked the signal on a 128-bit boundary, then 'sp' should * be word aligned here. */ if (regs->sp & 15) goto badframe; frame = (struct rt_sigframe __user *)regs->sp; if (!access_ok(frame, sizeof (*frame))) goto badframe; if (restore_sigframe(regs, frame)) goto badframe; if (restore_altstack(&frame->uc.uc_stack)) goto badframe; return regs->regs[0]; badframe: arm64_notify_segfault(regs->sp); return 0; } /* * Determine the layout of optional records in the signal frame * * add_all: if true, lays out the biggest possible signal frame for * this task; otherwise, generates a layout for the current state * of the task. */ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, bool add_all) { int err; if (system_supports_fpsimd()) { err = sigframe_alloc(user, &user->fpsimd_offset, sizeof(struct fpsimd_context)); if (err) return err; } /* fault information, if valid */ if (add_all || current->thread.fault_code) { err = sigframe_alloc(user, &user->esr_offset, sizeof(struct esr_context)); if (err) return err; } if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; if (add_all || current->thread.fp_type == FP_STATE_SVE || thread_sm_enabled(¤t->thread)) { int vl = max(sve_max_vl(), sme_max_vl()); if (!add_all) vl = thread_get_cur_vl(¤t->thread); vq = sve_vq_from_vl(vl); } err = sigframe_alloc(user, &user->sve_offset, SVE_SIG_CONTEXT_SIZE(vq)); if (err) return err; } if (system_supports_tpidr2()) { err = sigframe_alloc(user, &user->tpidr2_offset, sizeof(struct tpidr2_context)); if (err) return err; } if (system_supports_sme()) { unsigned int vl; unsigned int vq = 0; if (add_all) vl = sme_max_vl(); else vl = task_get_sme_vl(current); if (thread_za_enabled(¤t->thread)) vq = sve_vq_from_vl(vl); err = sigframe_alloc(user, &user->za_offset, ZA_SIG_CONTEXT_SIZE(vq)); if (err) return err; } if (system_supports_sme2()) { if (add_all || thread_za_enabled(¤t->thread)) { err = sigframe_alloc(user, &user->zt_offset, ZT_SIG_CONTEXT_SIZE(1)); if (err) return err; } } if (system_supports_fpmr()) { err = sigframe_alloc(user, &user->fpmr_offset, sizeof(struct fpmr_context)); if (err) return err; } return sigframe_alloc_end(user); } static int setup_sigframe(struct rt_sigframe_user_layout *user, struct pt_regs *regs, sigset_t *set) { int i, err = 0; struct rt_sigframe __user *sf = user->sigframe; /* set up the stack frame for unwinding */ __put_user_error(regs->regs[29], &user->next_frame->fp, err); __put_user_error(regs->regs[30], &user->next_frame->lr, err); for (i = 0; i < 31; i++) __put_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i], err); __put_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err); __put_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err); __put_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err); __put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); if (err == 0 && system_supports_fpsimd()) { struct fpsimd_context __user *fpsimd_ctx = apply_user_offset(user, user->fpsimd_offset); err |= preserve_fpsimd_context(fpsimd_ctx); } /* fault information, if valid */ if (err == 0 && user->esr_offset) { struct esr_context __user *esr_ctx = apply_user_offset(user, user->esr_offset); __put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err); __put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err); __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); } /* Scalable Vector Extension state (including streaming), if present */ if ((system_supports_sve() || system_supports_sme()) && err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = apply_user_offset(user, user->sve_offset); err |= preserve_sve_context(sve_ctx); } /* TPIDR2 if supported */ if (system_supports_tpidr2() && err == 0) { struct tpidr2_context __user *tpidr2_ctx = apply_user_offset(user, user->tpidr2_offset); err |= preserve_tpidr2_context(tpidr2_ctx); } /* FPMR if supported */ if (system_supports_fpmr() && err == 0) { struct fpmr_context __user *fpmr_ctx = apply_user_offset(user, user->fpmr_offset); err |= preserve_fpmr_context(fpmr_ctx); } /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = apply_user_offset(user, user->za_offset); err |= preserve_za_context(za_ctx); } /* ZT state if present */ if (system_supports_sme2() && err == 0 && user->zt_offset) { struct zt_context __user *zt_ctx = apply_user_offset(user, user->zt_offset); err |= preserve_zt_context(zt_ctx); } if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp = apply_user_offset(user, user->extra_offset); struct extra_context __user *extra; struct _aarch64_ctx __user *end; u64 extra_datap; u32 extra_size; extra = (struct extra_context __user *)userp; userp += EXTRA_CONTEXT_SIZE; end = (struct _aarch64_ctx __user *)userp; userp += TERMINATOR_SIZE; /* * extra_datap is just written to the signal frame. * The value gets cast back to a void __user * * during sigreturn. */ extra_datap = (__force u64)userp; extra_size = sfp + round_up(user->size, 16) - userp; __put_user_error(EXTRA_MAGIC, &extra->head.magic, err); __put_user_error(EXTRA_CONTEXT_SIZE, &extra->head.size, err); __put_user_error(extra_datap, &extra->datap, err); __put_user_error(extra_size, &extra->size, err); /* Add the terminator */ __put_user_error(0, &end->magic, err); __put_user_error(0, &end->size, err); } /* set the "end" magic */ if (err == 0) { struct _aarch64_ctx __user *end = apply_user_offset(user, user->end_offset); __put_user_error(0, &end->magic, err); __put_user_error(0, &end->size, err); } return err; } static int get_sigframe(struct rt_sigframe_user_layout *user, struct ksignal *ksig, struct pt_regs *regs) { unsigned long sp, sp_top; int err; init_user_layout(user); err = setup_sigframe_layout(user, false); if (err) return err; sp = sp_top = sigsp(regs->sp, ksig); sp = round_down(sp - sizeof(struct frame_record), 16); user->next_frame = (struct frame_record __user *)sp; sp = round_down(sp, 16) - sigframe_size(user); user->sigframe = (struct rt_sigframe __user *)sp; /* * Check that we can actually write to the signal frame. */ if (!access_ok(user->sigframe, sp_top - sp)) return -EFAULT; return 0; } static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, struct rt_sigframe_user_layout *user, int usig) { __sigrestore_t sigtramp; regs->regs[0] = usig; regs->sp = (unsigned long)user->sigframe; regs->regs[29] = (unsigned long)&user->next_frame->fp; regs->pc = (unsigned long)ka->sa.sa_handler; /* * Signal delivery is a (wacky) indirect function call in * userspace, so simulate the same setting of BTYPE as a BLR * <register containing the signal handler entry point>. * Signal delivery to a location in a PROT_BTI guarded page * that is not a function entry point will now trigger a * SIGILL in userspace. * * If the signal handler entry point is not in a PROT_BTI * guarded page, this is harmless. */ if (system_supports_bti()) { regs->pstate &= ~PSR_BTYPE_MASK; regs->pstate |= PSR_BTYPE_C; } /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT; /* Signal handlers are invoked with ZA and streaming mode disabled */ if (system_supports_sme()) { /* * If we were in streaming mode the saved register * state was SVE but we will exit SM and use the * FPSIMD register state - flush the saved FPSIMD * register state in case it gets loaded. */ if (current->thread.svcr & SVCR_SM_MASK) { memset(¤t->thread.uw.fpsimd_state, 0, sizeof(current->thread.uw.fpsimd_state)); current->thread.fp_type = FP_STATE_FPSIMD; } current->thread.svcr &= ~(SVCR_ZA_MASK | SVCR_SM_MASK); sme_smstop(); } if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); regs->regs[30] = (unsigned long)sigtramp; } static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe_user_layout user; struct rt_sigframe __user *frame; int err = 0; fpsimd_signal_preserve_current_state(); if (get_sigframe(&user, ksig, regs)) return 1; frame = user.sigframe; __put_user_error(0, &frame->uc.uc_flags, err); __put_user_error(NULL, &frame->uc.uc_link, err); err |= __save_altstack(&frame->uc.uc_stack, regs->sp); err |= setup_sigframe(&user, regs, set); if (err == 0) { setup_return(regs, &ksig->ka, &user, usig); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { err |= copy_siginfo_to_user(&frame->info, &ksig->info); regs->regs[1] = (unsigned long)&frame->info; regs->regs[2] = (unsigned long)&frame->uc; } } return err; } static void setup_restart_syscall(struct pt_regs *regs) { if (is_compat_task()) compat_setup_restart_syscall(regs); else regs->regs[8] = __NR_restart_syscall; } /* * OK, we're invoking a handler */ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { sigset_t *oldset = sigmask_to_save(); int usig = ksig->sig; int ret; rseq_signal_deliver(ksig, regs); /* * Set up the stack frame */ if (is_compat_task()) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) ret = compat_setup_rt_frame(usig, ksig, oldset, regs); else ret = compat_setup_frame(usig, ksig, oldset, regs); } else { ret = setup_rt_frame(usig, ksig, oldset, regs); } /* * Check that the resulting registers are actually sane. */ ret |= !valid_user_regs(®s->user_regs, current); /* Step into the signal handler if we are stepping */ signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. * * Note that we go through the signals twice: once to check the signals that * the kernel can handle, and then we build all the user-level signal handling * stack-frames in one go after that. */ void do_signal(struct pt_regs *regs) { unsigned long continue_addr = 0, restart_addr = 0; int retval = 0; struct ksignal ksig; bool syscall = in_syscall(regs); /* * If we were from a system call, check for system call restarting... */ if (syscall) { continue_addr = regs->pc; restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4); retval = regs->regs[0]; /* * Avoid additional syscall restarting via ret_to_user. */ forget_syscall(regs); /* * Prepare for system call restart. We do this here so that a * debugger will see the already changed PC. */ switch (retval) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTART_RESTARTBLOCK: regs->regs[0] = regs->orig_x0; regs->pc = restart_addr; break; } } /* * Get the signal to deliver. When running under ptrace, at this point * the debugger may change all of our registers. */ if (get_signal(&ksig)) { /* * Depending on the signal settings, we may need to revert the * decision to restart the system call, but skip this if a * debugger has chosen to restart at a different PC. */ if (regs->pc == restart_addr && (retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK || (retval == -ERESTARTSYS && !(ksig.ka.sa.sa_flags & SA_RESTART)))) { syscall_set_return_value(current, regs, -EINTR, 0); regs->pc = continue_addr; } handle_signal(&ksig, regs); return; } /* * Handle restarting a different system call. As above, if a debugger * has chosen to restart at a different PC, ignore the restart. */ if (syscall && regs->pc == restart_addr) { if (retval == -ERESTART_RESTARTBLOCK) setup_restart_syscall(regs); user_rewind_single_step(current); } restore_saved_sigmask(); } unsigned long __ro_after_init signal_minsigstksz; /* * Determine the stack space required for guaranteed signal devliery. * This function is used to populate AT_MINSIGSTKSZ at process startup. * cpufeatures setup is assumed to be complete. */ void __init minsigstksz_setup(void) { struct rt_sigframe_user_layout user; init_user_layout(&user); /* * If this fails, SIGFRAME_MAXSZ needs to be enlarged. It won't * be big enough, but it's our best guess: */ if (WARN_ON(setup_sigframe_layout(&user, true))) return; signal_minsigstksz = sigframe_size(&user) + round_up(sizeof(struct frame_record), 16) + 16; /* max alignment padding */ } /* * Compile-time assertions for siginfo_t offsets. Check NSIG* as well, as * changes likely come with new fields that should be added below. */ static_assert(NSIGILL == 11); static_assert(NSIGFPE == 15); static_assert(NSIGSEGV == 10); static_assert(NSIGBUS == 5); static_assert(NSIGTRAP == 6); static_assert(NSIGCHLD == 6); static_assert(NSIGSYS == 2); static_assert(sizeof(siginfo_t) == 128); static_assert(__alignof__(siginfo_t) == 8); static_assert(offsetof(siginfo_t, si_signo) == 0x00); static_assert(offsetof(siginfo_t, si_errno) == 0x04); static_assert(offsetof(siginfo_t, si_code) == 0x08); static_assert(offsetof(siginfo_t, si_pid) == 0x10); static_assert(offsetof(siginfo_t, si_uid) == 0x14); static_assert(offsetof(siginfo_t, si_tid) == 0x10); static_assert(offsetof(siginfo_t, si_overrun) == 0x14); static_assert(offsetof(siginfo_t, si_status) == 0x18); static_assert(offsetof(siginfo_t, si_utime) == 0x20); static_assert(offsetof(siginfo_t, si_stime) == 0x28); static_assert(offsetof(siginfo_t, si_value) == 0x18); static_assert(offsetof(siginfo_t, si_int) == 0x18); static_assert(offsetof(siginfo_t, si_ptr) == 0x18); static_assert(offsetof(siginfo_t, si_addr) == 0x10); static_assert(offsetof(siginfo_t, si_addr_lsb) == 0x18); static_assert(offsetof(siginfo_t, si_lower) == 0x20); static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x18); static_assert(offsetof(siginfo_t, si_call_addr) == 0x10); static_assert(offsetof(siginfo_t, si_syscall) == 0x18); static_assert(offsetof(siginfo_t, si_arch) == 0x1c); |
| 32 32 215 120 120 236 239 236 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock LSM - Filesystem management and hooks * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2021-2022 Microsoft Corporation * Copyright © 2022 Günther Noack <gnoack3000@gmail.com> * Copyright © 2023-2024 Google LLC */ #include <asm/ioctls.h> #include <kunit/test.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bits.h> #include <linux/compiler_types.h> #include <linux/dcache.h> #include <linux/err.h> #include <linux/falloc.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/lsm_hooks.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/path.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/workqueue.h> #include <uapi/linux/fiemap.h> #include <uapi/linux/landlock.h> #include "common.h" #include "cred.h" #include "fs.h" #include "limits.h" #include "object.h" #include "ruleset.h" #include "setup.h" /* Underlying object management */ static void release_inode(struct landlock_object *const object) __releases(object->lock) { struct inode *const inode = object->underobj; struct super_block *sb; if (!inode) { spin_unlock(&object->lock); return; } /* * Protects against concurrent use by hook_sb_delete() of the reference * to the underlying inode. */ object->underobj = NULL; /* * Makes sure that if the filesystem is concurrently unmounted, * hook_sb_delete() will wait for us to finish iput(). */ sb = inode->i_sb; atomic_long_inc(&landlock_superblock(sb)->inode_refs); spin_unlock(&object->lock); /* * Because object->underobj was not NULL, hook_sb_delete() and * get_inode_object() guarantee that it is safe to reset * landlock_inode(inode)->object while it is not NULL. It is therefore * not necessary to lock inode->i_lock. */ rcu_assign_pointer(landlock_inode(inode)->object, NULL); /* * Now, new rules can safely be tied to @inode with get_inode_object(). */ iput(inode); if (atomic_long_dec_and_test(&landlock_superblock(sb)->inode_refs)) wake_up_var(&landlock_superblock(sb)->inode_refs); } static const struct landlock_object_underops landlock_fs_underops = { .release = release_inode }; /* IOCTL helpers */ /** * is_masked_device_ioctl - Determine whether an IOCTL command is always * permitted with Landlock for device files. These commands can not be * restricted on device files by enforcing a Landlock policy. * * @cmd: The IOCTL command that is supposed to be run. * * By default, any IOCTL on a device file requires the * LANDLOCK_ACCESS_FS_IOCTL_DEV right. However, we blanket-permit some * commands, if: * * 1. The command is implemented in fs/ioctl.c's do_vfs_ioctl(), * not in f_ops->unlocked_ioctl() or f_ops->compat_ioctl(). * * 2. The command is harmless when invoked on devices. * * We also permit commands that do not make sense for devices, but where the * do_vfs_ioctl() implementation returns a more conventional error code. * * Any new IOCTL commands that are implemented in fs/ioctl.c's do_vfs_ioctl() * should be considered for inclusion here. * * Returns: true if the IOCTL @cmd can not be restricted with Landlock for * device files. */ static __attribute_const__ bool is_masked_device_ioctl(const unsigned int cmd) { switch (cmd) { /* * FIOCLEX, FIONCLEX, FIONBIO and FIOASYNC manipulate the FD's * close-on-exec and the file's buffered-IO and async flags. These * operations are also available through fcntl(2), and are * unconditionally permitted in Landlock. */ case FIOCLEX: case FIONCLEX: case FIONBIO: case FIOASYNC: /* * FIOQSIZE queries the size of a regular file, directory, or link. * * We still permit it, because it always returns -ENOTTY for * other file types. */ case FIOQSIZE: /* * FIFREEZE and FITHAW freeze and thaw the file system which the * given file belongs to. Requires CAP_SYS_ADMIN. * * These commands operate on the file system's superblock rather * than on the file itself. The same operations can also be * done through any other file or directory on the same file * system, so it is safe to permit these. */ case FIFREEZE: case FITHAW: /* * FS_IOC_FIEMAP queries information about the allocation of * blocks within a file. * * This IOCTL command only makes sense for regular files and is * not implemented by devices. It is harmless to permit. */ case FS_IOC_FIEMAP: /* * FIGETBSZ queries the file system's block size for a file or * directory. * * This command operates on the file system's superblock rather * than on the file itself. The same operation can also be done * through any other file or directory on the same file system, * so it is safe to permit it. */ case FIGETBSZ: /* * FICLONE, FICLONERANGE and FIDEDUPERANGE make files share * their underlying storage ("reflink") between source and * destination FDs, on file systems which support that. * * These IOCTL commands only apply to regular files * and are harmless to permit for device files. */ case FICLONE: case FICLONERANGE: case FIDEDUPERANGE: /* * FS_IOC_GETFSUUID and FS_IOC_GETFSSYSFSPATH both operate on * the file system superblock, not on the specific file, so * these operations are available through any other file on the * same file system as well. */ case FS_IOC_GETFSUUID: case FS_IOC_GETFSSYSFSPATH: return true; /* * FIONREAD, FS_IOC_GETFLAGS, FS_IOC_SETFLAGS, FS_IOC_FSGETXATTR and * FS_IOC_FSSETXATTR are forwarded to device implementations. */ /* * file_ioctl() commands (FIBMAP, FS_IOC_RESVSP, FS_IOC_RESVSP64, * FS_IOC_UNRESVSP, FS_IOC_UNRESVSP64 and FS_IOC_ZERO_RANGE) are * forwarded to device implementations, so not permitted. */ /* Other commands are guarded by the access right. */ default: return false; } } /* * is_masked_device_ioctl_compat - same as the helper above, but checking the * "compat" IOCTL commands. * * The IOCTL commands with special handling in compat-mode should behave the * same as their non-compat counterparts. */ static __attribute_const__ bool is_masked_device_ioctl_compat(const unsigned int cmd) { switch (cmd) { /* FICLONE is permitted, same as in the non-compat variant. */ case FICLONE: return true; #if defined(CONFIG_X86_64) /* * FS_IOC_RESVSP_32, FS_IOC_RESVSP64_32, FS_IOC_UNRESVSP_32, * FS_IOC_UNRESVSP64_32, FS_IOC_ZERO_RANGE_32: not blanket-permitted, * for consistency with their non-compat variants. */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: case FS_IOC_ZERO_RANGE_32: #endif /* * FS_IOC32_GETFLAGS, FS_IOC32_SETFLAGS are forwarded to their device * implementations. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: return false; default: return is_masked_device_ioctl(cmd); } } /* Ruleset management */ static struct landlock_object *get_inode_object(struct inode *const inode) { struct landlock_object *object, *new_object; struct landlock_inode_security *inode_sec = landlock_inode(inode); rcu_read_lock(); retry: object = rcu_dereference(inode_sec->object); if (object) { if (likely(refcount_inc_not_zero(&object->usage))) { rcu_read_unlock(); return object; } /* * We are racing with release_inode(), the object is going * away. Wait for release_inode(), then retry. */ spin_lock(&object->lock); spin_unlock(&object->lock); goto retry; } rcu_read_unlock(); /* * If there is no object tied to @inode, then create a new one (without * holding any locks). */ new_object = landlock_create_object(&landlock_fs_underops, inode); if (IS_ERR(new_object)) return new_object; /* * Protects against concurrent calls to get_inode_object() or * hook_sb_delete(). */ spin_lock(&inode->i_lock); if (unlikely(rcu_access_pointer(inode_sec->object))) { /* Someone else just created the object, bail out and retry. */ spin_unlock(&inode->i_lock); kfree(new_object); rcu_read_lock(); goto retry; } /* * @inode will be released by hook_sb_delete() on its superblock * shutdown, or by release_inode() when no more ruleset references the * related object. */ ihold(inode); rcu_assign_pointer(inode_sec->object, new_object); spin_unlock(&inode->i_lock); return new_object; } /* All access rights that can be tied to files. */ /* clang-format off */ #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE | \ LANDLOCK_ACCESS_FS_TRUNCATE | \ LANDLOCK_ACCESS_FS_IOCTL_DEV) /* clang-format on */ /* * @path: Should have been checked by get_path_from_fd(). */ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, access_mask_t access_rights) { int err; struct landlock_id id = { .type = LANDLOCK_KEY_INODE, }; /* Files only get access rights that make sense. */ if (!d_is_dir(path->dentry) && (access_rights | ACCESS_FILE) != ACCESS_FILE) return -EINVAL; if (WARN_ON_ONCE(ruleset->num_layers != 1)) return -EINVAL; /* Transforms relative access rights to absolute ones. */ access_rights |= LANDLOCK_MASK_ACCESS_FS & ~landlock_get_fs_access_mask(ruleset, 0); id.key.object = get_inode_object(d_backing_inode(path->dentry)); if (IS_ERR(id.key.object)) return PTR_ERR(id.key.object); mutex_lock(&ruleset->lock); err = landlock_insert_rule(ruleset, id, access_rights); mutex_unlock(&ruleset->lock); /* * No need to check for an error because landlock_insert_rule() * increments the refcount for the new object if needed. */ landlock_put_object(id.key.object); return err; } /* Access-control management */ /* * The lifetime of the returned rule is tied to @domain. * * Returns NULL if no rule is found or if @dentry is negative. */ static const struct landlock_rule * find_rule(const struct landlock_ruleset *const domain, const struct dentry *const dentry) { const struct landlock_rule *rule; const struct inode *inode; struct landlock_id id = { .type = LANDLOCK_KEY_INODE, }; /* Ignores nonexistent leafs. */ if (d_is_negative(dentry)) return NULL; inode = d_backing_inode(dentry); rcu_read_lock(); id.key.object = rcu_dereference(landlock_inode(inode)->object); rule = landlock_find_rule(domain, id); rcu_read_unlock(); return rule; } /* * Allows access to pseudo filesystems that will never be mountable (e.g. * sockfs, pipefs), but can still be reachable through * /proc/<pid>/fd/<file-descriptor> */ static bool is_nouser_or_private(const struct dentry *dentry) { return (dentry->d_sb->s_flags & SB_NOUSER) || (d_is_positive(dentry) && unlikely(IS_PRIVATE(d_backing_inode(dentry)))); } static access_mask_t get_raw_handled_fs_accesses(const struct landlock_ruleset *const domain) { access_mask_t access_dom = 0; size_t layer_level; for (layer_level = 0; layer_level < domain->num_layers; layer_level++) access_dom |= landlock_get_raw_fs_access_mask(domain, layer_level); return access_dom; } static access_mask_t get_handled_fs_accesses(const struct landlock_ruleset *const domain) { /* Handles all initially denied by default access rights. */ return get_raw_handled_fs_accesses(domain) | LANDLOCK_ACCESS_FS_INITIALLY_DENIED; } static const struct landlock_ruleset * get_fs_domain(const struct landlock_ruleset *const domain) { if (!domain || !get_raw_handled_fs_accesses(domain)) return NULL; return domain; } static const struct landlock_ruleset *get_current_fs_domain(void) { return get_fs_domain(landlock_get_current_domain()); } /* * Check that a destination file hierarchy has more restrictions than a source * file hierarchy. This is only used for link and rename actions. * * @layer_masks_child2: Optional child masks. */ static bool no_more_access( const layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS], const layer_mask_t (*const layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS], const bool child1_is_directory, const layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS], const layer_mask_t (*const layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS], const bool child2_is_directory) { unsigned long access_bit; for (access_bit = 0; access_bit < ARRAY_SIZE(*layer_masks_parent2); access_bit++) { /* Ignores accesses that only make sense for directories. */ const bool is_file_access = !!(BIT_ULL(access_bit) & ACCESS_FILE); if (child1_is_directory || is_file_access) { /* * Checks if the destination restrictions are a * superset of the source ones (i.e. inherited access * rights without child exceptions): * restrictions(parent2) >= restrictions(child1) */ if ((((*layer_masks_parent1)[access_bit] & (*layer_masks_child1)[access_bit]) | (*layer_masks_parent2)[access_bit]) != (*layer_masks_parent2)[access_bit]) return false; } if (!layer_masks_child2) continue; if (child2_is_directory || is_file_access) { /* * Checks inverted restrictions for RENAME_EXCHANGE: * restrictions(parent1) >= restrictions(child2) */ if ((((*layer_masks_parent2)[access_bit] & (*layer_masks_child2)[access_bit]) | (*layer_masks_parent1)[access_bit]) != (*layer_masks_parent1)[access_bit]) return false; } } return true; } #define NMA_TRUE(...) KUNIT_EXPECT_TRUE(test, no_more_access(__VA_ARGS__)) #define NMA_FALSE(...) KUNIT_EXPECT_FALSE(test, no_more_access(__VA_ARGS__)) #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_no_more_access(struct kunit *const test) { const layer_mask_t rx0[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_READ_FILE)] = BIT_ULL(0), }; const layer_mask_t mx0[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_MAKE_REG)] = BIT_ULL(0), }; const layer_mask_t x0[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), }; const layer_mask_t x1[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(1), }; const layer_mask_t x01[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0) | BIT_ULL(1), }; const layer_mask_t allows_all[LANDLOCK_NUM_ACCESS_FS] = {}; /* Checks without restriction. */ NMA_TRUE(&x0, &allows_all, false, &allows_all, NULL, false); NMA_TRUE(&allows_all, &x0, false, &allows_all, NULL, false); NMA_FALSE(&x0, &x0, false, &allows_all, NULL, false); /* * Checks that we can only refer a file if no more access could be * inherited. */ NMA_TRUE(&x0, &x0, false, &rx0, NULL, false); NMA_TRUE(&rx0, &rx0, false, &rx0, NULL, false); NMA_FALSE(&rx0, &rx0, false, &x0, NULL, false); NMA_FALSE(&rx0, &rx0, false, &x1, NULL, false); /* Checks allowed referring with different nested domains. */ NMA_TRUE(&x0, &x1, false, &x0, NULL, false); NMA_TRUE(&x1, &x0, false, &x0, NULL, false); NMA_TRUE(&x0, &x01, false, &x0, NULL, false); NMA_TRUE(&x0, &x01, false, &rx0, NULL, false); NMA_TRUE(&x01, &x0, false, &x0, NULL, false); NMA_TRUE(&x01, &x0, false, &rx0, NULL, false); NMA_FALSE(&x01, &x01, false, &x0, NULL, false); /* Checks that file access rights are also enforced for a directory. */ NMA_FALSE(&rx0, &rx0, true, &x0, NULL, false); /* Checks that directory access rights don't impact file referring... */ NMA_TRUE(&mx0, &mx0, false, &x0, NULL, false); /* ...but only directory referring. */ NMA_FALSE(&mx0, &mx0, true, &x0, NULL, false); /* Checks directory exchange. */ NMA_TRUE(&mx0, &mx0, true, &mx0, &mx0, true); NMA_TRUE(&mx0, &mx0, true, &mx0, &x0, true); NMA_FALSE(&mx0, &mx0, true, &x0, &mx0, true); NMA_FALSE(&mx0, &mx0, true, &x0, &x0, true); NMA_FALSE(&mx0, &mx0, true, &x1, &x1, true); /* Checks file exchange with directory access rights... */ NMA_TRUE(&mx0, &mx0, false, &mx0, &mx0, false); NMA_TRUE(&mx0, &mx0, false, &mx0, &x0, false); NMA_TRUE(&mx0, &mx0, false, &x0, &mx0, false); NMA_TRUE(&mx0, &mx0, false, &x0, &x0, false); /* ...and with file access rights. */ NMA_TRUE(&rx0, &rx0, false, &rx0, &rx0, false); NMA_TRUE(&rx0, &rx0, false, &rx0, &x0, false); NMA_FALSE(&rx0, &rx0, false, &x0, &rx0, false); NMA_FALSE(&rx0, &rx0, false, &x0, &x0, false); NMA_FALSE(&rx0, &rx0, false, &x1, &x1, false); /* * Allowing the following requests should not be a security risk * because domain 0 denies execute access, and domain 1 is always * nested with domain 0. However, adding an exception for this case * would mean to check all nested domains to make sure none can get * more privileges (e.g. processes only sandboxed by domain 0). * Moreover, this behavior (i.e. composition of N domains) could then * be inconsistent compared to domain 1's ruleset alone (e.g. it might * be denied to link/rename with domain 1's ruleset, whereas it would * be allowed if nested on top of domain 0). Another drawback would be * to create a cover channel that could enable sandboxed processes to * infer most of the filesystem restrictions from their domain. To * make it simple, efficient, safe, and more consistent, this case is * always denied. */ NMA_FALSE(&x1, &x1, false, &x0, NULL, false); NMA_FALSE(&x1, &x1, false, &rx0, NULL, false); NMA_FALSE(&x1, &x1, true, &x0, NULL, false); NMA_FALSE(&x1, &x1, true, &rx0, NULL, false); /* Checks the same case of exclusive domains with a file... */ NMA_TRUE(&x1, &x1, false, &x01, NULL, false); NMA_FALSE(&x1, &x1, false, &x01, &x0, false); NMA_FALSE(&x1, &x1, false, &x01, &x01, false); NMA_FALSE(&x1, &x1, false, &x0, &x0, false); /* ...and with a directory. */ NMA_FALSE(&x1, &x1, false, &x0, &x0, true); NMA_FALSE(&x1, &x1, true, &x0, &x0, false); NMA_FALSE(&x1, &x1, true, &x0, &x0, true); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #undef NMA_TRUE #undef NMA_FALSE /* * Removes @layer_masks accesses that are not requested. * * Returns true if the request is allowed, false otherwise. */ static bool scope_to_request(const access_mask_t access_request, layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) { const unsigned long access_req = access_request; unsigned long access_bit; if (WARN_ON_ONCE(!layer_masks)) return true; for_each_clear_bit(access_bit, &access_req, ARRAY_SIZE(*layer_masks)) (*layer_masks)[access_bit] = 0; return !memchr_inv(layer_masks, 0, sizeof(*layer_masks)); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_scope_to_request_with_exec_none(struct kunit *const test) { /* Allows everything. */ layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; /* Checks and scopes with execute. */ KUNIT_EXPECT_TRUE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &layer_masks)); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)]); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)]); } static void test_scope_to_request_with_exec_some(struct kunit *const test) { /* Denies execute and write. */ layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)] = BIT_ULL(1), }; /* Checks and scopes with execute. */ KUNIT_EXPECT_FALSE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &layer_masks)); KUNIT_EXPECT_EQ(test, BIT_ULL(0), layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)]); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)]); } static void test_scope_to_request_without_access(struct kunit *const test) { /* Denies execute and write. */ layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)] = BIT_ULL(1), }; /* Checks and scopes without access request. */ KUNIT_EXPECT_TRUE(test, scope_to_request(0, &layer_masks)); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)]); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)]); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ /* * Returns true if there is at least one access right different than * LANDLOCK_ACCESS_FS_REFER. */ static bool is_eacces(const layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS], const access_mask_t access_request) { unsigned long access_bit; /* LANDLOCK_ACCESS_FS_REFER alone must return -EXDEV. */ const unsigned long access_check = access_request & ~LANDLOCK_ACCESS_FS_REFER; if (!layer_masks) return false; for_each_set_bit(access_bit, &access_check, ARRAY_SIZE(*layer_masks)) { if ((*layer_masks)[access_bit]) return true; } return false; } #define IE_TRUE(...) KUNIT_EXPECT_TRUE(test, is_eacces(__VA_ARGS__)) #define IE_FALSE(...) KUNIT_EXPECT_FALSE(test, is_eacces(__VA_ARGS__)) #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_is_eacces_with_none(struct kunit *const test) { const layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; IE_FALSE(&layer_masks, 0); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } static void test_is_eacces_with_refer(struct kunit *const test) { const layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_REFER)] = BIT_ULL(0), }; IE_FALSE(&layer_masks, 0); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } static void test_is_eacces_with_write(struct kunit *const test) { const layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)] = BIT_ULL(0), }; IE_FALSE(&layer_masks, 0); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_TRUE(&layer_masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #undef IE_TRUE #undef IE_FALSE /** * is_access_to_paths_allowed - Check accesses for requests with a common path * * @domain: Domain to check against. * @path: File hierarchy to walk through. * @access_request_parent1: Accesses to check, once @layer_masks_parent1 is * equal to @layer_masks_parent2 (if any). This is tied to the unique * requested path for most actions, or the source in case of a refer action * (i.e. rename or link), or the source and destination in case of * RENAME_EXCHANGE. * @layer_masks_parent1: Pointer to a matrix of layer masks per access * masks, identifying the layers that forbid a specific access. Bits from * this matrix can be unset according to the @path walk. An empty matrix * means that @domain allows all possible Landlock accesses (i.e. not only * those identified by @access_request_parent1). This matrix can * initially refer to domain layer masks and, when the accesses for the * destination and source are the same, to requested layer masks. * @dentry_child1: Dentry to the initial child of the parent1 path. This * pointer must be NULL for non-refer actions (i.e. not link nor rename). * @access_request_parent2: Similar to @access_request_parent1 but for a * request involving a source and a destination. This refers to the * destination, except in case of RENAME_EXCHANGE where it also refers to * the source. Must be set to 0 when using a simple path request. * @layer_masks_parent2: Similar to @layer_masks_parent1 but for a refer * action. This must be NULL otherwise. * @dentry_child2: Dentry to the initial child of the parent2 path. This * pointer is only set for RENAME_EXCHANGE actions and must be NULL * otherwise. * * This helper first checks that the destination has a superset of restrictions * compared to the source (if any) for a common path. Because of * RENAME_EXCHANGE actions, source and destinations may be swapped. It then * checks that the collected accesses and the remaining ones are enough to * allow the request. * * Returns: * - true if the access request is granted; * - false otherwise. */ static bool is_access_to_paths_allowed( const struct landlock_ruleset *const domain, const struct path *const path, const access_mask_t access_request_parent1, layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS], const struct dentry *const dentry_child1, const access_mask_t access_request_parent2, layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS], const struct dentry *const dentry_child2) { bool allowed_parent1 = false, allowed_parent2 = false, is_dom_check, child1_is_directory = true, child2_is_directory = true; struct path walker_path; access_mask_t access_masked_parent1, access_masked_parent2; layer_mask_t _layer_masks_child1[LANDLOCK_NUM_ACCESS_FS], _layer_masks_child2[LANDLOCK_NUM_ACCESS_FS]; layer_mask_t(*layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS] = NULL, (*layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS] = NULL; if (!access_request_parent1 && !access_request_parent2) return true; if (WARN_ON_ONCE(!domain || !path)) return true; if (is_nouser_or_private(path->dentry)) return true; if (WARN_ON_ONCE(domain->num_layers < 1 || !layer_masks_parent1)) return false; if (unlikely(layer_masks_parent2)) { if (WARN_ON_ONCE(!dentry_child1)) return false; /* * For a double request, first check for potential privilege * escalation by looking at domain handled accesses (which are * a superset of the meaningful requested accesses). */ access_masked_parent1 = access_masked_parent2 = get_handled_fs_accesses(domain); is_dom_check = true; } else { if (WARN_ON_ONCE(dentry_child1 || dentry_child2)) return false; /* For a simple request, only check for requested accesses. */ access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; is_dom_check = false; } if (unlikely(dentry_child1)) { landlock_unmask_layers( find_rule(domain, dentry_child1), landlock_init_layer_masks( domain, LANDLOCK_MASK_ACCESS_FS, &_layer_masks_child1, LANDLOCK_KEY_INODE), &_layer_masks_child1, ARRAY_SIZE(_layer_masks_child1)); layer_masks_child1 = &_layer_masks_child1; child1_is_directory = d_is_dir(dentry_child1); } if (unlikely(dentry_child2)) { landlock_unmask_layers( find_rule(domain, dentry_child2), landlock_init_layer_masks( domain, LANDLOCK_MASK_ACCESS_FS, &_layer_masks_child2, LANDLOCK_KEY_INODE), &_layer_masks_child2, ARRAY_SIZE(_layer_masks_child2)); layer_masks_child2 = &_layer_masks_child2; child2_is_directory = d_is_dir(dentry_child2); } walker_path = *path; path_get(&walker_path); /* * We need to walk through all the hierarchy to not miss any relevant * restriction. */ while (true) { struct dentry *parent_dentry; const struct landlock_rule *rule; /* * If at least all accesses allowed on the destination are * already allowed on the source, respectively if there is at * least as much as restrictions on the destination than on the * source, then we can safely refer files from the source to * the destination without risking a privilege escalation. * This also applies in the case of RENAME_EXCHANGE, which * implies checks on both direction. This is crucial for * standalone multilayered security policies. Furthermore, * this helps avoid policy writers to shoot themselves in the * foot. */ if (unlikely(is_dom_check && no_more_access( layer_masks_parent1, layer_masks_child1, child1_is_directory, layer_masks_parent2, layer_masks_child2, child2_is_directory))) { allowed_parent1 = scope_to_request( access_request_parent1, layer_masks_parent1); allowed_parent2 = scope_to_request( access_request_parent2, layer_masks_parent2); /* Stops when all accesses are granted. */ if (allowed_parent1 && allowed_parent2) break; /* * Now, downgrades the remaining checks from domain * handled accesses to requested accesses. */ is_dom_check = false; access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; } rule = find_rule(domain, walker_path.dentry); allowed_parent1 = landlock_unmask_layers( rule, access_masked_parent1, layer_masks_parent1, ARRAY_SIZE(*layer_masks_parent1)); allowed_parent2 = landlock_unmask_layers( rule, access_masked_parent2, layer_masks_parent2, ARRAY_SIZE(*layer_masks_parent2)); /* Stops when a rule from each layer grants access. */ if (allowed_parent1 && allowed_parent2) break; jump_up: if (walker_path.dentry == walker_path.mnt->mnt_root) { if (follow_up(&walker_path)) { /* Ignores hidden mount points. */ goto jump_up; } else { /* * Stops at the real root. Denies access * because not all layers have granted access. */ break; } } if (unlikely(IS_ROOT(walker_path.dentry))) { /* * Stops at disconnected root directories. Only allows * access to internal filesystems (e.g. nsfs, which is * reachable through /proc/<pid>/ns/<namespace>). */ allowed_parent1 = allowed_parent2 = !!(walker_path.mnt->mnt_flags & MNT_INTERNAL); break; } parent_dentry = dget_parent(walker_path.dentry); dput(walker_path.dentry); walker_path.dentry = parent_dentry; } path_put(&walker_path); return allowed_parent1 && allowed_parent2; } static int check_access_path(const struct landlock_ruleset *const domain, const struct path *const path, access_mask_t access_request) { layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; access_request = landlock_init_layer_masks( domain, access_request, &layer_masks, LANDLOCK_KEY_INODE); if (is_access_to_paths_allowed(domain, path, access_request, &layer_masks, NULL, 0, NULL, NULL)) return 0; return -EACCES; } static int current_check_access_path(const struct path *const path, const access_mask_t access_request) { const struct landlock_ruleset *const dom = get_current_fs_domain(); if (!dom) return 0; return check_access_path(dom, path, access_request); } static access_mask_t get_mode_access(const umode_t mode) { switch (mode & S_IFMT) { case S_IFLNK: return LANDLOCK_ACCESS_FS_MAKE_SYM; case 0: /* A zero mode translates to S_IFREG. */ case S_IFREG: return LANDLOCK_ACCESS_FS_MAKE_REG; case S_IFDIR: return LANDLOCK_ACCESS_FS_MAKE_DIR; case S_IFCHR: return LANDLOCK_ACCESS_FS_MAKE_CHAR; case S_IFBLK: return LANDLOCK_ACCESS_FS_MAKE_BLOCK; case S_IFIFO: return LANDLOCK_ACCESS_FS_MAKE_FIFO; case S_IFSOCK: return LANDLOCK_ACCESS_FS_MAKE_SOCK; default: WARN_ON_ONCE(1); return 0; } } static access_mask_t maybe_remove(const struct dentry *const dentry) { if (d_is_negative(dentry)) return 0; return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR : LANDLOCK_ACCESS_FS_REMOVE_FILE; } /** * collect_domain_accesses - Walk through a file path and collect accesses * * @domain: Domain to check against. * @mnt_root: Last directory to check. * @dir: Directory to start the walk from. * @layer_masks_dom: Where to store the collected accesses. * * This helper is useful to begin a path walk from the @dir directory to a * @mnt_root directory used as a mount point. This mount point is the common * ancestor between the source and the destination of a renamed and linked * file. While walking from @dir to @mnt_root, we record all the domain's * allowed accesses in @layer_masks_dom. * * This is similar to is_access_to_paths_allowed() but much simpler because it * only handles walking on the same mount point and only checks one set of * accesses. * * Returns: * - true if all the domain access rights are allowed for @dir; * - false if the walk reached @mnt_root. */ static bool collect_domain_accesses( const struct landlock_ruleset *const domain, const struct dentry *const mnt_root, struct dentry *dir, layer_mask_t (*const layer_masks_dom)[LANDLOCK_NUM_ACCESS_FS]) { unsigned long access_dom; bool ret = false; if (WARN_ON_ONCE(!domain || !mnt_root || !dir || !layer_masks_dom)) return true; if (is_nouser_or_private(dir)) return true; access_dom = landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, layer_masks_dom, LANDLOCK_KEY_INODE); dget(dir); while (true) { struct dentry *parent_dentry; /* Gets all layers allowing all domain accesses. */ if (landlock_unmask_layers(find_rule(domain, dir), access_dom, layer_masks_dom, ARRAY_SIZE(*layer_masks_dom))) { /* * Stops when all handled accesses are allowed by at * least one rule in each layer. */ ret = true; break; } /* We should not reach a root other than @mnt_root. */ if (dir == mnt_root || WARN_ON_ONCE(IS_ROOT(dir))) break; parent_dentry = dget_parent(dir); dput(dir); dir = parent_dentry; } dput(dir); return ret; } /** * current_check_refer_path - Check if a rename or link action is allowed * * @old_dentry: File or directory requested to be moved or linked. * @new_dir: Destination parent directory. * @new_dentry: Destination file or directory. * @removable: Sets to true if it is a rename operation. * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE. * * Because of its unprivileged constraints, Landlock relies on file hierarchies * (and not only inodes) to tie access rights to files. Being able to link or * rename a file hierarchy brings some challenges. Indeed, moving or linking a * file (i.e. creating a new reference to an inode) can have an impact on the * actions allowed for a set of files if it would change its parent directory * (i.e. reparenting). * * To avoid trivial access right bypasses, Landlock first checks if the file or * directory requested to be moved would gain new access rights inherited from * its new hierarchy. Before returning any error, Landlock then checks that * the parent source hierarchy and the destination hierarchy would allow the * link or rename action. If it is not the case, an error with EACCES is * returned to inform user space that there is no way to remove or create the * requested source file type. If it should be allowed but the new inherited * access rights would be greater than the source access rights, then the * kernel returns an error with EXDEV. Prioritizing EACCES over EXDEV enables * user space to abort the whole operation if there is no way to do it, or to * manually copy the source to the destination if this remains allowed, e.g. * because file creation is allowed on the destination directory but not direct * linking. * * To achieve this goal, the kernel needs to compare two file hierarchies: the * one identifying the source file or directory (including itself), and the * destination one. This can be seen as a multilayer partial ordering problem. * The kernel walks through these paths and collects in a matrix the access * rights that are denied per layer. These matrices are then compared to see * if the destination one has more (or the same) restrictions as the source * one. If this is the case, the requested action will not return EXDEV, which * doesn't mean the action is allowed. The parent hierarchy of the source * (i.e. parent directory), and the destination hierarchy must also be checked * to verify that they explicitly allow such action (i.e. referencing, * creation and potentially removal rights). The kernel implementation is then * required to rely on potentially four matrices of access rights: one for the * source file or directory (i.e. the child), a potentially other one for the * other source/destination (in case of RENAME_EXCHANGE), one for the source * parent hierarchy and a last one for the destination hierarchy. These * ephemeral matrices take some space on the stack, which limits the number of * layers to a deemed reasonable number: 16. * * Returns: * - 0 if access is allowed; * - -EXDEV if @old_dentry would inherit new access rights from @new_dir; * - -EACCES if file removal or creation is denied. */ static int current_check_refer_path(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, const bool removable, const bool exchange) { const struct landlock_ruleset *const dom = get_current_fs_domain(); bool allow_parent1, allow_parent2; access_mask_t access_request_parent1, access_request_parent2; struct path mnt_dir; struct dentry *old_parent; layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {}, layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {}; if (!dom) return 0; if (WARN_ON_ONCE(dom->num_layers < 1)) return -EACCES; if (unlikely(d_is_negative(old_dentry))) return -ENOENT; if (exchange) { if (unlikely(d_is_negative(new_dentry))) return -ENOENT; access_request_parent1 = get_mode_access(d_backing_inode(new_dentry)->i_mode); } else { access_request_parent1 = 0; } access_request_parent2 = get_mode_access(d_backing_inode(old_dentry)->i_mode); if (removable) { access_request_parent1 |= maybe_remove(old_dentry); access_request_parent2 |= maybe_remove(new_dentry); } /* The mount points are the same for old and new paths, cf. EXDEV. */ if (old_dentry->d_parent == new_dir->dentry) { /* * The LANDLOCK_ACCESS_FS_REFER access right is not required * for same-directory referer (i.e. no reparenting). */ access_request_parent1 = landlock_init_layer_masks( dom, access_request_parent1 | access_request_parent2, &layer_masks_parent1, LANDLOCK_KEY_INODE); if (is_access_to_paths_allowed( dom, new_dir, access_request_parent1, &layer_masks_parent1, NULL, 0, NULL, NULL)) return 0; return -EACCES; } access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER; access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER; /* Saves the common mount point. */ mnt_dir.mnt = new_dir->mnt; mnt_dir.dentry = new_dir->mnt->mnt_root; /* * old_dentry may be the root of the common mount point and * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and * OPEN_TREE_CLONE). We do not need to call dget(old_parent) because * we keep a reference to old_dentry. */ old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : old_dentry->d_parent; /* new_dir->dentry is equal to new_dentry->d_parent */ allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry, old_parent, &layer_masks_parent1); allow_parent2 = collect_domain_accesses( dom, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); if (allow_parent1 && allow_parent2) return 0; /* * To be able to compare source and destination domain access rights, * take into account the @old_dentry access rights aggregated with its * parent access rights. This will be useful to compare with the * destination parent access rights. */ if (is_access_to_paths_allowed( dom, &mnt_dir, access_request_parent1, &layer_masks_parent1, old_dentry, access_request_parent2, &layer_masks_parent2, exchange ? new_dentry : NULL)) return 0; /* * This prioritizes EACCES over EXDEV for all actions, including * renames with RENAME_EXCHANGE. */ if (likely(is_eacces(&layer_masks_parent1, access_request_parent1) || is_eacces(&layer_masks_parent2, access_request_parent2))) return -EACCES; /* * Gracefully forbids reparenting if the destination directory * hierarchy is not a superset of restrictions of the source directory * hierarchy, or if LANDLOCK_ACCESS_FS_REFER is not allowed by the * source or the destination. */ return -EXDEV; } /* Inode hooks */ static void hook_inode_free_security(struct inode *const inode) { /* * All inodes must already have been untied from their object by * release_inode() or hook_sb_delete(). */ WARN_ON_ONCE(landlock_inode(inode)->object); } /* Super-block hooks */ /* * Release the inodes used in a security policy. * * Cf. fsnotify_unmount_inodes() and invalidate_inodes() */ static void hook_sb_delete(struct super_block *const sb) { struct inode *inode, *prev_inode = NULL; if (!landlock_initialized) return; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct landlock_object *object; /* Only handles referenced inodes. */ if (!atomic_read(&inode->i_count)) continue; /* * Protects against concurrent modification of inode (e.g. * from get_inode_object()). */ spin_lock(&inode->i_lock); /* * Checks I_FREEING and I_WILL_FREE to protect against a race * condition when release_inode() just called iput(), which * could lead to a NULL dereference of inode->security or a * second call to iput() for the same Landlock object. Also * checks I_NEW because such inode cannot be tied to an object. */ if (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } rcu_read_lock(); object = rcu_dereference(landlock_inode(inode)->object); if (!object) { rcu_read_unlock(); spin_unlock(&inode->i_lock); continue; } /* Keeps a reference to this inode until the next loop walk. */ __iget(inode); spin_unlock(&inode->i_lock); /* * If there is no concurrent release_inode() ongoing, then we * are in charge of calling iput() on this inode, otherwise we * will just wait for it to finish. */ spin_lock(&object->lock); if (object->underobj == inode) { object->underobj = NULL; spin_unlock(&object->lock); rcu_read_unlock(); /* * Because object->underobj was not NULL, * release_inode() and get_inode_object() guarantee * that it is safe to reset * landlock_inode(inode)->object while it is not NULL. * It is therefore not necessary to lock inode->i_lock. */ rcu_assign_pointer(landlock_inode(inode)->object, NULL); /* * At this point, we own the ihold() reference that was * originally set up by get_inode_object() and the * __iget() reference that we just set in this loop * walk. Therefore the following call to iput() will * not sleep nor drop the inode because there is now at * least two references to it. */ iput(inode); } else { spin_unlock(&object->lock); rcu_read_unlock(); } if (prev_inode) { /* * At this point, we still own the __iget() reference * that we just set in this loop walk. Therefore we * can drop the list lock and know that the inode won't * disappear from under us until the next loop walk. */ spin_unlock(&sb->s_inode_list_lock); /* * We can now actually put the inode reference from the * previous loop walk, which is not needed anymore. */ iput(prev_inode); cond_resched(); spin_lock(&sb->s_inode_list_lock); } prev_inode = inode; } spin_unlock(&sb->s_inode_list_lock); /* Puts the inode reference from the last loop walk, if any. */ if (prev_inode) iput(prev_inode); /* Waits for pending iput() in release_inode(). */ wait_var_event(&landlock_superblock(sb)->inode_refs, !atomic_long_read(&landlock_superblock(sb)->inode_refs)); } /* * Because a Landlock security policy is defined according to the filesystem * topology (i.e. the mount namespace), changing it may grant access to files * not previously allowed. * * To make it simple, deny any filesystem topology modification by landlocked * processes. Non-landlocked processes may still change the namespace of a * landlocked process, but this kind of threat must be handled by a system-wide * access-control security policy. * * This could be lifted in the future if Landlock can safely handle mount * namespace updates requested by a landlocked process. Indeed, we could * update the current domain (which is currently read-only) by taking into * account the accesses of the source and the destination of a new mount point. * However, it would also require to make all the child domains dynamically * inherit these new constraints. Anyway, for backward compatibility reasons, * a dedicated user space option would be required (e.g. as a ruleset flag). */ static int hook_sb_mount(const char *const dev_name, const struct path *const path, const char *const type, const unsigned long flags, void *const data) { if (!get_current_fs_domain()) return 0; return -EPERM; } static int hook_move_mount(const struct path *const from_path, const struct path *const to_path) { if (!get_current_fs_domain()) return 0; return -EPERM; } /* * Removing a mount point may reveal a previously hidden file hierarchy, which * may then grant access to files, which may have previously been forbidden. */ static int hook_sb_umount(struct vfsmount *const mnt, const int flags) { if (!get_current_fs_domain()) return 0; return -EPERM; } static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts) { if (!get_current_fs_domain()) return 0; return -EPERM; } /* * pivot_root(2), like mount(2), changes the current mount namespace. It must * then be forbidden for a landlocked process. * * However, chroot(2) may be allowed because it only changes the relative root * directory of the current process. Moreover, it can be used to restrict the * view of the filesystem. */ static int hook_sb_pivotroot(const struct path *const old_path, const struct path *const new_path) { if (!get_current_fs_domain()) return 0; return -EPERM; } /* Path hooks */ static int hook_path_link(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry) { return current_check_refer_path(old_dentry, new_dir, new_dentry, false, false); } static int hook_path_rename(const struct path *const old_dir, struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, const unsigned int flags) { /* old_dir refers to old_dentry->d_parent and new_dir->mnt */ return current_check_refer_path(old_dentry, new_dir, new_dentry, true, !!(flags & RENAME_EXCHANGE)); } static int hook_path_mkdir(const struct path *const dir, struct dentry *const dentry, const umode_t mode) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR); } static int hook_path_mknod(const struct path *const dir, struct dentry *const dentry, const umode_t mode, const unsigned int dev) { const struct landlock_ruleset *const dom = get_current_fs_domain(); if (!dom) return 0; return check_access_path(dom, dir, get_mode_access(mode)); } static int hook_path_symlink(const struct path *const dir, struct dentry *const dentry, const char *const old_name) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM); } static int hook_path_unlink(const struct path *const dir, struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE); } static int hook_path_rmdir(const struct path *const dir, struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR); } static int hook_path_truncate(const struct path *const path) { return current_check_access_path(path, LANDLOCK_ACCESS_FS_TRUNCATE); } /* File hooks */ /** * get_required_file_open_access - Get access needed to open a file * * @file: File being opened. * * Returns the access rights that are required for opening the given file, * depending on the file type and open mode. */ static access_mask_t get_required_file_open_access(const struct file *const file) { access_mask_t access = 0; if (file->f_mode & FMODE_READ) { /* A directory can only be opened in read mode. */ if (S_ISDIR(file_inode(file)->i_mode)) return LANDLOCK_ACCESS_FS_READ_DIR; access = LANDLOCK_ACCESS_FS_READ_FILE; } if (file->f_mode & FMODE_WRITE) access |= LANDLOCK_ACCESS_FS_WRITE_FILE; /* __FMODE_EXEC is indeed part of f_flags, not f_mode. */ if (file->f_flags & __FMODE_EXEC) access |= LANDLOCK_ACCESS_FS_EXECUTE; return access; } static int hook_file_alloc_security(struct file *const file) { /* * Grants all access rights, even if most of them are not checked later * on. It is more consistent. * * Notably, file descriptors for regular files can also be acquired * without going through the file_open hook, for example when using * memfd_create(2). */ landlock_file(file)->allowed_access = LANDLOCK_MASK_ACCESS_FS; return 0; } static bool is_device(const struct file *const file) { const struct inode *inode = file_inode(file); return S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode); } static int hook_file_open(struct file *const file) { layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; access_mask_t open_access_request, full_access_request, allowed_access, optional_access; const struct landlock_ruleset *const dom = get_fs_domain(landlock_cred(file->f_cred)->domain); if (!dom) return 0; /* * Because a file may be opened with O_PATH, get_required_file_open_access() * may return 0. This case will be handled with a future Landlock * evolution. */ open_access_request = get_required_file_open_access(file); /* * We look up more access than what we immediately need for open(), so * that we can later authorize operations on opened files. */ optional_access = LANDLOCK_ACCESS_FS_TRUNCATE; if (is_device(file)) optional_access |= LANDLOCK_ACCESS_FS_IOCTL_DEV; full_access_request = open_access_request | optional_access; if (is_access_to_paths_allowed( dom, &file->f_path, landlock_init_layer_masks(dom, full_access_request, &layer_masks, LANDLOCK_KEY_INODE), &layer_masks, NULL, 0, NULL, NULL)) { allowed_access = full_access_request; } else { unsigned long access_bit; const unsigned long access_req = full_access_request; /* * Calculate the actual allowed access rights from layer_masks. * Add each access right to allowed_access which has not been * vetoed by any layer. */ allowed_access = 0; for_each_set_bit(access_bit, &access_req, ARRAY_SIZE(layer_masks)) { if (!layer_masks[access_bit]) allowed_access |= BIT_ULL(access_bit); } } /* * For operations on already opened files (i.e. ftruncate()), it is the * access rights at the time of open() which decide whether the * operation is permitted. Therefore, we record the relevant subset of * file access rights in the opened struct file. */ landlock_file(file)->allowed_access = allowed_access; if ((open_access_request & allowed_access) == open_access_request) return 0; return -EACCES; } static int hook_file_truncate(struct file *const file) { /* * Allows truncation if the truncate right was available at the time of * opening the file, to get a consistent access check as for read, write * and execute operations. * * Note: For checks done based on the file's Landlock allowed access, we * enforce them independently of whether the current thread is in a * Landlock domain, so that open files passed between independent * processes retain their behaviour. */ if (landlock_file(file)->allowed_access & LANDLOCK_ACCESS_FS_TRUNCATE) return 0; return -EACCES; } static int hook_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { access_mask_t allowed_access = landlock_file(file)->allowed_access; /* * It is the access rights at the time of opening the file which * determine whether IOCTL can be used on the opened file later. * * The access right is attached to the opened file in hook_file_open(). */ if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV) return 0; if (!is_device(file)) return 0; if (is_masked_device_ioctl(cmd)) return 0; return -EACCES; } static int hook_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { access_mask_t allowed_access = landlock_file(file)->allowed_access; /* * It is the access rights at the time of opening the file which * determine whether IOCTL can be used on the opened file later. * * The access right is attached to the opened file in hook_file_open(). */ if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV) return 0; if (!is_device(file)) return 0; if (is_masked_device_ioctl_compat(cmd)) return 0; return -EACCES; } static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_free_security, hook_inode_free_security), LSM_HOOK_INIT(sb_delete, hook_sb_delete), LSM_HOOK_INIT(sb_mount, hook_sb_mount), LSM_HOOK_INIT(move_mount, hook_move_mount), LSM_HOOK_INIT(sb_umount, hook_sb_umount), LSM_HOOK_INIT(sb_remount, hook_sb_remount), LSM_HOOK_INIT(sb_pivotroot, hook_sb_pivotroot), LSM_HOOK_INIT(path_link, hook_path_link), LSM_HOOK_INIT(path_rename, hook_path_rename), LSM_HOOK_INIT(path_mkdir, hook_path_mkdir), LSM_HOOK_INIT(path_mknod, hook_path_mknod), LSM_HOOK_INIT(path_symlink, hook_path_symlink), LSM_HOOK_INIT(path_unlink, hook_path_unlink), LSM_HOOK_INIT(path_rmdir, hook_path_rmdir), LSM_HOOK_INIT(path_truncate, hook_path_truncate), LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security), LSM_HOOK_INIT(file_open, hook_file_open), LSM_HOOK_INIT(file_truncate, hook_file_truncate), LSM_HOOK_INIT(file_ioctl, hook_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, hook_file_ioctl_compat), }; __init void landlock_add_fs_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST /* clang-format off */ static struct kunit_case test_cases[] = { KUNIT_CASE(test_no_more_access), KUNIT_CASE(test_scope_to_request_with_exec_none), KUNIT_CASE(test_scope_to_request_with_exec_some), KUNIT_CASE(test_scope_to_request_without_access), KUNIT_CASE(test_is_eacces_with_none), KUNIT_CASE(test_is_eacces_with_refer), KUNIT_CASE(test_is_eacces_with_write), {} }; /* clang-format on */ static struct kunit_suite test_suite = { .name = "landlock_fs", .test_cases = test_cases, }; kunit_test_suite(test_suite); #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ |
| 15 15 15 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_NETLINK_H #define __NET_NETLINK_H #include <linux/types.h> #include <linux/netlink.h> #include <linux/jiffies.h> #include <linux/in6.h> /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) * ------------------------------------------------------------------------ * Messages Interface * ------------------------------------------------------------------------ * * Message Format: * <--- nlmsg_total_size(payload) ---> * <-- nlmsg_msg_size(payload) -> * +----------+- - -+-------------+- - -+-------- - - * | nlmsghdr | Pad | Payload | Pad | nlmsghdr * +----------+- - -+-------------+- - -+-------- - - * nlmsg_data(nlh)---^ ^ * nlmsg_next(nlh)-----------------------+ * * Payload Format: * <---------------------- nlmsg_len(nlh) ---------------------> * <------ hdrlen ------> <- nlmsg_attrlen(nlh, hdrlen) -> * +----------------------+- - -+--------------------------------+ * | Family Header | Pad | Attributes | * +----------------------+- - -+--------------------------------+ * nlmsg_attrdata(nlh, hdrlen)---^ * * Data Structures: * struct nlmsghdr netlink message header * * Message Construction: * nlmsg_new() create a new netlink message * nlmsg_put() add a netlink message to an skb * nlmsg_put_answer() callback based nlmsg_put() * nlmsg_end() finalize netlink message * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction * nlmsg_consume() free a netlink message (expected) * nlmsg_free() free a netlink message (drop) * * Message Sending: * nlmsg_multicast() multicast message to several groups * nlmsg_unicast() unicast a message to a single socket * nlmsg_notify() send notification message * * Message Length Calculations: * nlmsg_msg_size(payload) length of message w/o padding * nlmsg_total_size(payload) length of message w/ padding * nlmsg_padlen(payload) length of padding at tail * * Message Payload Access: * nlmsg_data(nlh) head of message payload * nlmsg_len(nlh) length of message payload * nlmsg_attrdata(nlh, hdrlen) head of attributes data * nlmsg_attrlen(nlh, hdrlen) length of attributes data * * Message Parsing: * nlmsg_ok(nlh, remaining) does nlh fit into remaining bytes? * nlmsg_next(nlh, remaining) get next netlink message * nlmsg_parse() parse attributes of a message * nlmsg_find_attr() find an attribute in a message * nlmsg_for_each_msg() loop over all messages * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes * * Misc: * nlmsg_report() report back to application? * * ------------------------------------------------------------------------ * Attributes Interface * ------------------------------------------------------------------------ * * Attribute Format: * <------- nla_total_size(payload) -------> * <---- nla_attr_size(payload) -----> * +----------+- - -+- - - - - - - - - +- - -+-------- - - * | Header | Pad | Payload | Pad | Header * +----------+- - -+- - - - - - - - - +- - -+-------- - - * <- nla_len(nla) -> ^ * nla_data(nla)----^ | * nla_next(nla)-----------------------------' * * Data Structures: * struct nlattr netlink attribute header * * Attribute Construction: * nla_reserve(skb, type, len) reserve room for an attribute * nla_reserve_nohdr(skb, len) reserve room for an attribute w/o hdr * nla_put(skb, type, len, data) add attribute to skb * nla_put_nohdr(skb, len, data) add attribute w/o hdr * nla_append(skb, len, data) append data to skb * * Attribute Construction for Basic Types: * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb * nla_put_u64_64bit(skb, type, * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb * nla_put_s64(skb, type, value, * padattr) add s64 attribute to skb * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies, * padattr) add msecs attribute to skb * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding * nla_total_size(payload) length of attribute w/ padding * nla_padlen(payload) length of padding * * Attribute Payload Access: * nla_data(nla) head of attribute payload * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: * nla_get_uint(nla) get payload for a uint attribute * nla_get_sint(nla) get payload for a sint attribute * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute * nla_get_u64(nla) get payload for a u64 attribute * nla_get_s8(nla) get payload for a s8 attribute * nla_get_s16(nla) get payload for a s16 attribute * nla_get_s32(nla) get payload for a s32 attribute * nla_get_s64(nla) get payload for a s64 attribute * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area * nla_strscpy(dst, nla, size) copy attribute to a sized string * nla_strcmp(nla, str) compare attribute with string * * Attribute Parsing: * nla_ok(nla, remaining) does nla fit into remaining bytes? * nla_next(nla, remaining) get next netlink attribute * nla_validate() validate a stream of attributes * nla_validate_nested() validate a stream of nested attributes * nla_find() find attribute in stream of attributes * nla_find_nested() find attribute in nested attributes * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes * nla_for_each_attr_type() loop over all attributes with the * given type * nla_for_each_nested() loop over the nested attributes * nla_for_each_nested_type() loop over the nested attributes with * the given type *========================================================================= */ /** * Standard attribute types to specify validation policy */ enum { NLA_UNSPEC, NLA_U8, NLA_U16, NLA_U32, NLA_U64, NLA_STRING, NLA_FLAG, NLA_MSECS, NLA_NESTED, NLA_NESTED_ARRAY, NLA_NUL_STRING, NLA_BINARY, NLA_S8, NLA_S16, NLA_S32, NLA_S64, NLA_BITFIELD32, NLA_REJECT, NLA_BE16, NLA_BE32, NLA_SINT, NLA_UINT, __NLA_TYPE_MAX, }; #define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) struct netlink_range_validation { u64 min, max; }; struct netlink_range_validation_signed { s64 min, max; }; enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_MASK, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, }; /** * struct nla_policy - attribute validation policy * @type: Type of attribute or NLA_UNSPEC * @validation_type: type of attribute validation done in addition to * type-specific validation (e.g. range, function call), see * &enum nla_policy_validation * @len: Type specific length of payload * * Policies are defined as arrays of this struct, the array must be * accessible by attribute type up to the highest identifier to be expected. * * Meaning of `len' field: * NLA_STRING Maximum length of string * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if * nested_policy is also used, for the max attr * number in the nested policy. * NLA_SINT, NLA_UINT, * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, * NLA_S32, NLA_S64, * NLA_BE16, NLA_BE32, * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused * All other Minimum length of attribute payload * * Meaning of validation union: * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and * `bitfield32_valid' is the u32 value of valid flags * NLA_REJECT This attribute is always rejected and `reject_message' * may point to a string to report as the error instead * of the generic one in extended ACK. * NLA_NESTED `nested_policy' to a nested policy to validate, must * also set `len' to the max attribute number. Use the * provided NLA_POLICY_NESTED() macro. * Note that nla_parse() will validate, but of course not * parse, the nested sub-policies. * NLA_NESTED_ARRAY `nested_policy' points to a nested policy to validate, * must also set `len' to the max attribute number. Use * the provided NLA_POLICY_NESTED_ARRAY() macro. * The difference to NLA_NESTED is the structure: * NLA_NESTED has the nested attributes directly inside * while an array has the nested attributes at another * level down and the attribute types directly in the * nesting don't matter. * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64, * NLA_BE16, * NLA_BE32, * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 The `min' and `max' fields are used depending on the * validation_type field, if that is min/max/range then * the min, max or both are used (respectively) to check * the value of the integer attribute. * Note that in the interest of code simplicity and * struct size both limits are s16, so you cannot * enforce a range that doesn't fall within the range * of s16 - do that using the NLA_POLICY_FULL_RANGE() * or NLA_POLICY_FULL_RANGE_SIGNED() macros instead. * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and * NLA_POLICY_RANGE() macros. * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64 If the validation_type field instead is set to * NLA_VALIDATE_RANGE_PTR, `range' must be a pointer * to a struct netlink_range_validation that indicates * the min/max values. * Use NLA_POLICY_FULL_RANGE(). * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 If the validation_type field instead is set to * NLA_VALIDATE_RANGE_PTR, `range_signed' must be a * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). * * NLA_BINARY If the validation type is like the ones for integers * above, then the min/max length (not value like for * integers) of the attribute is enforced. * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: * NLA_BINARY Validation function called for the attribute. * All other Unused - but note that it's a union * * Example: * * static const u32 myvalidflags = 0xff231023; * * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ struct nla_policy { u8 type; u8 validation_type; u16 len; union { /** * @strict_start_type: first attribute to validate strictly * * This entry is special, and used for the attribute at index 0 * only, and specifies special data about the policy, namely it * specifies the "boundary type" where strict length validation * starts for any attribute types >= this value, also, strict * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to * get the previous pure { .len = xyz } behaviour. The advantage * of this is that types not specified in the policy will be * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones * it should be set at least when new attributes are added to * the enum used by the policy, and be set to the new value that * was added to enforce strict validation from thereon. */ u16 strict_start_type; /* private: use NLA_POLICY_*() to set */ const u32 bitfield32_valid; const u32 mask; const char *reject_message; const struct nla_policy *nested_policy; const struct netlink_range_validation *range; const struct netlink_range_validation_signed *range_signed; struct { s16 min, max; }; int (*validate)(const struct nlattr *attr, struct netlink_ext_ack *extack); }; }; #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) #define _NLA_POLICY_NESTED(maxattr, policy) \ { .type = NLA_NESTED, .nested_policy = policy, .len = maxattr } #define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ { .type = NLA_NESTED_ARRAY, .nested_policy = policy, .len = maxattr } #define NLA_POLICY_NESTED(policy) \ _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_NESTED_ARRAY(policy) \ _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_BITFIELD32(valid) \ { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_IS_UINT_TYPE(tp) \ (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \ tp == NLA_U64 || tp == NLA_UINT || \ tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_IS_SINT_TYPE(tp) \ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64 || \ tp == NLA_SINT) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp) #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp) #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ __NLA_IS_SINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } #define NLA_POLICY_FULL_RANGE_SIGNED(tp, _range) { \ .type = NLA_ENSURE_SINT_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range_signed = _range, \ } #define NLA_POLICY_MIN(tp, _min) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } #define NLA_POLICY_MASK(tp, _mask) { \ .type = NLA_ENSURE_UINT_TYPE(tp), \ .validation_type = NLA_VALIDATE_MASK, \ .mask = _mask, \ } #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ .validation_type = NLA_VALIDATE_FUNCTION, \ .validate = fn, \ .len = __VA_ARGS__ + 0, \ } #define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) #define NLA_POLICY_EXACT_LEN_WARN(_len) { \ .type = NLA_BINARY, \ .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ .min = _len, \ .max = _len \ } #define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application * @skip_notify: Skip netlink notifications to user space * @skip_notify_kernel: Skip selected in-kernel notifications */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; u32 portid; u8 skip_notify:1, skip_notify_kernel:1; }; /** * enum netlink_validation - netlink message/attribute validation levels * @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about * extra data at the end of the message, attributes being longer than * they should be, or unknown attributes being present. * @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing. * @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING * this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict(). * @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy. * This can safely be set by the kernel when the given policy has no * NLA_UNSPEC anymore, and can thus be used to ensure policy entries * are enforced going forward. * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g. * U8, U16, U32 must have exact size, etc.) * @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY) * and unset for other policies. */ enum netlink_validation { NL_VALIDATE_LIBERAL = 0, NL_VALIDATE_TRAILING = BIT(0), NL_VALIDATE_MAXTYPE = BIT(1), NL_VALIDATE_UNSPEC = BIT(2), NL_VALIDATE_STRICT_ATTRS = BIT(3), NL_VALIDATE_NESTED = BIT(4), }; #define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE) #define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE |\ NL_VALIDATE_UNSPEC |\ NL_VALIDATE_STRICT_ATTRS |\ NL_VALIDATE_NESTED) int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)); int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags); int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize); char *nla_strdup(const struct nlattr *nla, gfp_t flags); int nla_memcpy(void *dest, const struct nlattr *src, int count); int nla_memcmp(const struct nlattr *nla, const void *data, size_t size); int nla_strcmp(const struct nlattr *nla, const char *str); struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen); struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen); void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_append(struct sk_buff *skb, int attrlen, const void *data); /************************************************************************** * Netlink Messages **************************************************************************/ /** * nlmsg_msg_size - length of netlink message not including padding * @payload: length of message payload */ static inline int nlmsg_msg_size(int payload) { return NLMSG_HDRLEN + payload; } /** * nlmsg_total_size - length of netlink message including padding * @payload: length of message payload */ static inline int nlmsg_total_size(int payload) { return NLMSG_ALIGN(nlmsg_msg_size(payload)); } /** * nlmsg_padlen - length of padding at the message's tail * @payload: length of message payload */ static inline int nlmsg_padlen(int payload) { return nlmsg_total_size(payload) - nlmsg_msg_size(payload); } /** * nlmsg_data - head of message payload * @nlh: netlink message header */ static inline void *nlmsg_data(const struct nlmsghdr *nlh) { return (unsigned char *) nlh + NLMSG_HDRLEN; } /** * nlmsg_len - length of message payload * @nlh: netlink message header */ static inline int nlmsg_len(const struct nlmsghdr *nlh) { return nlh->nlmsg_len - NLMSG_HDRLEN; } /** * nlmsg_attrdata - head of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline struct nlattr *nlmsg_attrdata(const struct nlmsghdr *nlh, int hdrlen) { unsigned char *data = nlmsg_data(nlh); return (struct nlattr *) (data + NLMSG_ALIGN(hdrlen)); } /** * nlmsg_attrlen - length of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline int nlmsg_attrlen(const struct nlmsghdr *nlh, int hdrlen) { return nlmsg_len(nlh) - NLMSG_ALIGN(hdrlen); } /** * nlmsg_ok - check if the netlink message fits into the remaining bytes * @nlh: netlink message header * @remaining: number of bytes remaining in message stream */ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) { return (remaining >= (int) sizeof(struct nlmsghdr) && nlh->nlmsg_len >= sizeof(struct nlmsghdr) && nlh->nlmsg_len <= remaining); } /** * nlmsg_next - next netlink message in message stream * @nlh: netlink message header * @remaining: number of bytes remaining in message stream * * Returns the next netlink message in the message stream and * decrements remaining by the size of the current message. */ static inline struct nlmsghdr * nlmsg_next(const struct nlmsghdr *nlh, int *remaining) { int totlen = NLMSG_ALIGN(nlh->nlmsg_len); *remaining -= totlen; return (struct nlmsghdr *) ((unsigned char *) nlh + totlen); } /** * nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected, policy must be specified, attributes * will be validated in the strictest way possible. * * Returns 0 on success or a negative error code. */ static inline int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_deprecated - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be ignored and attributes from the policy are not * always strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected as well as trailing data, but the * policy is not completely strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * __nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() */ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { NL_SET_ERR_MSG(extack, "Invalid header length"); return -EINVAL; } return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), policy, validate, extack); } /** * nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_parse_deprecated - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_parse_deprecated_strict - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated_strict() */ static inline int nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header * @hdrlen: length of familiy specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, int hdrlen, int attrtype) { return nla_find(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), attrtype); } /** * nla_validate_deprecated - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. * See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate_deprecated(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. * See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header * @hdrlen: length of familiy specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, int hdrlen, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; return __nla_validate(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_report - need to report back to application? * @nlh: netlink message header * * Returns 1 if a report back to the application is requested. */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0; } /** * nlmsg_seq - return the seq number of netlink message * @nlh: netlink message header * * Returns 0 if netlink message is NULL */ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) { return nlh ? nlh->nlmsg_seq : 0; } /** * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header * @hdrlen: length of familiy specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ nla_for_each_attr(pos, nlmsg_attrdata(nlh, hdrlen), \ nlmsg_attrlen(nlh, hdrlen), rem) /** * nlmsg_put - Add a new netlink message to an skb * @skb: socket buffer to store message in * @portid: netlink PORTID of requesting application * @seq: sequence number of message * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int payload, int flags) { if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload))) return NULL; return __nlmsg_put(skb, portid, seq, type, payload, flags); } /** * nlmsg_append - Add more data to a nlmsg in a skb * @skb: socket buffer to store message in * @size: length of message payload * * Append data to an existing nlmsg, used when constructing a message * with multiple fixed-format headers (which is rare). * Returns NULL if the tailroom of the skb is insufficient to store * the extra payload. */ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) { if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size))) return NULL; if (NLMSG_ALIGN(size) - size) memset(skb_tail_pointer(skb) + size, 0, NLMSG_ALIGN(size) - size); return __skb_put(skb, NLMSG_ALIGN(size)); } /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in * @cb: netlink callback * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, struct netlink_callback *cb, int type, int payload, int flags) { return nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, type, payload, flags); } /** * nlmsg_new - Allocate a new netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. * * Use NLMSG_DEFAULT_SIZE if the size of the payload isn't known * and a good default is needed. */ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) { return alloc_skb(nlmsg_total_size(payload), flags); } /** * nlmsg_new_large - Allocate a new netlink message with non-contiguous * physical memory * @payload: size of the message payload * * The allocated skb is unable to have frag page for shinfo->frags*, * as the NULL setting for skb->head in netlink_skb_destructor() will * bypass most of the handling in skb_release_data() */ static inline struct sk_buff *nlmsg_new_large(size_t payload) { return netlink_alloc_large_skb(nlmsg_total_size(payload), 0); } /** * nlmsg_end - Finalize a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Corrects the netlink message header to include the appeneded * attributes. Only necessary if attributes have been added to * the message. */ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) { nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; } /** * nlmsg_get_pos - return current position in netlink message * @skb: socket buffer the message is stored in * * Returns a pointer to the current tail of the message. */ static inline void *nlmsg_get_pos(struct sk_buff *skb) { return skb_tail_pointer(skb); } /** * nlmsg_trim - Trim message to a mark * @skb: socket buffer the message is stored in * @mark: mark to trim to * * Trims the message to the provided mark. */ static inline void nlmsg_trim(struct sk_buff *skb, const void *mark) { if (mark) { WARN_ON((unsigned char *) mark < skb->data); skb_trim(skb, (unsigned char *) mark - skb->data); } } /** * nlmsg_cancel - Cancel construction of a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Removes the complete netlink message including all * attributes from the socket buffer again. */ static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) { nlmsg_trim(skb, nlh); } /** * nlmsg_free - drop a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_free(struct sk_buff *skb) { kfree_skb(skb); } /** * nlmsg_consume - free a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_consume(struct sk_buff *skb) { consume_skb(skb); } /** * nlmsg_multicast_filtered - multicast a netlink message with filter function * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags * @filter: filter function * @filter_data: filter function private data * * Return: 0 on success, negative error code for failure. */ static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags, netlink_filter_fn filter, void *filter_data) { int err; NETLINK_CB(skb).dst_group = group; err = netlink_broadcast_filtered(sk, skb, portid, group, flags, filter, filter_data); if (err > 0) err = 0; return err; } /** * nlmsg_multicast - multicast a netlink message * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return nlmsg_multicast_filtered(sk, skb, portid, group, flags, NULL, NULL); } /** * nlmsg_unicast - unicast a netlink message * @sk: netlink socket to spread message to * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 portid) { int err; err = netlink_unicast(sk, skb, portid, MSG_DONTWAIT); if (err > 0) err = 0; return err; } /** * nlmsg_for_each_msg - iterate over a stream of messages * @pos: loop counter, set to current message * @head: head of message stream * @len: length of message stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_msg(pos, head, len, rem) \ for (pos = head, rem = len; \ nlmsg_ok(pos, rem); \ pos = nlmsg_next(pos, &(rem))) /** * nl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @nlh: netlink message header to write the flag to * * This function checks if the sequence (generation) number changed during dump * and if it did, advertises it in the netlink message header. * * The correct way to use it is to set cb->seq to the generation counter when * all locks for dumping have been acquired, and then call this function for * each message that is generated. * * Note that due to initialisation concerns, 0 is an invalid sequence number * and must not be used by code that uses this functionality. */ static inline void nl_dump_check_consistent(struct netlink_callback *cb, struct nlmsghdr *nlh) { if (cb->prev_seq && cb->seq != cb->prev_seq) nlh->nlmsg_flags |= NLM_F_DUMP_INTR; cb->prev_seq = cb->seq; } /************************************************************************** * Netlink Attributes **************************************************************************/ /** * nla_attr_size - length of attribute not including padding * @payload: length of payload */ static inline int nla_attr_size(int payload) { return NLA_HDRLEN + payload; } /** * nla_total_size - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size(int payload) { return NLA_ALIGN(nla_attr_size(payload)); } /** * nla_padlen - length of padding at the tail of attribute * @payload: length of payload */ static inline int nla_padlen(int payload) { return nla_total_size(payload) - nla_attr_size(payload); } /** * nla_type - attribute type * @nla: netlink attribute */ static inline int nla_type(const struct nlattr *nla) { return nla->nla_type & NLA_TYPE_MASK; } /** * nla_data - head of payload * @nla: netlink attribute */ static inline void *nla_data(const struct nlattr *nla) { return (char *) nla + NLA_HDRLEN; } /** * nla_len - length of payload * @nla: netlink attribute */ static inline u16 nla_len(const struct nlattr *nla) { return nla->nla_len - NLA_HDRLEN; } /** * nla_ok - check if the netlink attribute fits into the remaining bytes * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream */ static inline int nla_ok(const struct nlattr *nla, int remaining) { return remaining >= (int) sizeof(*nla) && nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } /** * nla_next - next netlink attribute in attribute stream * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream * * Returns the next netlink attribute in the attribute stream and * decrements remaining by the size of the current attribute. */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) { unsigned int totlen = NLA_ALIGN(nla->nla_len); *remaining -= totlen; return (struct nlattr *) ((char *) nla + totlen); } /** * nla_find_nested - find attribute in a set of nested attributes * @nla: attribute containing the nested attributes * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr * nla_find_nested(const struct nlattr *nla, int attrtype) { return nla_find(nla_data(nla), nla_len(nla), attrtype); } /** * nla_parse_nested - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (!(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing"); return -EINVAL; } return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_nested_deprecated - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_put_u8 - Add a u8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) { /* temporary variables to work around GCC PR81715 with asan-stack=1 */ u8 tmp = value; return nla_put(skb, attrtype, sizeof(u8), &tmp); } /** * nla_put_u16 - Add a u16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) { u16 tmp = value; return nla_put(skb, attrtype, sizeof(u16), &tmp); } /** * nla_put_be16 - Add a __be16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put(skb, attrtype, sizeof(__be16), &tmp); } /** * nla_put_net16 - Add 16-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le16 - Add a __le16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) { __le16 tmp = value; return nla_put(skb, attrtype, sizeof(__le16), &tmp); } /** * nla_put_u32 - Add a u32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) { u32 tmp = value; return nla_put(skb, attrtype, sizeof(u32), &tmp); } /** * nla_put_uint - Add a variable-size unsigned int to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_uint(struct sk_buff *skb, int attrtype, u64 value) { u64 tmp64 = value; u32 tmp32 = value; if (tmp64 == tmp32) return nla_put_u32(skb, attrtype, tmp32); return nla_put(skb, attrtype, sizeof(u64), &tmp64); } /** * nla_put_be32 - Add a __be32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put(skb, attrtype, sizeof(__be32), &tmp); } /** * nla_put_net32 - Add 32-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le32 - Add a __le32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) { __le32 tmp = value; return nla_put(skb, attrtype, sizeof(__le32), &tmp); } /** * nla_put_u64_64bit - Add a u64 netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, u64 value, int padattr) { u64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_be64 - Add a __be64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr); } /** * nla_put_net64 - Add 64-bit network byte order nlattr to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp, padattr); } /** * nla_put_le64 - Add a __le64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, int padattr) { __le64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr); } /** * nla_put_s8 - Add a s8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) { s8 tmp = value; return nla_put(skb, attrtype, sizeof(s8), &tmp); } /** * nla_put_s16 - Add a s16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) { s16 tmp = value; return nla_put(skb, attrtype, sizeof(s16), &tmp); } /** * nla_put_s32 - Add a s32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) { s32 tmp = value; return nla_put(skb, attrtype, sizeof(s32), &tmp); } /** * nla_put_s64 - Add a s64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, int padattr) { s64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } /** * nla_put_sint - Add a variable-size signed int to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_sint(struct sk_buff *skb, int attrtype, s64 value) { s64 tmp64 = value; s32 tmp32 = value; if (tmp64 == tmp32) return nla_put_s32(skb, attrtype, tmp32); return nla_put(skb, attrtype, sizeof(s64), &tmp64); } /** * nla_put_string - Add a string netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @str: NUL terminated string */ static inline int nla_put_string(struct sk_buff *skb, int attrtype, const char *str) { return nla_put(skb, attrtype, strlen(str) + 1, str); } /** * nla_put_flag - Add a flag netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type */ static inline int nla_put_flag(struct sk_buff *skb, int attrtype) { return nla_put(skb, attrtype, 0, NULL); } /** * nla_put_msecs - Add a msecs netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @njiffies: number of jiffies to convert to msecs * @padattr: attribute type for the padding */ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, unsigned long njiffies, int padattr) { u64 tmp = jiffies_to_msecs(njiffies); return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_in_addr - Add an IPv4 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv4 address */ static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, __be32 addr) { __be32 tmp = addr; return nla_put_be32(skb, attrtype, tmp); } /** * nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv6 address */ static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype, const struct in6_addr *addr) { return nla_put(skb, attrtype, sizeof(*addr), addr); } /** * nla_put_bitfield32 - Add a bitfield32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: value carrying bits * @selector: selector of valid bits */ static inline int nla_put_bitfield32(struct sk_buff *skb, int attrtype, __u32 value, __u32 selector) { struct nla_bitfield32 tmp = { value, selector, }; return nla_put(skb, attrtype, sizeof(tmp), &tmp); } /** * nla_get_u32 - return payload of u32 attribute * @nla: u32 netlink attribute */ static inline u32 nla_get_u32(const struct nlattr *nla) { return *(u32 *) nla_data(nla); } /** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ static inline __be32 nla_get_be32(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ static inline __le32 nla_get_le32(const struct nlattr *nla) { return *(__le32 *) nla_data(nla); } /** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ static inline u16 nla_get_u16(const struct nlattr *nla) { return *(u16 *) nla_data(nla); } /** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ static inline __be16 nla_get_be16(const struct nlattr *nla) { return *(__be16 *) nla_data(nla); } /** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ static inline __le16 nla_get_le16(const struct nlattr *nla) { return *(__le16 *) nla_data(nla); } /** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ static inline u8 nla_get_u8(const struct nlattr *nla) { return *(u8 *) nla_data(nla); } /** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ static inline u64 nla_get_u64(const struct nlattr *nla) { u64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_uint - return payload of uint attribute * @nla: uint netlink attribute */ static inline u64 nla_get_uint(const struct nlattr *nla) { if (nla_len(nla) == sizeof(u32)) return nla_get_u32(nla); return nla_get_u64(nla); } /** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ static inline __be64 nla_get_be64(const struct nlattr *nla) { __be64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ static inline __le64 nla_get_le64(const struct nlattr *nla) { return *(__le64 *) nla_data(nla); } /** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ static inline s32 nla_get_s32(const struct nlattr *nla) { return *(s32 *) nla_data(nla); } /** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ static inline s16 nla_get_s16(const struct nlattr *nla) { return *(s16 *) nla_data(nla); } /** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ static inline s8 nla_get_s8(const struct nlattr *nla) { return *(s8 *) nla_data(nla); } /** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ static inline s64 nla_get_s64(const struct nlattr *nla) { s64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_sint - return payload of uint attribute * @nla: uint netlink attribute */ static inline s64 nla_get_sint(const struct nlattr *nla) { if (nla_len(nla) == sizeof(s32)) return nla_get_s32(nla); return nla_get_s64(nla); } /** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ static inline int nla_get_flag(const struct nlattr *nla) { return !!nla; } /** * nla_get_msecs - return payload of msecs attribute * @nla: msecs netlink attribute * * Returns the number of milliseconds in jiffies. */ static inline unsigned long nla_get_msecs(const struct nlattr *nla) { u64 msecs = nla_get_u64(nla); return msecs_to_jiffies((unsigned long) msecs); } /** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ static inline __be32 nla_get_in_addr(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) { struct in6_addr tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_bitfield32 - return payload of 32 bitfield attribute * @nla: nla_bitfield32 attribute */ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) { struct nla_bitfield32 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_memdup - duplicate attribute memory (kmemdup) * @src: netlink attribute to duplicate from * @gfp: GFP mask */ static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp) { return kmemdup_noprof(nla_data(src), nla_len(src), gfp); } #define nla_memdup(...) alloc_hooks(nla_memdup_noprof(__VA_ARGS__)) /** * nla_nest_start_noflag - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * This function exists for backward compatibility to use in APIs which never * marked their nest attributes with NLA_F_NESTED flag. New APIs should use * nla_nest_start() which sets the flag. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, int attrtype) { struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb); if (nla_put(skb, attrtype, 0, NULL) < 0) return NULL; return start; } /** * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED * flag. This is the preferred function to use in new code. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) { return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED); } /** * nla_nest_end - Finalize nesting of attributes * @skb: socket buffer the attributes are stored in * @start: container attribute * * Corrects the container attribute header to include the all * appeneded attributes. * * Returns the total data length of the skb. */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { start->nla_len = skb_tail_pointer(skb) - (unsigned char *)start; return skb->len; } /** * nla_nest_cancel - Cancel nesting of attributes * @skb: socket buffer the message is stored in * @start: container attribute * * Removes the container attribute and including all nested * attributes. Returns -EMSGSIZE */ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) { nlmsg_trim(skb, start); } /** * __nla_validate_nested - Validate a stream of nested attributes * @start: container attribute * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be * ignored. See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate(nla_data(start), nla_len(start), maxtype, policy, validate, extack); } static inline int nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_STRICT, extack); } static inline int nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute * @skb: socket buffer the message is stored in * * Return true if padding is needed to align the next attribute (nla_data()) to * a 64-bit aligned area. */ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) { #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS /* The nlattr header is 4 bytes in size, that's why we test * if the skb->data _is_ aligned. A NOP attribute, plus * nlattr header for next attribute, will make nla_data() * 8-byte aligned. */ if (IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) return true; #endif return false; } /** * nla_align_64bit - 64-bit align the nla_data() of next attribute * @skb: socket buffer the message is stored in * @padattr: attribute type for the padding * * Conditionally emit a padding netlink attribute in order to make * the next attribute we emit have a 64-bit aligned nla_data() area. * This will only be done in architectures which do not have * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. * * Returns zero on success or a negative error code. */ static inline int nla_align_64bit(struct sk_buff *skb, int padattr) { if (nla_need_padding_for_64bit(skb) && !nla_reserve(skb, padattr, 0)) return -EMSGSIZE; return 0; } /** * nla_total_size_64bit - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size_64bit(int payload) { return NLA_ALIGN(nla_attr_size(payload)) #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + NLA_ALIGN(nla_attr_size(0)) #endif ; } /** * nla_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr(pos, head, len, rem) \ for (pos = head, rem = len; \ nla_ok(pos, rem); \ pos = nla_next(pos, &(rem))) /** * nla_for_each_attr_type - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @type: required attribute type for @pos * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr_type(pos, type, head, len, rem) \ nla_for_each_attr(pos, head, len, rem) \ if (nla_type(pos) == type) /** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested(pos, nla, rem) \ nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** * nla_for_each_nested_type - iterate over nested attributes * @pos: loop counter, set to current attribute * @type: required attribute type for @pos * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested_type(pos, type, nla, rem) \ nla_for_each_nested(pos, nla, rem) \ if (nla_type(pos) == type) /** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream */ static inline bool nla_is_last(const struct nlattr *nla, int rem) { return nla->nla_len == rem; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range); void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range); struct netlink_policy_dump_state; int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, const struct nla_policy *policy, unsigned int maxtype); int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, const struct nla_policy *policy, unsigned int maxtype); bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); int netlink_policy_dump_write(struct sk_buff *skb, struct netlink_policy_dump_state *state); int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt); int netlink_policy_dump_write_attr(struct sk_buff *skb, const struct nla_policy *pt, int nestattr); void netlink_policy_dump_free(struct netlink_policy_dump_state *state); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/exception.h * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_EXCEPTION_H #define __ASM_EXCEPTION_H #include <asm/esr.h> #include <asm/ptrace.h> #include <linux/interrupt.h> #define __exception_irq_entry __irq_entry static inline unsigned long disr_to_esr(u64 disr) { unsigned long esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT; if ((disr & DISR_EL1_IDS) == 0) esr |= (disr & DISR_EL1_ESR_MASK); else esr |= (disr & ESR_ELx_ISS_MASK); return esr; } asmlinkage void __noreturn handle_bad_stack(struct pt_regs *regs); asmlinkage void el1t_64_sync_handler(struct pt_regs *regs); asmlinkage void el1t_64_irq_handler(struct pt_regs *regs); asmlinkage void el1t_64_fiq_handler(struct pt_regs *regs); asmlinkage void el1t_64_error_handler(struct pt_regs *regs); asmlinkage void el1h_64_sync_handler(struct pt_regs *regs); asmlinkage void el1h_64_irq_handler(struct pt_regs *regs); asmlinkage void el1h_64_fiq_handler(struct pt_regs *regs); asmlinkage void el1h_64_error_handler(struct pt_regs *regs); asmlinkage void el0t_64_sync_handler(struct pt_regs *regs); asmlinkage void el0t_64_irq_handler(struct pt_regs *regs); asmlinkage void el0t_64_fiq_handler(struct pt_regs *regs); asmlinkage void el0t_64_error_handler(struct pt_regs *regs); asmlinkage void el0t_32_sync_handler(struct pt_regs *regs); asmlinkage void el0t_32_irq_handler(struct pt_regs *regs); asmlinkage void el0t_32_fiq_handler(struct pt_regs *regs); asmlinkage void el0t_32_error_handler(struct pt_regs *regs); asmlinkage void call_on_irq_stack(struct pt_regs *regs, void (*func)(struct pt_regs *)); asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs); void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs); void do_el0_undef(struct pt_regs *regs, unsigned long esr); void do_el1_undef(struct pt_regs *regs, unsigned long esr); void do_el0_bti(struct pt_regs *regs); void do_el1_bti(struct pt_regs *regs, unsigned long esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs); void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs); void do_sve_acc(unsigned long esr, struct pt_regs *regs); void do_sme_acc(unsigned long esr, struct pt_regs *regs); void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs); void do_el0_sys(unsigned long esr, struct pt_regs *regs); void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs); void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr); void do_el0_cp15(unsigned long esr, struct pt_regs *regs); int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs); void do_el0_svc(struct pt_regs *regs); void do_el0_svc_compat(struct pt_regs *regs); void do_el0_fpac(struct pt_regs *regs, unsigned long esr); void do_el1_fpac(struct pt_regs *regs, unsigned long esr); void do_el0_mops(struct pt_regs *regs, unsigned long esr); void do_serror(struct pt_regs *regs, unsigned long esr); void do_signal(struct pt_regs *regs); void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ |
| 13 99 13 13 13 13 13 13 13 13 13 13 13 96 96 96 96 96 96 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 256 259 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/irq.c * * Copyright (C) 1992 Linus Torvalds * Modifications for ARM processor Copyright (C) 1995-2000 Russell King. * Support for Dynamic Tick Timer Copyright (C) 2004-2005 Nokia Corporation. * Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and * Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>. * Copyright (C) 2012 ARM Ltd. */ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqchip.h> #include <linux/kprobes.h> #include <linux/memory.h> #include <linux/scs.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> #include <asm/numa.h> #include <asm/softirq_stack.h> #include <asm/stacktrace.h> #include <asm/vmap_stack.h> /* Only access this in an NMI enter/exit */ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); DEFINE_PER_CPU(unsigned long *, irq_stack_ptr); DECLARE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #ifdef CONFIG_SHADOW_CALL_STACK DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #endif static void init_irq_scs(void) { int cpu; if (!scs_is_enabled()) return; for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } #else /* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); static void init_irq_stacks(void) { int cpu; for_each_possible_cpu(cpu) per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); } #endif #ifndef CONFIG_PREEMPT_RT static void ____do_softirq(struct pt_regs *regs) { __do_softirq(); } void do_softirq_own_stack(void) { call_on_irq_stack(NULL, ____do_softirq); } #endif static void default_handle_irq(struct pt_regs *regs) { panic("IRQ taken without a root IRQ handler\n"); } static void default_handle_fiq(struct pt_regs *regs) { panic("FIQ taken without a root FIQ handler\n"); } void (*handle_arch_irq)(struct pt_regs *) __ro_after_init = default_handle_irq; void (*handle_arch_fiq)(struct pt_regs *) __ro_after_init = default_handle_fiq; int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) { if (handle_arch_irq != default_handle_irq) return -EBUSY; handle_arch_irq = handle_irq; pr_info("Root IRQ handler: %ps\n", handle_irq); return 0; } int __init set_handle_fiq(void (*handle_fiq)(struct pt_regs *)) { if (handle_arch_fiq != default_handle_fiq) return -EBUSY; handle_arch_fiq = handle_fiq; pr_info("Root FIQ handler: %ps\n", handle_fiq); return 0; } void __init init_IRQ(void) { init_irq_stacks(); init_irq_scs(); irqchip_init(); if (system_uses_irq_prio_masking()) { /* * Now that we have a stack for our IRQ handler, set * the PMR/PSR pair to a consistent state. */ WARN_ON(read_sysreg(daif) & PSR_A_BIT); local_daif_restore(DAIF_PROCCTX_NOIRQ); } } |
| 159 116 32 116 116 32 116 32 105 32 32 32 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *anon_inode_make_secure_inode( const char *name, const struct inode *context_inode) { struct inode *inode; const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; error = security_inode_init_security_anon(inode, &qname, context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (make_inode) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @f_mode: [in] fmode * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Allows setting the fmode. Returns the newly created file* or an error * pointer. */ struct file *anon_inode_getfile_fmode(const char *name, const struct file_operations *fops, void *priv, int flags, fmode_t f_mode) { struct file *file; file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); if (!IS_ERR(file)) file->f_mode |= f_mode; return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); /** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns the newly created file* or an error pointer. */ struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, make_inode); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns a newly created file descriptor or an error code. */ int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); return 0; } fs_initcall(anon_inode_init); |
| 15 15 15 15 15 15 15 15 15 15 14 15 15 15 15 15 15 15 15 15 15 15 14 15 15 15 15 15 15 15 15 14 14 15 3 3 3 3 3 3 3 15 15 15 15 15 15 15 15 3 14 15 15 10 10 10 10 10 10 15 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 | // SPDX-License-Identifier: GPL-2.0-or-later /* audit.c -- Auditing support * Gateway between the kernel (e.g., selinux) and the user-space audit daemon. * System-call specific features have moved to auditsc.c * * Copyright 2003-2007 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> * * Goals: 1) Integrate fully with Security Modules. * 2) Minimal run-time overhead: * a) Minimal when syscall auditing is disabled (audit_enable=0). * b) Small when syscall auditing is enabled and no audit record * is generated (defer as much work as possible to record * generation time): * i) context is allocated, * ii) names from getname are stored without a copy, and * iii) inode information stored from path_lookup. * 3) Ability to disable syscall auditing at boot time (audit=0). * 4) Usable by other parts of the kernel (if audit_log* is called, * then a syscall record will be generated automatically for the * current syscall). * 5) Netlink interface to user-space. * 6) Support low-overhead kernel-based filtering to minimize the * information that must be passed to user-space. * * Audit userspace, documentation, tests, and bug/issue trackers: * https://github.com/linux-audit */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/file.h> #include <linux/init.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/pid.h> #include <linux/audit.h> #include <net/sock.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/security.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <net/netns/generic.h> #include "audit.h" /* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. * (Initialization happens after skb_init is called.) */ #define AUDIT_DISABLED -1 #define AUDIT_UNINITIALIZED 0 #define AUDIT_INITIALIZED 1 static int audit_initialized = AUDIT_UNINITIALIZED; u32 audit_enabled = AUDIT_OFF; bool audit_ever_enabled = !!AUDIT_OFF; EXPORT_SYMBOL_GPL(audit_enabled); /* Default state when kernel boots without any parameters. */ static u32 audit_default = AUDIT_OFF; /* If auditing cannot proceed, audit_failure selects what happens. */ static u32 audit_failure = AUDIT_FAIL_PRINTK; /* private audit network namespace index */ static unsigned int audit_net_id; /** * struct audit_net - audit private network namespace data * @sk: communication socket */ struct audit_net { struct sock *sk; }; /** * struct auditd_connection - kernel/auditd connection state * @pid: auditd PID * @portid: netlink portid * @net: the associated network namespace * @rcu: RCU head * * Description: * This struct is RCU protected; you must either hold the RCU lock for reading * or the associated spinlock for writing. */ struct auditd_connection { struct pid *pid; u32 portid; struct net *net; struct rcu_head rcu; }; static struct auditd_connection __rcu *auditd_conn; static DEFINE_SPINLOCK(auditd_conn_lock); /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in * audit records being dropped. */ static u32 audit_rate_limit; /* Number of outstanding audit_buffers allowed. * When set to zero, this means unlimited. */ static u32 audit_backlog_limit = 64; #define AUDIT_BACKLOG_WAIT_TIME (60 * HZ) static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; /* The identity of the user shutting down the audit system. */ static kuid_t audit_sig_uid = INVALID_UID; static pid_t audit_sig_pid = -1; static u32 audit_sig_sid; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] 1) out of memory in audit_log_start [kmalloc of struct audit_buffer] 2) out of memory in audit_log_move [alloc_skb] 3) suppressed due to audit_rate_limit 4) suppressed due to audit_backlog_limit */ static atomic_t audit_lost = ATOMIC_INIT(0); /* Monotonically increasing sum of time the kernel has spent * waiting while the backlog limit is exceeded. */ static atomic_t audit_backlog_wait_time_actual = ATOMIC_INIT(0); /* Hash for inode-based rules */ struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; static struct kmem_cache *audit_buffer_cache; /* queue msgs to send via kauditd_task */ static struct sk_buff_head audit_queue; /* queue msgs due to temporary unicast send problems */ static struct sk_buff_head audit_retry_queue; /* queue msgs waiting for new auditd connection */ static struct sk_buff_head audit_hold_queue; /* queue servicing thread */ static struct task_struct *kauditd_task; static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); /* waitqueue for callers who are blocked on the audit backlog */ static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION, .mask = -1, .features = 0, .lock = 0,}; static char *audit_feature_names[2] = { "only_unset_loginuid", "loginuid_immutable", }; /** * struct audit_ctl_mutex - serialize requests from userspace * @lock: the mutex used for locking * @owner: the task which owns the lock * * Description: * This is the lock struct used to ensure we only process userspace requests * in an orderly fashion. We can't simply use a mutex/lock here because we * need to track lock ownership so we don't end up blocking the lock owner in * audit_log_start() or similar. */ static struct audit_ctl_mutex { struct mutex lock; void *owner; } audit_cmd_mutex; /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting * audit records. Since printk uses a 1024 byte buffer, this buffer * should be at least that large. */ #define AUDIT_BUFSIZ 1024 /* The audit_buffer is used when formatting an audit record. The caller * locks briefly to get the record off the freelist or to allocate the * buffer, and locks briefly to send the buffer to the netlink layer or * to place it on a transmit queue. Multiple audit_buffers can be in * use simultaneously. */ struct audit_buffer { struct sk_buff *skb; /* formatted skb ready to send */ struct audit_context *ctx; /* NULL or associated context */ gfp_t gfp_mask; }; struct audit_reply { __u32 portid; struct net *net; struct sk_buff *skb; }; /** * auditd_test_task - Check to see if a given task is an audit daemon * @task: the task to check * * Description: * Return 1 if the task is a registered audit daemon, 0 otherwise. */ int auditd_test_task(struct task_struct *task) { int rc; struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); rc = (ac && ac->pid == task_tgid(task) ? 1 : 0); rcu_read_unlock(); return rc; } /** * audit_ctl_lock - Take the audit control lock */ void audit_ctl_lock(void) { mutex_lock(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = current; } /** * audit_ctl_unlock - Drop the audit control lock */ void audit_ctl_unlock(void) { audit_cmd_mutex.owner = NULL; mutex_unlock(&audit_cmd_mutex.lock); } /** * audit_ctl_owner_current - Test to see if the current task owns the lock * * Description: * Return true if the current task owns the audit control lock, false if it * doesn't own the lock. */ static bool audit_ctl_owner_current(void) { return (current == audit_cmd_mutex.owner); } /** * auditd_pid_vnr - Return the auditd PID relative to the namespace * * Description: * Returns the PID in relation to the namespace, 0 on failure. */ static pid_t auditd_pid_vnr(void) { pid_t pid; const struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac || !ac->pid) pid = 0; else pid = pid_vnr(ac->pid); rcu_read_unlock(); return pid; } /** * audit_get_sk - Return the audit socket for the given network namespace * @net: the destination network namespace * * Description: * Returns the sock pointer if valid, NULL otherwise. The caller must ensure * that a reference is held for the network namespace while the sock is in use. */ static struct sock *audit_get_sk(const struct net *net) { struct audit_net *aunet; if (!net) return NULL; aunet = net_generic(net, audit_net_id); return aunet->sk; } void audit_panic(const char *message) { switch (audit_failure) { case AUDIT_FAIL_SILENT: break; case AUDIT_FAIL_PRINTK: if (printk_ratelimit()) pr_err("%s\n", message); break; case AUDIT_FAIL_PANIC: panic("audit: %s\n", message); break; } } static inline int audit_rate_check(void) { static unsigned long last_check = 0; static int messages = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int retval = 0; if (!audit_rate_limit) return 1; spin_lock_irqsave(&lock, flags); if (++messages < audit_rate_limit) { retval = 1; } else { now = jiffies; if (time_after(now, last_check + HZ)) { last_check = now; messages = 0; retval = 1; } } spin_unlock_irqrestore(&lock, flags); return retval; } /** * audit_log_lost - conditionally log lost audit message event * @message: the message stating reason for lost audit message * * Emit at least 1 message per second, even if audit_rate_check is * throttling. * Always increment the lost messages counter. */ void audit_log_lost(const char *message) { static unsigned long last_msg = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int print; atomic_inc(&audit_lost); print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit); if (!print) { spin_lock_irqsave(&lock, flags); now = jiffies; if (time_after(now, last_msg + HZ)) { print = 1; last_msg = now; } spin_unlock_irqrestore(&lock, flags); } if (print) { if (printk_ratelimit()) pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n", atomic_read(&audit_lost), audit_rate_limit, audit_backlog_limit); audit_panic(message); } } static int audit_log_config_change(char *function_name, u32 new, u32 old, int allow_changes) { struct audit_buffer *ab; int rc = 0; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (unlikely(!ab)) return rc; audit_log_format(ab, "op=set %s=%u old=%u ", function_name, new, old); audit_log_session_info(ab); rc = audit_log_task_context(ab); if (rc) allow_changes = 0; /* Something weird, deny request */ audit_log_format(ab, " res=%d", allow_changes); audit_log_end(ab); return rc; } static int audit_do_config_change(char *function_name, u32 *to_change, u32 new) { int allow_changes, rc = 0; u32 old = *to_change; /* check if we are locked */ if (audit_enabled == AUDIT_LOCKED) allow_changes = 0; else allow_changes = 1; if (audit_enabled != AUDIT_OFF) { rc = audit_log_config_change(function_name, new, old, allow_changes); if (rc) allow_changes = 0; } /* If we are allowed, make the change */ if (allow_changes == 1) *to_change = new; /* Not allowed, update reason */ else if (rc == 0) rc = -EPERM; return rc; } static int audit_set_rate_limit(u32 limit) { return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit); } static int audit_set_backlog_limit(u32 limit) { return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit); } static int audit_set_backlog_wait_time(u32 timeout) { return audit_do_config_change("audit_backlog_wait_time", &audit_backlog_wait_time, timeout); } static int audit_set_enabled(u32 state) { int rc; if (state > AUDIT_LOCKED) return -EINVAL; rc = audit_do_config_change("audit_enabled", &audit_enabled, state); if (!rc) audit_ever_enabled |= !!state; return rc; } static int audit_set_failure(u32 state) { if (state != AUDIT_FAIL_SILENT && state != AUDIT_FAIL_PRINTK && state != AUDIT_FAIL_PANIC) return -EINVAL; return audit_do_config_change("audit_failure", &audit_failure, state); } /** * auditd_conn_free - RCU helper to release an auditd connection struct * @rcu: RCU head * * Description: * Drop any references inside the auditd connection tracking struct and free * the memory. */ static void auditd_conn_free(struct rcu_head *rcu) { struct auditd_connection *ac; ac = container_of(rcu, struct auditd_connection, rcu); put_pid(ac->pid); put_net(ac->net); kfree(ac); } /** * auditd_set - Set/Reset the auditd connection state * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer * @skb: the netlink command from the audit daemon * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ static int auditd_set(struct pid *pid, u32 portid, struct net *net, struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; struct nlmsghdr *nlh; if (!pid || !net) return -EINVAL; ac_new = kzalloc(sizeof(*ac_new), GFP_KERNEL); if (!ac_new) return -ENOMEM; ac_new->pid = get_pid(pid); ac_new->portid = portid; ac_new->net = get_net(net); /* send the ack now to avoid a race with the queue backlog */ if (*ack) { nlh = nlmsg_hdr(skb); netlink_ack(skb, nlh, 0, NULL); *ack = false; } spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); rcu_assign_pointer(auditd_conn, ac_new); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); return 0; } /** * kauditd_printk_skb - Print the audit record to the ring buffer * @skb: audit record * * Whatever the reason, this packet may not make it to the auditd connection * so write it via printk so the information isn't completely lost. */ static void kauditd_printk_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); char *data = nlmsg_data(nlh); if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit()) pr_notice("type=%d %s\n", nlh->nlmsg_type, data); } /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { /* put the record back in the queue */ skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this * function is called we haven't given up yet on sending the record, but things * are not looking good. The first thing we want to do is try to write the * record via printk and then see if we want to try and hold on to the record * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ if (!audit_default) goto drop; /* the hold queue is only for when the daemon goes away completely, * not -EAGAIN failures; if we are in a -EAGAIN state requeue the * record on the retry queue unless it's full, in which case drop it */ if (error == -EAGAIN) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } audit_log_lost("kauditd retry queue overflow"); goto drop; } /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); return; } /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } /* we have to drop the record, send it via printk as a last effort */ kauditd_printk_skb(skb); audit_log_lost("kauditd retry queue overflow"); kfree_skb(skb); } /** * auditd_reset - Disconnect the auditd connection * @ac: auditd connection state * * Description: * Break the auditd/kauditd connection and move all the queued records into the * hold queue in case auditd reconnects. It is important to note that the @ac * pointer should never be dereferenced inside this function as it may be NULL * or invalid, you can only compare the memory address! If @ac is NULL then * the connection will always be reset. */ static void auditd_reset(const struct auditd_connection *ac) { unsigned long flags; struct sk_buff *skb; struct auditd_connection *ac_old; /* if it isn't already broken, break the connection */ spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); if (ac && ac != ac_old) { /* someone already registered a new auditd connection */ spin_unlock_irqrestore(&auditd_conn_lock, flags); return; } rcu_assign_pointer(auditd_conn, NULL); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) kauditd_hold_skb(skb, -ECONNREFUSED); } /** * auditd_send_unicast_skb - Send a record via unicast to auditd * @skb: audit record * * Description: * Send a skb to the audit daemon, returns positive/zero values on success and * negative values on failure; in all cases the skb will be consumed by this * function. If the send results in -ECONNREFUSED the connection with auditd * will be reset. This function may sleep so callers should not hold any locks * where this would cause a problem. */ static int auditd_send_unicast_skb(struct sk_buff *skb) { int rc; u32 portid; struct net *net; struct sock *sk; struct auditd_connection *ac; /* NOTE: we can't call netlink_unicast while in the RCU section so * take a reference to the network namespace and grab local * copies of the namespace, the sock, and the portid; the * namespace and sock aren't going to go away while we hold a * reference and if the portid does become invalid after the RCU * section netlink_unicast() should safely return an error */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); kfree_skb(skb); rc = -ECONNREFUSED; goto err; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); rc = netlink_unicast(sk, skb, portid, 0); put_net(net); if (rc < 0) goto err; return rc; err: if (ac && rc == -ECONNREFUSED) auditd_reset(ac); return rc; } /** * kauditd_send_queue - Helper for kauditd_thread to flush skb queues * @sk: the sending sock * @portid: the netlink destination * @queue: the skb queue to process * @retry_limit: limit on number of netlink unicast failures * @skb_hook: per-skb hook for additional processing * @err_hook: hook called if the skb fails the netlink unicast send * * Description: * Run through the given queue and attempt to send the audit records to auditd, * returns zero on success, negative values on failure. It is up to the caller * to ensure that the @sk is valid for the duration of this function. * */ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; struct sk_buff *skb = NULL; struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ skb_tail = skb_peek_tail(queue); while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) (*err_hook)(skb, -ECONNREFUSED); continue; } retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ continue; } else goto retry; } else { /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } return (rc >= 0 ? 0 : rc); } /* * kauditd_send_multicast_skb - Send a record to any multicast listeners * @skb: audit record * * Description: * Write a multicast message to anyone listening in the initial network * namespace. This function doesn't consume an skb as might be expected since * it has to copy it anyways. */ static void kauditd_send_multicast_skb(struct sk_buff *skb) { struct sk_buff *copy; struct sock *sock = audit_get_sk(&init_net); struct nlmsghdr *nlh; /* NOTE: we are not taking an additional reference for init_net since * we don't have to worry about it going away */ if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) return; /* * The seemingly wasteful skb_copy() rather than bumping the refcount * using skb_get() is necessary because non-standard mods are made to * the skb by the original kaudit unicast socket send routine. The * existing auditd daemon assumes this breakage. Fixing this would * require co-ordinating a change in the established protocol between * the kaudit kernel subsystem and the auditd userspace code. There is * no reason for new multicast clients to continue with this * non-compliance. */ copy = skb_copy(skb, GFP_KERNEL); if (!copy) return; nlh = nlmsg_hdr(copy); nlh->nlmsg_len = skb->len; nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL); } /** * kauditd_thread - Worker thread to send audit records to userspace * @dummy: unused */ static int kauditd_thread(void *dummy) { int rc; u32 portid = 0; struct net *net = NULL; struct sock *sk = NULL; struct auditd_connection *ac; #define UNICAST_RETRIES 5 set_freezable(); while (!kthread_should_stop()) { /* NOTE: see the lock comments in auditd_send_unicast_skb() */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); goto main_queue; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); /* attempt to flush the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_hold_queue, UNICAST_RETRIES, NULL, kauditd_rehold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } /* attempt to flush the retry queue */ rc = kauditd_send_queue(sk, portid, &audit_retry_queue, UNICAST_RETRIES, NULL, kauditd_hold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } main_queue: /* process the main queue - do the multicast send and attempt * unicast, dump failed record sends to the retry queue; if * sk == NULL due to previous failures we will just do the * multicast send and move the record to the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_queue, 1, kauditd_send_multicast_skb, (sk ? kauditd_retry_skb : kauditd_hold_skb)); if (ac && rc < 0) auditd_reset(ac); sk = NULL; /* drop our netns reference, no auditd sends past this line */ if (net) { put_net(net); net = NULL; } /* we have processed all the queues so wake everyone */ wake_up(&audit_backlog_wait); /* NOTE: we want to wake up if there is anything on the queue, * regardless of if an auditd is connected, as we need to * do the multicast send and rotate records from the * main queue to the retry/hold queues */ wait_event_freezable(kauditd_wait, (skb_queue_len(&audit_queue) ? 1 : 0)); } return 0; } int audit_send_list_thread(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; struct sock *sk = audit_get_sk(dest->net); /* wait for parent to finish and send an ACK */ audit_ctl_lock(); audit_ctl_unlock(); while ((skb = __skb_dequeue(&dest->q)) != NULL) netlink_unicast(sk, skb, dest->portid, 0); put_net(dest->net); kfree(dest); return 0; } struct sk_buff *audit_make_reply(int seq, int type, int done, int multi, const void *payload, int size) { struct sk_buff *skb; struct nlmsghdr *nlh; void *data; int flags = multi ? NLM_F_MULTI : 0; int t = done ? NLMSG_DONE : type; skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return NULL; nlh = nlmsg_put(skb, 0, seq, t, size, flags); if (!nlh) goto out_kfree_skb; data = nlmsg_data(nlh); memcpy(data, payload, size); return skb; out_kfree_skb: kfree_skb(skb); return NULL; } static void audit_free_reply(struct audit_reply *reply) { if (!reply) return; kfree_skb(reply->skb); if (reply->net) put_net(reply->net); kfree(reply); } static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; audit_ctl_lock(); audit_ctl_unlock(); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0); reply->skb = NULL; audit_free_reply(reply); return 0; } /** * audit_send_reply - send an audit reply message via netlink * @request_skb: skb of request we are replying to (used to target the reply) * @seq: sequence number * @type: audit message type * @done: done (last) flag * @multi: multi-part message flag * @payload: payload data * @size: payload size * * Allocates a skb, builds the netlink message, and sends it to the port id. */ static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { struct task_struct *tsk; struct audit_reply *reply; reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (!reply) return; reply->skb = audit_make_reply(seq, type, done, multi, payload, size); if (!reply->skb) goto err; reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); reply->portid = NETLINK_CB(request_skb).portid; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); if (IS_ERR(tsk)) goto err; return; err: audit_free_reply(reply); } /* * Check for appropriate CAP_AUDIT_ capabilities on incoming audit * control messages. */ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; /* Only support initial user namespace for now. */ /* * We return ECONNREFUSED because it tricks userspace into thinking * that audit was not configured into the kernel. Lots of users * configure their PAM stack (because that's what the distro does) * to reject login if unable to send messages to audit. If we return * ECONNREFUSED the PAM stack thinks the kernel does not have audit * configured in and will let login proceed. If we return EPERM * userspace will reject all logins. This should be removed when we * support non init namespaces!! */ if (current_user_ns() != &init_user_ns) return -ECONNREFUSED; switch (msg_type) { case AUDIT_LIST: case AUDIT_ADD: case AUDIT_DEL: return -EOPNOTSUPP; case AUDIT_GET: case AUDIT_SET: case AUDIT_GET_FEATURE: case AUDIT_SET_FEATURE: case AUDIT_LIST_RULES: case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: case AUDIT_SIGNAL_INFO: case AUDIT_TTY_GET: case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: /* Only support auditd and auditctl in initial pid namespace * for now. */ if (task_active_pid_ns(current) != &init_pid_ns) return -EPERM; if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ err = -EINVAL; } return err; } static void audit_log_common_recv_msg(struct audit_context *context, struct audit_buffer **ab, u16 msg_type) { uid_t uid = from_kuid(&init_user_ns, current_uid()); pid_t pid = task_tgid_nr(current); if (!audit_enabled && msg_type != AUDIT_USER_AVC) { *ab = NULL; return; } *ab = audit_log_start(context, GFP_KERNEL, msg_type); if (unlikely(!*ab)) return; audit_log_format(*ab, "pid=%d uid=%u ", pid, uid); audit_log_session_info(*ab); audit_log_task_context(*ab); } static inline void audit_log_user_recv_msg(struct audit_buffer **ab, u16 msg_type) { audit_log_common_recv_msg(NULL, ab, msg_type); } static int is_audit_feature_set(int i) { return af.features & AUDIT_FEATURE_TO_MASK(i); } static int audit_get_feature(struct sk_buff *skb) { u32 seq; seq = nlmsg_hdr(skb)->nlmsg_seq; audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature, u32 old_lock, u32 new_lock, int res) { struct audit_buffer *ab; if (audit_enabled == AUDIT_OFF) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE); if (!ab) return; audit_log_task_info(ab); audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); } static int audit_set_feature(struct audit_features *uaf) { int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); /* if there is ever a version 2 we should handle that here */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; new_lock = (uaf->lock | af.lock) & feature; old_lock = af.lock & feature; /* are we changing a locked feature? */ if (old_lock && (new_feature != old_feature)) { audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 0); return -EPERM; } } /* nothing invalid, do the changes */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; old_lock = af.lock & feature; new_lock = (uaf->lock | af.lock) & feature; if (new_feature != old_feature) audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 1); if (new_feature) af.features |= feature; else af.features &= ~feature; af.lock |= new_lock; } return 0; } static int audit_replace(struct pid *pid) { pid_t pvnr; struct sk_buff *skb; pvnr = pid_vnr(pid); skb = audit_make_reply(0, AUDIT_REPLACE, 0, 0, &pvnr, sizeof(pvnr)); if (!skb) return -ENOMEM; return auditd_send_unicast_skb(skb); } static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, bool *ack) { u32 seq; void *data; int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; char *ctx = NULL; u32 len; err = audit_netlink_ok(skb, msg_type); if (err) return err; seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { struct audit_status s; memset(&s, 0, sizeof(s)); s.enabled = audit_enabled; s.failure = audit_failure; /* NOTE: use pid_vnr() so the PID is relative to the current * namespace */ s.pid = auditd_pid_vnr(); s.rate_limit = audit_rate_limit; s.backlog_limit = audit_backlog_limit; s.lost = atomic_read(&audit_lost); s.backlog = skb_queue_len(&audit_queue); s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL; s.backlog_wait_time = audit_backlog_wait_time; s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual); audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_SET: { struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_FAILURE) { err = audit_set_failure(s.failure); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_PID) { /* NOTE: we are using the vnr PID functions below * because the s.pid value is relative to the * namespace of the caller; at present this * doesn't matter much since you can really only * run auditd from the initial pid namespace, but * something to keep in mind if this changes */ pid_t new_pid = s.pid; pid_t auditd_pid; struct pid *req_pid = task_tgid(current); /* Sanity check - PID values must match. Setting * pid to 0 is how auditd ends auditing. */ if (new_pid && (new_pid != pid_vnr(req_pid))) return -EINVAL; /* test the auditd connection */ audit_replace(req_pid); auditd_pid = auditd_pid_vnr(); if (auditd_pid) { /* replacing a healthy auditd is not allowed */ if (new_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EEXIST; } /* only current auditd can unregister itself */ if (pid_vnr(req_pid) != auditd_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EACCES; } } if (new_pid) { /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, sock_net(NETLINK_CB(skb).sk), skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, err ? 0 : 1); if (err) return err; /* try to process any backlog */ wake_up_interruptible(&kauditd_wait); } else { if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, 1); /* unregister the auditd connection */ auditd_reset(NULL); } } if (s.mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(s.rate_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) { err = audit_set_backlog_limit(s.backlog_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) { if (sizeof(s) > (size_t)nlh->nlmsg_len) return -EINVAL; if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME) return -EINVAL; err = audit_set_backlog_wait_time(s.backlog_wait_time); if (err < 0) return err; } if (s.mask == AUDIT_STATUS_LOST) { u32 lost = atomic_xchg(&audit_lost, 0); audit_log_config_change("lost", 0, lost, 1); return lost; } if (s.mask == AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) { u32 actual = atomic_xchg(&audit_backlog_wait_time_actual, 0); audit_log_config_change("backlog_wait_time_actual", 0, actual, 1); return actual; } break; } case AUDIT_GET_FEATURE: err = audit_get_feature(skb); if (err) return err; break; case AUDIT_SET_FEATURE: if (data_len < sizeof(struct audit_features)) return -EINVAL; err = audit_set_feature(data); if (err) return err; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; /* exit early if there isn't at least one character to print */ if (data_len < 2) return -EINVAL; err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ char *str = data; err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); if (err) break; } audit_log_user_recv_msg(&ab, msg_type); if (msg_type != AUDIT_USER_TTY) { /* ensure NULL termination */ str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, str); } else { audit_log_format(ab, " data="); if (str[data_len - 1] == '\0') data_len--; audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=%s audit_enabled=%d res=0", msg_type == AUDIT_ADD_RULE ? "add_rule" : "remove_rule", audit_enabled); audit_log_end(ab); return -EPERM; } err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=trim res=1"); audit_log_end(ab); break; case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; size_t msglen = data_len; char *old, *new; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; memcpy(sizes, bufp, 2 * sizeof(u32)); bufp += 2 * sizeof(u32); msglen -= 2 * sizeof(u32); old = audit_unpack_string(&bufp, &msglen, sizes[0]); if (IS_ERR(old)) { err = PTR_ERR(old); break; } new = audit_unpack_string(&bufp, &msglen, sizes[1]); if (IS_ERR(new)) { err = PTR_ERR(new); kfree(old); break; } /* OK, here comes... */ err = audit_tag_tree(old, new); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=make_equiv old="); audit_log_untrustedstring(ab, old); audit_log_format(ab, " new="); audit_log_untrustedstring(ab, new); audit_log_format(ab, " res=%d", !err); audit_log_end(ab); kfree(old); kfree(new); break; } case AUDIT_SIGNAL_INFO: len = 0; if (audit_sig_sid) { err = security_secid_to_secctx(audit_sig_sid, &ctx, &len); if (err) return err; } sig_data = kmalloc(struct_size(sig_data, ctx, len), GFP_KERNEL); if (!sig_data) { if (audit_sig_sid) security_release_secctx(ctx, len); return -ENOMEM; } sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; if (audit_sig_sid) { memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, struct_size(sig_data, ctx, len)); kfree(sig_data); break; case AUDIT_TTY_GET: { struct audit_tty_status s; unsigned int t; t = READ_ONCE(current->signal->audit_tty); s.enabled = t & AUDIT_TTY_ENABLE; s.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { struct audit_tty_status s, old; struct audit_buffer *ab; unsigned int t; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) err = -EINVAL; if (err) t = READ_ONCE(current->signal->audit_tty); else { t = s.enabled | (-s.log_passwd & AUDIT_TTY_LOG_PASSWD); t = xchg(¤t->signal->audit_tty, t); } old.enabled = t & AUDIT_TTY_ENABLE; old.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d" " old-log_passwd=%d new-log_passwd=%d res=%d", old.enabled, s.enabled, old.log_passwd, s.log_passwd, !err); audit_log_end(ab); break; } default: err = -EINVAL; break; } return err < 0 ? err : 0; } /** * audit_receive - receive messages from a netlink control socket * @skb: the message buffer * * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned */ int len; int err; nlh = nlmsg_hdr(skb); len = skb->len; audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { ack = nlh->nlmsg_flags & NLM_F_ACK; err = audit_receive_msg(skb, nlh, &ack); /* send an ack if the user asked for one and audit_receive_msg * didn't already do it, or if there was an error. */ if (ack || err) netlink_ack(skb, nlh, err, NULL); nlh = nlmsg_next(nlh, &len); } audit_ctl_unlock(); /* can't block with the ctrl lock, so penalize the sender now */ if (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { DECLARE_WAITQUEUE(wait, current); /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(audit_backlog_wait_time); remove_wait_queue(&audit_backlog_wait, &wait); } } /* Log information about who is connecting to the audit multicast socket */ static void audit_log_multicast(int group, const char *op, int err) { const struct cred *cred; struct tty_struct *tty; char comm[sizeof(current->comm)]; struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER); if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u", task_pid_nr(current), from_kuid(&init_user_ns, cred->uid), from_kuid(&init_user_ns, audit_get_loginuid(current)), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_task_context(ab); /* subj= */ audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); /* exe= */ audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err); audit_log_end(ab); } /* Run custom bind function on netlink socket group connect or bind requests. */ static int audit_multicast_bind(struct net *net, int group) { int err = 0; if (!capable(CAP_AUDIT_READ)) err = -EPERM; audit_log_multicast(group, "connect", err); return err; } static void audit_multicast_unbind(struct net *net, int group) { audit_log_multicast(group, "disconnect", 0); } static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, .bind = audit_multicast_bind, .unbind = audit_multicast_unbind, .flags = NL_CFG_F_NONROOT_RECV, .groups = AUDIT_NLGRP_MAX, }; struct audit_net *aunet = net_generic(net, audit_net_id); aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); if (aunet->sk == NULL) { audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } /* limit the timeout in case auditd is blocked/stopped */ aunet->sk->sk_sndtimeo = HZ / 10; return 0; } static void __net_exit audit_net_exit(struct net *net) { struct audit_net *aunet = net_generic(net, audit_net_id); /* NOTE: you would think that we would want to check the auditd * connection and potentially reset it here if it lives in this * namespace, but since the auditd connection tracking struct holds a * reference to this namespace (see auditd_set()) we are only ever * going to get here after that connection has been released */ netlink_kernel_release(aunet->sk); } static struct pernet_operations audit_net_ops __net_initdata = { .init = audit_net_init, .exit = audit_net_exit, .id = &audit_net_id, .size = sizeof(struct audit_net), }; /* Initialize audit support at boot time. */ static int __init audit_init(void) { int i; if (audit_initialized == AUDIT_DISABLED) return 0; audit_buffer_cache = KMEM_CACHE(audit_buffer, SLAB_PANIC); skb_queue_head_init(&audit_queue); skb_queue_head_init(&audit_retry_queue); skb_queue_head_init(&audit_hold_queue); for (i = 0; i < AUDIT_INODE_BUCKETS; i++) INIT_LIST_HEAD(&audit_inode_hash[i]); mutex_init(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = NULL; pr_info("initializing netlink subsys (%s)\n", audit_default ? "enabled" : "disabled"); register_pernet_subsys(&audit_net_ops); audit_initialized = AUDIT_INITIALIZED; kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); if (IS_ERR(kauditd_task)) { int err = PTR_ERR(kauditd_task); panic("audit: failed to start the kauditd thread (%d)\n", err); } audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "state=initialized audit_enabled=%u res=1", audit_enabled); return 0; } postcore_initcall(audit_init); /* * Process kernel command-line parameter at boot time. * audit={0|off} or audit={1|on}. */ static int __init audit_enable(char *str) { if (!strcasecmp(str, "off") || !strcmp(str, "0")) audit_default = AUDIT_OFF; else if (!strcasecmp(str, "on") || !strcmp(str, "1")) audit_default = AUDIT_ON; else { pr_err("audit: invalid 'audit' parameter value (%s)\n", str); audit_default = AUDIT_ON; } if (audit_default == AUDIT_OFF) audit_initialized = AUDIT_DISABLED; if (audit_set_enabled(audit_default)) pr_err("audit: error setting audit state (%d)\n", audit_default); pr_info("%s\n", audit_default ? "enabled (after initialization)" : "disabled (until reboot)"); return 1; } __setup("audit=", audit_enable); /* Process kernel command-line parameter at boot time. * audit_backlog_limit=<n> */ static int __init audit_backlog_limit_set(char *str) { u32 audit_backlog_limit_arg; pr_info("audit_backlog_limit: "); if (kstrtouint(str, 0, &audit_backlog_limit_arg)) { pr_cont("using default of %u, unable to parse %s\n", audit_backlog_limit, str); return 1; } audit_backlog_limit = audit_backlog_limit_arg; pr_cont("%d\n", audit_backlog_limit); return 1; } __setup("audit_backlog_limit=", audit_backlog_limit_set); static void audit_buffer_free(struct audit_buffer *ab) { if (!ab) return; kfree_skb(ab->skb); kmem_cache_free(audit_buffer_cache, ab); } static struct audit_buffer *audit_buffer_alloc(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; ab = kmem_cache_alloc(audit_buffer_cache, gfp_mask); if (!ab) return NULL; ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); if (!ab->skb) goto err; if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0)) goto err; ab->ctx = ctx; ab->gfp_mask = gfp_mask; return ab; err: audit_buffer_free(ab); return NULL; } /** * audit_serial - compute a serial number for the audit record * * Compute a serial number for the audit record. Audit records are * written to user-space as soon as they are generated, so a complete * audit record may be written in several pieces. The timestamp of the * record and this serial number are used by the user-space tools to * determine which pieces belong to the same audit record. The * (timestamp,serial) tuple is unique for each syscall and is live from * syscall entry to syscall exit. * * NOTE: Another possibility is to store the formatted records off the * audit context (for those records that have a context), and emit them * all at syscall exit. However, this could delay the reporting of * significant errors until syscall exit (or never, if the system * halts). */ unsigned int audit_serial(void) { static atomic_t serial = ATOMIC_INIT(0); return atomic_inc_return(&serial); } static inline void audit_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { ktime_get_coarse_real_ts64(t); *serial = audit_serial(); } } /** * audit_log_start - obtain an audit buffer * @ctx: audit_context (may be NULL) * @gfp_mask: type of allocation * @type: audit message type * * Returns audit_buffer pointer on success or NULL on error. * * Obtain an audit buffer. This routine does locking to obtain the * audit buffer, but then no locking is required for calls to * audit_log_*format. If the task (ctx) is a task that is currently in a * syscall, then the syscall is marked as auditable and an audit record * will be written at syscall exit. If there is no associated task, then * task context (ctx) should be NULL. */ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; struct timespec64 t; unsigned int serial; if (audit_initialized != AUDIT_INITIALIZED) return NULL; if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE))) return NULL; /* NOTE: don't ever fail/sleep on these two conditions: * 1. auditd generated record - since we need auditd to drain the * queue; also, when we are checking for auditd, compare PIDs using * task_tgid_vnr() since auditd_pid is set in audit_receive_msg() * using a PID anchored in the caller's namespace * 2. generator holding the audit_cmd_mutex - we don't want to block * while holding the mutex, although we do penalize the sender * later in audit_receive() when it is safe to block */ if (!(auditd_test_task(current) || audit_ctl_owner_current())) { long stime = audit_backlog_wait_time; while (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); /* sleep if we are allowed and we haven't exhausted our * backlog wait limit */ if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) { long rtime = stime; DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); stime = schedule_timeout(rtime); atomic_add(rtime - stime, &audit_backlog_wait_time_actual); remove_wait_queue(&audit_backlog_wait, &wait); } else { if (audit_rate_check() && printk_ratelimit()) pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n", skb_queue_len(&audit_queue), audit_backlog_limit); audit_log_lost("backlog limit exceeded"); return NULL; } } } ab = audit_buffer_alloc(ctx, gfp_mask, type); if (!ab) { audit_log_lost("out of memory in audit_log_start"); return NULL; } audit_get_stamp(ab->ctx, &t, &serial); /* cancel dummy context to enable supporting records */ if (ctx) ctx->dummy = 0; audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); return ab; } /** * audit_expand - expand skb in the audit buffer * @ab: audit_buffer * @extra: space to add at tail of the skb * * Returns 0 (no space) on failed expansion, or available space if * successful. */ static inline int audit_expand(struct audit_buffer *ab, int extra) { struct sk_buff *skb = ab->skb; int oldtail = skb_tailroom(skb); int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask); int newtail = skb_tailroom(skb); if (ret < 0) { audit_log_lost("out of memory in audit_expand"); return 0; } skb->truesize += newtail - oldtail; return newtail; } /* * Format an audit message into the audit buffer. If there isn't enough * room in the audit buffer, more room will be allocated and vsnprint * will be called a second time. Currently, we assume that a printk * can't format message larger than 1024 bytes, so we don't either. */ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, va_list args) { int len, avail; struct sk_buff *skb; va_list args2; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); if (avail == 0) { avail = audit_expand(ab, AUDIT_BUFSIZ); if (!avail) goto out; } va_copy(args2, args); len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args); if (len >= avail) { /* The printk buffer is 1024 bytes long, so if we get * here and AUDIT_BUFSIZ is at least 1024, then we can * log everything that printk could have logged. */ avail = audit_expand(ab, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) goto out_va_end; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } if (len > 0) skb_put(skb, len); out_va_end: va_end(args2); out: return; } /** * audit_log_format - format a message into the audit buffer. * @ab: audit_buffer * @fmt: format string * @...: optional parameters matching @fmt string * * All the work is done in audit_log_vformat. */ void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { va_list args; if (!ab) return; va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); } /** * audit_log_n_hex - convert a buffer to hex and append it to the audit skb * @ab: the audit_buffer * @buf: buffer to convert to hex * @len: length of @buf to be converted * * No return value; failure to expand is silently ignored. * * This function will take the passed buf and convert it into a string of * ascii hex digits. The new string is placed onto the skb. */ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { int i, avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = len<<1; if (new_len >= avail) { /* Round the buffer request up to the next multiple */ new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); for (i = 0; i < len; i++) ptr = hex_byte_pack_upper(ptr, buf[i]); *ptr = 0; skb_put(skb, len << 1); /* new string is twice the old string */ } /* * Format a string of no more than slen characters into the audit buffer, * enclosed in quote marks. */ void audit_log_n_string(struct audit_buffer *ab, const char *string, size_t slen) { int avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = slen + 3; /* enclosing quotes + null terminator */ if (new_len > avail) { avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); *ptr++ = '"'; memcpy(ptr, string, slen); ptr += slen; *ptr++ = '"'; *ptr = 0; skb_put(skb, slen + 2); /* don't include null terminator */ } /** * audit_string_contains_control - does a string need to be logged in hex * @string: string to be checked * @len: max length of the string to check */ bool audit_string_contains_control(const char *string, size_t len) { const unsigned char *p; for (p = string; p < (const unsigned char *)string + len; p++) { if (*p == '"' || *p < 0x21 || *p > 0x7e) return true; } return false; } /** * audit_log_n_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @len: length of string (not including trailing null) * @string: string to be logged * * This code will escape a string that is passed to it if the string * contains a control character, unprintable character, double quote mark, * or a space. Unescaped strings will start and end with a double quote mark. * Strings that are escaped are printed in hex (2 digits per char). * * The caller specifies the number of characters in the string to log, which may * or may not be the entire string. */ void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t len) { if (audit_string_contains_control(string, len)) audit_log_n_hex(ab, string, len); else audit_log_n_string(ab, string, len); } /** * audit_log_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @string: string to be logged * * Same as audit_log_n_untrustedstring(), except that strlen is used to * determine string length. */ void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { audit_log_n_untrustedstring(ab, string, strlen(string)); } /* This is a helper-function to print the escaped d_path */ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { char *p, *pathname; if (prefix) audit_log_format(ab, "%s", prefix); /* We will allow 11 spaces for ' (deleted)' to be appended */ pathname = kmalloc(PATH_MAX+11, ab->gfp_mask); if (!pathname) { audit_log_format(ab, "\"<no_memory>\""); return; } p = d_path(path, pathname, PATH_MAX+11); if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */ /* FIXME: can we save some information here? */ audit_log_format(ab, "\"<too_long>\""); } else audit_log_untrustedstring(ab, p); kfree(pathname); } void audit_log_session_info(struct audit_buffer *ab) { unsigned int sessionid = audit_get_sessionid(current); uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current)); audit_log_format(ab, "auid=%u ses=%u", auid, sessionid); } void audit_log_key(struct audit_buffer *ab, char *key) { audit_log_format(ab, " key="); if (key) audit_log_untrustedstring(ab, key); else audit_log_format(ab, "(null)"); } int audit_log_task_context(struct audit_buffer *ab) { char *ctx = NULL; unsigned len; int error; u32 sid; security_current_getsecid_subj(&sid); if (!sid) return 0; error = security_secid_to_secctx(sid, &ctx, &len); if (error) { if (error != -EINVAL) goto error_path; return 0; } audit_log_format(ab, " subj=%s", ctx); security_release_secctx(ctx, len); return 0; error_path: audit_panic("error in audit_log_task_context"); return error; } EXPORT_SYMBOL(audit_log_task_context); void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm) { struct file *exe_file; if (!mm) goto out_null; exe_file = get_mm_exe_file(mm); if (!exe_file) goto out_null; audit_log_d_path(ab, " exe=", &exe_file->f_path); fput(exe_file); return; out_null: audit_log_format(ab, " exe=(null)"); } struct tty_struct *audit_get_tty(void) { struct tty_struct *tty = NULL; unsigned long flags; spin_lock_irqsave(¤t->sighand->siglock, flags); if (current->signal) tty = tty_kref_get(current->signal->tty); spin_unlock_irqrestore(¤t->sighand->siglock, flags); return tty; } void audit_put_tty(struct tty_struct *tty) { tty_kref_put(tty); } void audit_log_task_info(struct audit_buffer *ab) { const struct cred *cred; char comm[sizeof(current->comm)]; struct tty_struct *tty; if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", task_ppid_nr(current), task_tgid_nr(current), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, cred->uid), from_kgid(&init_user_ns, cred->gid), from_kuid(&init_user_ns, cred->euid), from_kuid(&init_user_ns, cred->suid), from_kuid(&init_user_ns, cred->fsuid), from_kgid(&init_user_ns, cred->egid), from_kgid(&init_user_ns, cred->sgid), from_kgid(&init_user_ns, cred->fsgid), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); audit_log_task_context(ab); } EXPORT_SYMBOL(audit_log_task_info); /** * audit_log_path_denied - report a path restriction denial * @type: audit message type (AUDIT_ANOM_LINK, AUDIT_ANOM_CREAT, etc) * @operation: specific operation name */ void audit_log_path_denied(int type, const char *operation) { struct audit_buffer *ab; if (!audit_enabled || audit_dummy_context()) return; /* Generate log with subject, operation, outcome. */ ab = audit_log_start(audit_context(), GFP_KERNEL, type); if (!ab) return; audit_log_format(ab, "op=%s", operation); audit_log_task_info(ab); audit_log_format(ab, " res=0"); audit_log_end(ab); } /* global counter which is incremented every time something logs in */ static atomic_t session_id = ATOMIC_INIT(0); static int audit_set_loginuid_perm(kuid_t loginuid) { /* if we are unset, we don't need privs */ if (!audit_loginuid_set(current)) return 0; /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) return -EPERM; /* it is set, you need permission */ if (!capable(CAP_AUDIT_CONTROL)) return -EPERM; /* reject if this is not an unset and we don't allow that */ if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) return -EPERM; return 0; } static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, unsigned int oldsessionid, unsigned int sessionid, int rc) { struct audit_buffer *ab; uid_t uid, oldloginuid, loginuid; struct tty_struct *tty; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_LOGIN); if (!ab) return; uid = from_kuid(&init_user_ns, task_uid(current)); oldloginuid = from_kuid(&init_user_ns, koldloginuid); loginuid = from_kuid(&init_user_ns, kloginuid); tty = audit_get_tty(); audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid); audit_log_task_context(ab); audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", oldloginuid, loginuid, tty ? tty_name(tty) : "(none)", oldsessionid, sessionid, !rc); audit_put_tty(tty); audit_log_end(ab); } /** * audit_set_loginuid - set current task's loginuid * @loginuid: loginuid value * * Returns 0. * * Called (set) from fs/proc/base.c::proc_loginuid_write(). */ int audit_set_loginuid(kuid_t loginuid) { unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; kuid_t oldloginuid; int rc; oldloginuid = audit_get_loginuid(current); oldsessionid = audit_get_sessionid(current); rc = audit_set_loginuid_perm(loginuid); if (rc) goto out; /* are we setting or clearing? */ if (uid_valid(loginuid)) { sessionid = (unsigned int)atomic_inc_return(&session_id); if (unlikely(sessionid == AUDIT_SID_UNSET)) sessionid = (unsigned int)atomic_inc_return(&session_id); } current->sessionid = sessionid; current->loginuid = loginuid; out: audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); return rc; } /** * audit_signal_info - record signal info for shutting down audit subsystem * @sig: signal value * @t: task being signaled * * If the audit subsystem is being terminated, record the task (pid) * and uid that is doing that. */ int audit_signal_info(int sig, struct task_struct *t) { kuid_t uid = current_uid(), auid; if (auditd_test_task(t) && (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2)) { audit_sig_pid = task_tgid_nr(current); auid = audit_get_loginuid(current); if (uid_valid(auid)) audit_sig_uid = auid; else audit_sig_uid = uid; security_current_getsecid_subj(&audit_sig_sid); } return audit_signal_info_syscall(t); } /** * audit_log_end - end one audit record * @ab: the audit_buffer * * We can not do a netlink send inside an irq context because it blocks (last * arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a * queue and a kthread is scheduled to remove them from the queue outside the * irq context. May be called in any context. */ void audit_log_end(struct audit_buffer *ab) { struct sk_buff *skb; struct nlmsghdr *nlh; if (!ab) return; if (audit_rate_check()) { skb = ab->skb; ab->skb = NULL; /* setup the netlink header, see the comments in * kauditd_send_multicast_skb() for length quirks */ nlh = nlmsg_hdr(skb); nlh->nlmsg_len = skb->len - NLMSG_HDRLEN; /* queue the netlink packet and poke the kauditd thread */ skb_queue_tail(&audit_queue, skb); wake_up_interruptible(&kauditd_wait); } else audit_log_lost("rate limit exceeded"); audit_buffer_free(ab); } /** * audit_log - Log an audit record * @ctx: audit context * @gfp_mask: type of allocation * @type: audit message type * @fmt: format string to use * @...: variable parameters matching the format string * * This is a convenience function that calls audit_log_start, * audit_log_vformat, and audit_log_end. It may be called * in any context. */ void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { struct audit_buffer *ab; va_list args; ab = audit_log_start(ctx, gfp_mask, type); if (ab) { va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); audit_log_end(ab); } } EXPORT_SYMBOL(audit_log_start); EXPORT_SYMBOL(audit_log_end); EXPORT_SYMBOL(audit_log_format); EXPORT_SYMBOL(audit_log); |
| 84 84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM csd #if !defined(_TRACE_CSD_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CSD_H #include <linux/tracepoint.h> TRACE_EVENT(csd_queue_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, smp_call_func_t func, call_single_data_t *csd), TP_ARGS(cpu, callsite, func, csd), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, func) __field(void *, csd) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->func = func; __entry->csd = csd; ), TP_printk("cpu=%u callsite=%pS func=%ps csd=%p", __entry->cpu, __entry->callsite, __entry->func, __entry->csd) ); /* * Tracepoints for a function which is called as an effect of smp_call_function.* */ DECLARE_EVENT_CLASS(csd_function, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd), TP_STRUCT__entry( __field(void *, func) __field(void *, csd) ), TP_fast_assign( __entry->func = func; __entry->csd = csd; ), TP_printk("func=%ps, csd=%p", __entry->func, __entry->csd) ); DEFINE_EVENT(csd_function, csd_function_entry, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd) ); DEFINE_EVENT(csd_function, csd_function_exit, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd) ); #endif /* _TRACE_CSD_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 193 193 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_PAGE_EXT_H #define __LINUX_PAGE_EXT_H #include <linux/types.h> #include <linux/stacktrace.h> struct pglist_data; #ifdef CONFIG_PAGE_EXTENSION /** * struct page_ext_operations - per page_ext client operations * @offset: Offset to the client's data within page_ext. Offset is returned to * the client by page_ext_init. * @size: The size of the client data within page_ext. * @need: Function that returns true if client requires page_ext. * @init: (optional) Called to initialize client once page_exts are allocated. * @need_shared_flags: True when client is using shared page_ext->flags * field. * * Each Page Extension client must define page_ext_operations in * page_ext_ops array. */ struct page_ext_operations { size_t offset; size_t size; bool (*need)(void); void (*init)(void); bool need_shared_flags; }; /* * The page_ext_flags users must set need_shared_flags to true. */ enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, #endif }; /* * Page Extension can be considered as an extended mem_map. * A page_ext page is associated with every page descriptor. The * page_ext helps us add more information about the page. * All page_ext are allocated at boot or memory hotplug event, * then the page_ext for pfn always exists. */ struct page_ext { unsigned long flags; }; extern bool early_page_ext; extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); static inline bool early_page_ext_enabled(void) { return early_page_ext; } #ifdef CONFIG_SPARSEMEM static inline void page_ext_init_flatmem(void) { } extern void page_ext_init(void); static inline void page_ext_init_flatmem_late(void) { } #else extern void page_ext_init_flatmem(void); extern void page_ext_init_flatmem_late(void); static inline void page_ext_init(void) { } #endif extern struct page_ext *page_ext_get(const struct page *page); extern void page_ext_put(struct page_ext *page_ext); static inline void *page_ext_data(struct page_ext *page_ext, struct page_ext_operations *ops) { return (void *)(page_ext) + ops->offset; } static inline struct page_ext *page_ext_next(struct page_ext *curr) { void *next = curr; next += page_ext_size; return next; } #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; static inline bool early_page_ext_enabled(void) { return false; } static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { } static inline void page_ext_init(void) { } static inline void page_ext_init_flatmem_late(void) { } static inline void page_ext_init_flatmem(void) { } static inline struct page_ext *page_ext_get(const struct page *page) { return NULL; } static inline void page_ext_put(struct page_ext *page_ext) { } #endif /* CONFIG_PAGE_EXTENSION */ #endif /* __LINUX_PAGE_EXT_H */ |
| 152 152 152 152 152 152 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> #ifndef CONFIG_PREEMPT_RT typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) #else /* !CONFIG_PREEMPT_RT */ /* * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the * critical section while staying preemptible. */ typedef spinlock_t local_lock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define __local_lock_init(l) \ do { \ local_spin_lock_init((l)); \ } while (0) #define __local_lock(__lock) \ do { \ migrate_disable(); \ spin_lock(this_cpu_ptr((__lock))); \ } while (0) #define __local_lock_irq(lock) __local_lock(lock) #define __local_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = 0; \ __local_lock(lock); \ } while (0) #define __local_unlock(__lock) \ do { \ spin_unlock(this_cpu_ptr((__lock))); \ migrate_enable(); \ } while (0) #define __local_unlock_irq(lock) __local_unlock(lock) #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) #endif /* CONFIG_PREEMPT_RT */ |
| 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(!file->f_ep)) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_release(struct file *file) {} #endif #if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT) /* ARM OABI has an incompatible struct layout and needs a special handler */ extern struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent); #else static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { if (__put_user(revents, &uevent->events) || __put_user(data, &uevent->data)) return NULL; return uevent+1; } #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/drivers/char/serial_core.h * * Copyright (C) 2000 Deep Blue Solutions Ltd. */ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/sysrq.h> #include <uapi/linux/serial_core.h> #ifdef CONFIG_SERIAL_CORE_CONSOLE #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else #define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; struct serial_struct; struct serial_port_device; struct device; struct gpio_desc; /** * struct uart_ops -- interface between serial_core and the driver * * This structure describes all the operations that can be done on the * physical hardware. * * @tx_empty: ``unsigned int ()(struct uart_port *port)`` * * This function tests whether the transmitter fifo and shifter for the * @port is empty. If it is empty, this function should return * %TIOCSER_TEMT, otherwise return 0. If the port does not support this * operation, then it should return %TIOCSER_TEMT. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @set_mctrl: ``void ()(struct uart_port *port, unsigned int mctrl)`` * * This function sets the modem control lines for @port to the state * described by @mctrl. The relevant bits of @mctrl are: * * - %TIOCM_RTS RTS signal. * - %TIOCM_DTR DTR signal. * - %TIOCM_OUT1 OUT1 signal. * - %TIOCM_OUT2 OUT2 signal. * - %TIOCM_LOOP Set the port into loopback mode. * * If the appropriate bit is set, the signal should be driven * active. If the bit is clear, the signal should be driven * inactive. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @get_mctrl: ``unsigned int ()(struct uart_port *port)`` * * Returns the current state of modem control inputs of @port. The state * of the outputs should not be returned, since the core keeps track of * their state. The state information should include: * * - %TIOCM_CAR state of DCD signal * - %TIOCM_CTS state of CTS signal * - %TIOCM_DSR state of DSR signal * - %TIOCM_RI state of RI signal * * The bit is set if the signal is currently driven active. If * the port does not support CTS, DCD or DSR, the driver should * indicate that the signal is permanently active. If RI is * not available, the signal should not be indicated as active. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_tx: ``void ()(struct uart_port *port)`` * * Stop transmitting characters. This might be due to the CTS line * becoming inactive or the tty layer indicating we want to stop * transmission due to an %XOFF character. * * The driver should stop transmitting characters as soon as possible. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @start_tx: ``void ()(struct uart_port *port)`` * * Start transmitting characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @throttle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that input buffers for the line discipline are * close to full, and it should somehow signal that no more characters * should be sent to the serial port. * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @unthrottle() and termios modification by the * tty layer. * * @unthrottle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that characters can now be sent to the serial * port without fear of overrunning the input buffers of the line * disciplines. * * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @throttle() and termios modification by the * tty layer. * * @send_xchar: ``void ()(struct uart_port *port, char ch)`` * * Transmit a high priority character, even if the port is stopped. This * is used to implement XON/XOFF flow control and tcflow(). If the serial * driver does not implement this function, the tty core will append the * character to the circular buffer and then call start_tx() / stop_tx() * to flush the data out. * * Do not transmit if @ch == '\0' (%__DISABLED_CHAR). * * Locking: none. * Interrupts: caller dependent. * * @start_rx: ``void ()(struct uart_port *port)`` * * Start receiving characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_rx: ``void ()(struct uart_port *port)`` * * Stop receiving characters; the @port is in the process of being closed. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @enable_ms: ``void ()(struct uart_port *port)`` * * Enable the modem status interrupts. * * This method may be called multiple times. Modem status interrupts * should be disabled when the @shutdown() method is called. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @break_ctl: ``void ()(struct uart_port *port, int ctl)`` * * Control the transmission of a break signal. If @ctl is nonzero, the * break signal should be transmitted. The signal should be terminated * when another call is made with a zero @ctl. * * Locking: caller holds tty_port->mutex * * @startup: ``int ()(struct uart_port *port)`` * * Grab any interrupt resources and initialise any low level driver state. * Enable the port for reception. It should not activate RTS nor DTR; * this will be done via a separate call to @set_mctrl(). * * This method will only be called when the port is initially opened. * * Locking: port_sem taken. * Interrupts: globally disabled. * * @shutdown: ``void ()(struct uart_port *port)`` * * Disable the @port, disable any break condition that may be in effect, * and free any interrupt resources. It should not disable RTS nor DTR; * this will have already been done via a separate call to @set_mctrl(). * * Drivers must not access @port->state once this call has completed. * * This method will only be called when there are no more users of this * @port. * * Locking: port_sem taken. * Interrupts: caller dependent. * * @flush_buffer: ``void ()(struct uart_port *port)`` * * Flush any write buffers, reset any DMA state and stop any ongoing DMA * transfers. * * This will be called whenever the @port->state->xmit circular buffer is * cleared. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @set_termios: ``void ()(struct uart_port *port, struct ktermios *new, * struct ktermios *old)`` * * Change the @port parameters, including word length, parity, stop bits. * Update @port->read_status_mask and @port->ignore_status_mask to * indicate the types of events we are interested in receiving. Relevant * ktermios::c_cflag bits are: * * - %CSIZE - word size * - %CSTOPB - 2 stop bits * - %PARENB - parity enable * - %PARODD - odd parity (when %PARENB is in force) * - %ADDRB - address bit (changed through uart_port::rs485_config()). * - %CREAD - enable reception of characters (if not set, still receive * characters from the port, but throw them away). * - %CRTSCTS - if set, enable CTS status change reporting. * - %CLOCAL - if not set, enable modem status change reporting. * * Relevant ktermios::c_iflag bits are: * * - %INPCK - enable frame and parity error events to be passed to the TTY * layer. * - %BRKINT / %PARMRK - both of these enable break events to be passed to * the TTY layer. * - %IGNPAR - ignore parity and framing errors. * - %IGNBRK - ignore break errors. If %IGNPAR is also set, ignore overrun * errors as well. * * The interaction of the ktermios::c_iflag bits is as follows (parity * error given as an example): * * ============ ======= ======= ========================================= * Parity error INPCK IGNPAR * ============ ======= ======= ========================================= * n/a 0 n/a character received, marked as %TTY_NORMAL * None 1 n/a character received, marked as %TTY_NORMAL * Yes 1 0 character received, marked as %TTY_PARITY * Yes 1 1 character discarded * ============ ======= ======= ========================================= * * Other flags may be used (eg, xon/xoff characters) if your hardware * supports hardware "soft" flow control. * * Locking: caller holds tty_port->mutex * Interrupts: caller dependent. * This call must not sleep * * @set_ldisc: ``void ()(struct uart_port *port, struct ktermios *termios)`` * * Notifier for discipline change. See * Documentation/driver-api/tty/tty_ldisc.rst. * * Locking: caller holds tty_port->mutex * * @pm: ``void ()(struct uart_port *port, unsigned int state, * unsigned int oldstate)`` * * Perform any power management related activities on the specified @port. * @state indicates the new state (defined by enum uart_pm_state), * @oldstate indicates the previous state. * * This function should not be used to grab any resources. * * This will be called when the @port is initially opened and finally * closed, except when the @port is also the system console. This will * occur even if %CONFIG_PM is not set. * * Locking: none. * Interrupts: caller dependent. * * @type: ``const char *()(struct uart_port *port)`` * * Return a pointer to a string constant describing the specified @port, * or return %NULL, in which case the string 'unknown' is substituted. * * Locking: none. * Interrupts: caller dependent. * * @release_port: ``void ()(struct uart_port *port)`` * * Release any memory and IO region resources currently in use by the * @port. * * Locking: none. * Interrupts: caller dependent. * * @request_port: ``int ()(struct uart_port *port)`` * * Request any memory and IO region resources required by the port. If any * fail, no resources should be registered when this function returns, and * it should return -%EBUSY on failure. * * Locking: none. * Interrupts: caller dependent. * * @config_port: ``void ()(struct uart_port *port, int type)`` * * Perform any autoconfiguration steps required for the @port. @type * contains a bit mask of the required configuration. %UART_CONFIG_TYPE * indicates that the port requires detection and identification. * @port->type should be set to the type found, or %PORT_UNKNOWN if no * port was detected. * * %UART_CONFIG_IRQ indicates autoconfiguration of the interrupt signal, * which should be probed using standard kernel autoprobing techniques. * This is not necessary on platforms where ports have interrupts * internally hard wired (eg, system on a chip implementations). * * Locking: none. * Interrupts: caller dependent. * * @verify_port: ``int ()(struct uart_port *port, * struct serial_struct *serinfo)`` * * Verify the new serial port information contained within @serinfo is * suitable for this port type. * * Locking: none. * Interrupts: caller dependent. * * @ioctl: ``int ()(struct uart_port *port, unsigned int cmd, * unsigned long arg)`` * * Perform any port specific IOCTLs. IOCTL commands must be defined using * the standard numbering system found in <asm/ioctl.h>. * * Locking: none. * Interrupts: caller dependent. * * @poll_init: ``int ()(struct uart_port *port)`` * * Called by kgdb to perform the minimal hardware initialization needed to * support @poll_put_char() and @poll_get_char(). Unlike @startup(), this * should not request interrupts. * * Locking: %tty_mutex and tty_port->mutex taken. * Interrupts: n/a. * * @poll_put_char: ``void ()(struct uart_port *port, unsigned char ch)`` * * Called by kgdb to write a single character @ch directly to the serial * @port. It can and should block until there is space in the TX FIFO. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @poll_get_char: ``int ()(struct uart_port *port)`` * * Called by kgdb to read a single character directly from the serial * port. If data is available, it should be returned; otherwise the * function should return %NO_POLL_CHAR immediately. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int mctrl); unsigned int (*get_mctrl)(struct uart_port *); void (*stop_tx)(struct uart_port *); void (*start_tx)(struct uart_port *); void (*throttle)(struct uart_port *); void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); void (*start_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); const char *(*type)(struct uart_port *); void (*release_port)(struct uart_port *); int (*request_port)(struct uart_port *); void (*config_port)(struct uart_port *, int); int (*verify_port)(struct uart_port *, struct serial_struct *); int (*ioctl)(struct uart_port *, unsigned int, unsigned long); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct uart_port *); void (*poll_put_char)(struct uart_port *, unsigned char); int (*poll_get_char)(struct uart_port *); #endif }; #define NO_POLL_CHAR 0x00ff0000 #define UART_CONFIG_TYPE (1 << 0) #define UART_CONFIG_IRQ (1 << 1) struct uart_icount { __u32 cts; __u32 dsr; __u32 rng; __u32 dcd; __u32 rx; __u32 tx; __u32 frame; __u32 overrun; __u32 parity; __u32 brk; __u32 buf_overrun; }; typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t; struct uart_port { spinlock_t lock; /* port lock */ unsigned long iobase; /* in/out[bwl] */ unsigned char __iomem *membase; /* read/write[bwl] */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); unsigned int (*get_divisor)(struct uart_port *, unsigned int baud, unsigned int *frac); void (*set_divisor)(struct uart_port *, unsigned int baud, unsigned int quot, unsigned int quot_frac); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); void (*unthrottle)(struct uart_port *port); int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int old); void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct ktermios *termios, struct serial_rs485 *rs485); int (*iso7816_config)(struct uart_port *, struct serial_iso7816 *iso7816); unsigned int ctrl_id; /* optional serial core controller id */ unsigned int port_id; /* optional serial core port id */ unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ unsigned int fifosize; /* tx fifo size */ unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char iotype; /* io access style */ #define UPIO_UNKNOWN ((unsigned char)~0U) /* UCHAR_MAX */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ #define UPIO_MEM (SERIAL_IO_MEM) /* driver-specific */ #define UPIO_MEM32 (SERIAL_IO_MEM32) /* 32b little endian */ #define UPIO_AU (SERIAL_IO_AU) /* Au1x00 and RT288x type IO */ #define UPIO_TSI (SERIAL_IO_TSI) /* Tsi108/109 type IO */ #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ unsigned char quirks; /* internal quirks */ /* internal quirks must be updated while holding port mutex */ #define UPQ_NO_TXEN_TEST BIT(0) unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ /* flags must be updated while holding port mutex */ upf_t flags; /* * These flags must be equivalent to the flags defined in * include/uapi/linux/tty_flags.h which are the userspace definitions * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ #define UPF_FOURPORT ((__force upf_t) ASYNC_FOURPORT /* 1 */ ) #define UPF_SAK ((__force upf_t) ASYNC_SAK /* 2 */ ) #define UPF_SPD_HI ((__force upf_t) ASYNC_SPD_HI /* 4 */ ) #define UPF_SPD_VHI ((__force upf_t) ASYNC_SPD_VHI /* 5 */ ) #define UPF_SPD_CUST ((__force upf_t) ASYNC_SPD_CUST /* 0x0030 */ ) #define UPF_SPD_WARP ((__force upf_t) ASYNC_SPD_WARP /* 0x1010 */ ) #define UPF_SPD_MASK ((__force upf_t) ASYNC_SPD_MASK /* 0x1030 */ ) #define UPF_SKIP_TEST ((__force upf_t) ASYNC_SKIP_TEST /* 6 */ ) #define UPF_AUTO_IRQ ((__force upf_t) ASYNC_AUTO_IRQ /* 7 */ ) #define UPF_HARDPPS_CD ((__force upf_t) ASYNC_HARDPPS_CD /* 11 */ ) #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) #define UPF_NO_THRE_TEST ((__force upf_t) BIT_ULL(19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) BIT_ULL(20)) #define UPF_AUTO_RTS ((__force upf_t) BIT_ULL(21)) #define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ #define UPF_SOFT_FLOW ((__force upf_t) BIT_ULL(22)) #define UPF_CONS_FLOW ((__force upf_t) BIT_ULL(23)) #define UPF_SHARE_IRQ ((__force upf_t) BIT_ULL(24)) #define UPF_EXAR_EFR ((__force upf_t) BIT_ULL(25)) #define UPF_BUG_THRE ((__force upf_t) BIT_ULL(26)) /* The exact UART type is known and should not be probed. */ #define UPF_FIXED_TYPE ((__force upf_t) BIT_ULL(27)) #define UPF_BOOT_AUTOCONF ((__force upf_t) BIT_ULL(28)) #define UPF_FIXED_PORT ((__force upf_t) BIT_ULL(29)) #define UPF_DEAD ((__force upf_t) BIT_ULL(30)) #define UPF_IOREMAP ((__force upf_t) BIT_ULL(31)) #define UPF_FULL_PROBE ((__force upf_t) BIT_ULL(32)) #define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK) #define UPF_USR_MASK ((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY)) #if __UPF_CHANGE_MASK > ASYNC_FLAGS #error Change mask not equivalent to userspace-visible bit defines #endif /* * Must hold termios_rwsem, port mutex and port lock to change; * can hold any one lock to read. */ upstat_t status; #define UPSTAT_CTS_ENABLE ((__force upstat_t) (1 << 0)) #define UPSTAT_DCD_ENABLE ((__force upstat_t) (1 << 1)) #define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) #define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; unsigned int line; /* port index */ unsigned int minor; resource_size_t mapbase; /* for ioremap */ resource_size_t mapsize; struct device *dev; /* serial port physical parent device */ struct serial_port_device *port_dev; /* serial core port device */ unsigned long sysrq; /* sysrq timeout */ u8 sysrq_ch; /* char for sysrq */ unsigned char has_sysrq; unsigned char sysrq_seq; /* index in sysrq_toggle_seq */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; struct serial_rs485 rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct gpio_desc *rs485_rx_during_tx_gpio; /* Output GPIO that sets the state of RS485 RX during TX */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); } /** * uart_port_lock_irq - Lock the UART port and disable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); } /** * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage */ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); } /** * uart_port_trylock - Try to lock the UART port * @up: Pointer to UART port structure * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock(struct uart_port *up) { return spin_trylock(&up->lock); } /** * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { return spin_trylock_irqsave(&up->lock, *flags); } /** * uart_port_unlock - Unlock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_unlock(struct uart_port *up) { spin_unlock(&up->lock); } /** * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_unlock_irq(struct uart_port *up) { spin_unlock_irq(&up->lock); } /** * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts * @up: Pointer to UART port structure * @flags: The saved interrupt flags for restore */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { spin_unlock_irqrestore(&up->lock, flags); } static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); } static inline void serial_port_out(struct uart_port *up, int offset, int value) { up->serial_out(up, offset, value); } /** * enum uart_pm_state - power states for UARTs * @UART_PM_STATE_ON: UART is powered, up and operational * @UART_PM_STATE_OFF: UART is powered off * @UART_PM_STATE_UNDEFINED: sentinel */ enum uart_pm_state { UART_PM_STATE_ON = 0, UART_PM_STATE_OFF = 3, /* number taken from ACPI */ UART_PM_STATE_UNDEFINED, }; /* * This is the state information which is persistent across opens. */ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; atomic_t refcount; wait_queue_head_t remove_wait; struct uart_port *uart_port; }; #define UART_XMIT_SIZE PAGE_SIZE /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 /** * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars * @up: uart_port structure describing the port * @chars: number of characters sent * * This function advances the tail of circular xmit buffer by the number of * @chars transmitted and handles accounting of transmitted bytes (into * @up's icount.tx). */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { struct tty_port *tport = &up->state->port; kfifo_skip_count(&tport->xmit_fifo, chars); up->icount.tx += chars; } static inline unsigned int uart_fifo_out(struct uart_port *up, unsigned char *buf, unsigned int chars) { struct tty_port *tport = &up->state->port; chars = kfifo_out(&tport->xmit_fifo, buf, chars); up->icount.tx += chars; return chars; } static inline unsigned int uart_fifo_get(struct uart_port *up, unsigned char *ch) { struct tty_port *tport = &up->state->port; unsigned int chars; chars = kfifo_get(&tport->xmit_fifo, ch); up->icount.tx += chars; return chars; } struct module; struct tty_driver; struct uart_driver { struct module *owner; const char *driver_name; const char *dev_name; int major; int minor; int nr; struct console *cons; /* * these are private; the low level driver should not * touch these; they should be initialised to NULL */ struct uart_state *state; struct tty_driver *tty_driver; }; void uart_write_wakeup(struct uart_port *port); /** * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() * * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer */ enum UART_TX_FLAGS { UART_TX_NOSTOP = BIT(0), }; #define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct tty_port *__tport = &__port->state->port; \ unsigned int pending; \ \ for (; (for_test) && (tx_ready); (for_post), __port->icount.tx++) { \ if (__port->x_char) { \ (ch) = __port->x_char; \ (put_char); \ __port->x_char = 0; \ continue; \ } \ \ if (uart_tx_stopped(__port)) \ break; \ \ if (!kfifo_get(&__tport->xmit_fifo, &(ch))) \ break; \ \ (put_char); \ } \ \ (tx_done); \ \ pending = kfifo_len(&__tport->xmit_fifo); \ if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ pending; \ }) /** * uart_port_tx_limited -- transmit helper for uart_port with count limiting * @port: uart port * @ch: variable to store a character to be written to the HW * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * This helper transmits characters from the xmit buffer to the hardware using * @put_char(). It does so until @count characters are sent and while @tx_ready * evaluates to true. * * Returns: the number of characters in the xmit buffer when done. * * The expression in macro parameters shall be designed as follows: * * **tx_ready:** should evaluate to true if the HW can accept more data to * be sent. This parameter can be %true, which means the HW is always ready. * * **put_char:** shall write @ch to the device of @port. * * **tx_done:** when the write loop is done, this can perform arbitrary * action before potential invocation of ops->stop_tx() happens. If the * driver does not need to do anything, use e.g. ({}). * * For all of them, @port->lock is held, interrupts are locally disabled and * the expressions must not sleep. */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx_limited_flags -- transmit helper for uart_port with count limiting with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_limited_flags(port, ch, flags, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, flags, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx -- transmit helper for uart_port * @port: uart port * @ch: variable to store a character to be written to the HW * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) /** * uart_port_tx_flags -- transmit helper for uart_port with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); /* * Calculates FIFO drain time. */ static inline unsigned long uart_fifo_timeout(struct uart_port *port) { u64 fifo_timeout = (u64)READ_ONCE(port->frame_time) * port->fifosize; /* Add .02 seconds of slop */ fifo_timeout += 20 * NSEC_PER_MSEC; return max(nsecs_to_jiffies(fifo_timeout), 1UL); } /* Base timer interval for polling */ static inline unsigned long uart_poll_timeout(struct uart_port *port) { unsigned long timeout = uart_fifo_timeout(port); return timeout > 6 ? (timeout / 2 - 2) : 1; } /* * Console helpers. */ struct earlycon_device { struct console *con; struct uart_port port; char options[32]; /* e.g., 115200n8 */ unsigned int baud; }; struct earlycon_id { char name[15]; char name_term; /* In case compiler didn't '\0' term name */ char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); }; extern const struct earlycon_id __earlycon_table[]; extern const struct earlycon_id __earlycon_table_end[]; #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) #define EARLYCON_USED_OR_UNUSED __used #else #define EARLYCON_USED_OR_UNUSED __maybe_unused #endif #define OF_EARLYCON_DECLARE(_name, compat, fn) \ static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ EARLYCON_USED_OR_UNUSED __section("__earlycon_table") \ __aligned(__alignof__(struct earlycon_id)) \ = { .name = __stringify(_name), \ .compatible = compat, \ .setup = fn } #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; int setup_earlycon(char *buf); #else static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif /* Variant of uart_console_registered() when the console_list_lock is held. */ static inline bool uart_console_registered_locked(struct uart_port *port) { return uart_console(port) && console_is_registered_locked(port->cons); } static inline bool uart_console_registered(struct uart_port *port) { return uart_console(port) && console_is_registered(port->cons); } struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options); void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow); int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow); struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal */ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); int uart_read_port_properties(struct uart_port *port); int uart_read_and_validate_port_properties(struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); /* * Power Management */ int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; if ((tty && tty->flow.stopped) || port->hw_stopped) return 1; return 0; } static inline bool uart_cts_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_CTS_ENABLE); } static inline bool uart_softcts_mode(struct uart_port *uport) { upstat_t mask = UPSTAT_CTS_ENABLE | UPSTAT_AUTOCTS; return ((uport->status & mask) == UPSTAT_CTS_ENABLE); } /* * The following are helper functions for the low level drivers. */ void uart_handle_dcd_change(struct uart_port *uport, bool active); void uart_handle_cts_change(struct uart_port *uport, bool active); void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag); void uart_xchar_out(struct uart_port *uport, int offset); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch); static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { handle_sysrq(ch); port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { port->sysrq_ch = ch; port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock(port); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock(port); if (sysrq_ch) handle_sysrq(sysrq_ch); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock_irqrestore(port, flags); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock_irqrestore(port, flags); if (sysrq_ch) handle_sysrq(sysrq_ch); } #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { uart_port_unlock(port); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { uart_port_unlock_irqrestore(port, flags); } #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* * We do the SysRQ and SAK checking like this... */ static inline int uart_handle_break(struct uart_port *port) { struct uart_state *state = port->state; if (port->handle_break) port->handle_break(port); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL if (port->has_sysrq && uart_console(port)) { if (!port->sysrq) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return 1; } port->sysrq = 0; } #endif if (port->flags & UPF_SAK) do_SAK(state->port.tty); return 0; } /* * UART_ENABLE_MS - determine if port should enable modem status irqs */ #define UART_ENABLE_MS(port,cflag) ((port)->flags & UPF_HARDPPS_CD || \ (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_H */ |
| 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019 Arm Limited * Author: Andrew Murray <Andrew.Murray@arm.com> */ #include <linux/kvm_host.h> #include <linux/perf_event.h> static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events); /* * Given the perf event attributes and system type, determine * if we are going to need to switch counters at guest entry/exit. */ static bool kvm_pmu_switch_needed(struct perf_event_attr *attr) { /** * With VHE the guest kernel runs at EL1 and the host at EL2, * where user (EL0) is excluded then we have no reason to switch * counters. */ if (has_vhe() && attr->exclude_user) return false; /* Only switch if attributes are different */ return (attr->exclude_host != attr->exclude_guest); } struct kvm_pmu_events *kvm_get_pmu_events(void) { return this_cpu_ptr(&kvm_pmu_events); } /* * Add events to track that we may want to switch at guest entry/exit * time. */ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) pmu->events_host |= set; if (!attr->exclude_guest) pmu->events_guest |= set; } /* * Stop tracking events */ void kvm_clr_pmu_events(u32 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); if (!kvm_arm_support_pmu_v3()) return; pmu->events_host &= ~clr; pmu->events_guest &= ~clr; } #define PMEVTYPER_READ_CASE(idx) \ case idx: \ return read_sysreg(pmevtyper##idx##_el0) #define PMEVTYPER_WRITE_CASE(idx) \ case idx: \ write_sysreg(val, pmevtyper##idx##_el0); \ break #define PMEVTYPER_CASES(readwrite) \ PMEVTYPER_##readwrite##_CASE(0); \ PMEVTYPER_##readwrite##_CASE(1); \ PMEVTYPER_##readwrite##_CASE(2); \ PMEVTYPER_##readwrite##_CASE(3); \ PMEVTYPER_##readwrite##_CASE(4); \ PMEVTYPER_##readwrite##_CASE(5); \ PMEVTYPER_##readwrite##_CASE(6); \ PMEVTYPER_##readwrite##_CASE(7); \ PMEVTYPER_##readwrite##_CASE(8); \ PMEVTYPER_##readwrite##_CASE(9); \ PMEVTYPER_##readwrite##_CASE(10); \ PMEVTYPER_##readwrite##_CASE(11); \ PMEVTYPER_##readwrite##_CASE(12); \ PMEVTYPER_##readwrite##_CASE(13); \ PMEVTYPER_##readwrite##_CASE(14); \ PMEVTYPER_##readwrite##_CASE(15); \ PMEVTYPER_##readwrite##_CASE(16); \ PMEVTYPER_##readwrite##_CASE(17); \ PMEVTYPER_##readwrite##_CASE(18); \ PMEVTYPER_##readwrite##_CASE(19); \ PMEVTYPER_##readwrite##_CASE(20); \ PMEVTYPER_##readwrite##_CASE(21); \ PMEVTYPER_##readwrite##_CASE(22); \ PMEVTYPER_##readwrite##_CASE(23); \ PMEVTYPER_##readwrite##_CASE(24); \ PMEVTYPER_##readwrite##_CASE(25); \ PMEVTYPER_##readwrite##_CASE(26); \ PMEVTYPER_##readwrite##_CASE(27); \ PMEVTYPER_##readwrite##_CASE(28); \ PMEVTYPER_##readwrite##_CASE(29); \ PMEVTYPER_##readwrite##_CASE(30) /* * Read a value direct from PMEVTYPER<idx> where idx is 0-30 * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31). */ static u64 kvm_vcpu_pmu_read_evtype_direct(int idx) { switch (idx) { PMEVTYPER_CASES(READ); case ARMV8_PMU_CYCLE_IDX: return read_sysreg(pmccfiltr_el0); default: WARN_ON(1); } return 0; } /* * Write a value direct to PMEVTYPER<idx> where idx is 0-30 * or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31). */ static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val) { switch (idx) { PMEVTYPER_CASES(WRITE); case ARMV8_PMU_CYCLE_IDX: write_sysreg(val, pmccfiltr_el0); break; default: WARN_ON(1); } } /* * Modify ARMv8 PMU events to include EL0 counting */ static void kvm_vcpu_pmu_enable_el0(unsigned long events) { u64 typer; u32 counter; for_each_set_bit(counter, &events, 32) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer &= ~ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); } } /* * Modify ARMv8 PMU events to exclude EL0 counting */ static void kvm_vcpu_pmu_disable_el0(unsigned long events) { u64 typer; u32 counter; for_each_set_bit(counter, &events, 32) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer |= ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); } } /* * On VHE ensure that only guest events have EL0 counting enabled. * This is called from both vcpu_{load,put} and the sysreg handling. * Since the latter is preemptible, special care must be taken to * disable preemption. */ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; u32 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; preempt_disable(); pmu = kvm_get_pmu_events(); events_guest = pmu->events_guest; events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); preempt_enable(); } /* * On VHE ensure that only host events have EL0 counting enabled */ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; u32 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; pmu = kvm_get_pmu_events(); events_guest = pmu->events_guest; events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_host); kvm_vcpu_pmu_disable_el0(events_guest); } /* * With VHE, keep track of the PMUSERENR_EL0 value for the host EL0 on the pCPU * where PMUSERENR_EL0 for the guest is loaded, since PMUSERENR_EL0 is switched * to the value for the guest on vcpu_load(). The value for the host EL0 * will be restored on vcpu_put(), before returning to userspace. * This isn't necessary for nVHE, as the register is context switched for * every guest enter/exit. * * Return true if KVM takes care of the register. Otherwise return false. */ bool kvm_set_pmuserenr(u64 val) { struct kvm_cpu_context *hctxt; struct kvm_vcpu *vcpu; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return false; vcpu = kvm_get_running_vcpu(); if (!vcpu || !vcpu_get_flag(vcpu, PMUSERENR_ON_CPU)) return false; hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val; return true; } /* * If we interrupted the guest to update the host PMU context, make * sure we re-apply the guest EL0 state. */ void kvm_vcpu_pmu_resync_el0(void) { struct kvm_vcpu *vcpu; if (!has_vhe() || !in_interrupt()) return; vcpu = kvm_get_running_vcpu(); if (!vcpu) return; kvm_make_request(KVM_REQ_RESYNC_PMU_EL0, vcpu); } |
| 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> linux/include/linux/rbtree.h To use rbtrees you'll have to implement your own insert and search cores. This will avoid us to use callbacks and to drop drammatically performances. I know it's not the cleaner way, but in C (not in C++) to get performances and genericity... See Documentation/core-api/rbtree.rst for documentation and samples. */ #ifndef _LINUX_RBTREE_H #define _LINUX_RBTREE_H #include <linux/container_of.h> #include <linux/rbtree_types.h> #include <linux/stddef.h> #include <linux/rcupdate.h> #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */ #define RB_EMPTY_NODE(node) \ ((node)->__rb_parent_color == (unsigned long)(node)) #define RB_CLEAR_NODE(node) \ ((node)->__rb_parent_color = (unsigned long)(node)) extern void rb_insert_color(struct rb_node *, struct rb_root *); extern void rb_erase(struct rb_node *, struct rb_root *); /* Find logical next and previous nodes in a tree */ extern struct rb_node *rb_next(const struct rb_node *); extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; *rb_link = node; } static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; rcu_assign_pointer(*rb_link, node); } #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) /** * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of * given type allowing the backing memory of @pos to be invalidated * * @pos: the 'type *' to use as a loop cursor. * @n: another 'type *' to use as temporary storage * @root: 'rb_root *' of the rbtree. * @field: the name of the rb_node field within 'type'. * * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as * list_for_each_entry_safe() and allows the iteration to continue independent * of changes to @pos by the body of the loop. * * Note, however, that it cannot handle other modifications that re-order the * rbtree it is iterating over. This includes calling rb_erase() on @pos, as * rb_erase() may rebalance the tree, causing us to miss some nodes. */ #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \ pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \ typeof(*pos), field); 1; }); \ pos = n) /* Same as rb_first(), but O(1) */ #define rb_first_cached(root) (root)->rb_leftmost static inline void rb_insert_color_cached(struct rb_node *node, struct rb_root_cached *root, bool leftmost) { if (leftmost) root->rb_leftmost = node; rb_insert_color(node, &root->rb_root); } static inline struct rb_node * rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) { struct rb_node *leftmost = NULL; if (root->rb_leftmost == node) leftmost = root->rb_leftmost = rb_next(node); rb_erase(node, &root->rb_root); return leftmost; } static inline void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, struct rb_root_cached *root) { if (root->rb_leftmost == victim) root->rb_leftmost = new; rb_replace_node(victim, new, &root->rb_root); } /* * The below helper functions use 2 operators with 3 different * calling conventions. The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * rb_find(). * * The reason for this is to allow the find() interface without requiring an * on-stack dummy object, which might not be feasible due to object size. */ /** * rb_add_cached() - insert @node into the leftmost cached tree @tree * @node: node to insert * @tree: leftmost cached tree to insert @node into * @less: operator defining the (partial) node order * * Returns @node when it is the new leftmost, or NULL. */ static __always_inline struct rb_node * rb_add_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); rb_insert_color_cached(node, tree, leftmost); return leftmost ? node : NULL; } /** * rb_add() - insert @node into @tree * @node: node to insert * @tree: tree to insert @node into * @less: operator defining the (partial) node order */ static __always_inline void rb_add(struct rb_node *node, struct rb_root *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; while (*link) { parent = *link; if (less(node, parent)) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node(node, parent, link); rb_insert_color(node, tree); } /** * rb_find_add() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify * @cmp: operator defining the node order * * Returns the rb_node matching @node, or NULL when no match is found and @node * is inserted. */ static __always_inline struct rb_node * rb_find_add(struct rb_node *node, struct rb_root *tree, int (*cmp)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; int c; while (*link) { parent = *link; c = cmp(node, parent); if (c < 0) link = &parent->rb_left; else if (c > 0) link = &parent->rb_right; else return parent; } rb_link_node(node, parent, link); rb_insert_color(node, tree); return NULL; } /** * rb_find() - find @key in tree @tree * @key: key to match * @tree: tree to search * @cmp: operator defining the node order * * Returns the rb_node matching @key or NULL. */ static __always_inline struct rb_node * rb_find(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; while (node) { int c = cmp(key, node); if (c < 0) node = node->rb_left; else if (c > 0) node = node->rb_right; else return node; } return NULL; } /** * rb_find_first() - find the first @key in @tree * @key: key to match * @tree: tree to search * @cmp: operator defining node order * * Returns the leftmost node matching @key, or NULL. */ static __always_inline struct rb_node * rb_find_first(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; struct rb_node *match = NULL; while (node) { int c = cmp(key, node); if (c <= 0) { if (!c) match = node; node = node->rb_left; } else if (c > 0) { node = node->rb_right; } } return match; } /** * rb_next_match() - find the next @key in @tree * @key: key to match * @tree: tree to search * @cmp: operator defining node order * * Returns the next node matching @key, or NULL. */ static __always_inline struct rb_node * rb_next_match(const void *key, struct rb_node *node, int (*cmp)(const void *key, const struct rb_node *)) { node = rb_next(node); if (node && cmp(key, node)) node = NULL; return node; } /** * rb_for_each() - iterates a subtree matching @key * @node: iterator * @key: key to match * @tree: tree to search * @cmp: operator defining node order */ #define rb_for_each(node, key, tree, cmp) \ for ((node) = rb_find_first((key), (tree), (cmp)); \ (node); (node) = rb_next_match((key), (node), (cmp))) #endif /* _LINUX_RBTREE_H */ |
| 18 18 18 67 67 18 18 18 67 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/flush.c * * Copyright (C) 1995-2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/libnvdimm.h> #include <linux/pagemap.h> #include <asm/cacheflush.h> #include <asm/cache.h> #include <asm/tlbflush.h> void sync_icache_aliases(unsigned long start, unsigned long end) { if (icache_is_aliasing()) { dcache_clean_pou(start, end); icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ caches_clean_inval_pou(start, end); } } static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_flags & VM_EXEC) sync_icache_aliases(start, end); } /* * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { memcpy(dst, src, len); flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) { struct folio *folio = page_folio(pte_page(pte)); if (!test_bit(PG_dcache_clean, &folio->flags)) { sync_icache_aliases((unsigned long)folio_address(folio), (unsigned long)folio_address(folio) + folio_size(folio)); set_bit(PG_dcache_clean, &folio->flags); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ void flush_dcache_folio(struct folio *folio) { if (test_bit(PG_dcache_clean, &folio->flags)) clear_bit(PG_dcache_clean, &folio->flags); } EXPORT_SYMBOL(flush_dcache_folio); void flush_dcache_page(struct page *page) { flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif |
| 123 120 101 84 3 3 3 101 156 155 84 84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_FIND_H_ #define __LINUX_FIND_H_ #ifndef __LINUX_BITMAP_H #error only <linux/bitmap.h> can be included directly #endif #include <linux/bitops.h> unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, unsigned long start); unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); #endif #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr, size, offset); } #endif #ifndef find_next_and_bit /** * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & *addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_and_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_andnot_bit /** * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits * in *addr2 * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_or_bit /** * find_next_or_bit - find the next set bit in either memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = (*addr1 | *addr2) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_or_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ static inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit(addr, size, offset); } #endif #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_bit(addr, size); } #endif /** * find_nth_bit - find N'th set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * The following is semantically equivalent: * idx = find_nth_bit(addr, size, 0); * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_bit(addr, size, n); } /** * find_nth_and_bit - find N'th set bit in 2 memory regions * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_bit(addr1, addr2, size, n); } /** * find_nth_andnot_bit - find N'th set bit in 2 memory regions, * flipping bits in 2nd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_andnot_bit(addr1, addr2, size, n); } /** * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, * excluding those set in 3rd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @addr3: The 3rd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); } #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_bit(addr1, addr2, size); } #endif /** * find_first_and_and_bit - find the first set bit in 3 memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @addr3: The third address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns @size. */ static inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_and_bit(addr1, addr2, addr3, size); } #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ static inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit(addr, size); } #endif #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region * @addr: The address to start the search at * @size: The number of bits to search * * Returns the bit number of the last set bit, or size. */ static inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __fls(val) : size; } return _find_last_bit(addr, size); } #endif /** * find_next_and_bit_wrap - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_and_bit(addr1, addr2, offset); return bit < offset ? bit : size; } /** * find_next_bit_wrap - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { unsigned long bit = find_next_bit(addr, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_bit(addr, offset); return bit < offset ? bit : size; } /* * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ static inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { unsigned long bit; /* If not wrapped around */ if (n > start) { /* and have a bit, just return it. */ bit = find_next_bit(bitmap, size, n); if (bit < size) return bit; /* Otherwise, wrap around and ... */ n = 0; } /* Search the other part. */ bit = find_next_bit(bitmap, start, n); return bit < start ? bit : size; } /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on * @size: bitmap size in number of bits * @offset: bit offset at which to start searching * * Returns the bit offset for the next set clump; the found clump value is * copied to the location pointed by @clump. If no bits are set, returns @size. */ extern unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset); #define find_first_clump8(clump, bits, size) \ find_next_clump8((clump), (bits), (size), 0) #if defined(__LITTLE_ENDIAN) static inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } static inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } static inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le static inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit_le(addr, size, offset); } #endif #ifndef find_first_zero_bit_le static inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit_le(addr, size); } #endif #ifndef find_next_bit_le static inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit_le(addr, size, offset); } #endif #else #error "Please fix <asm/byteorder.h>" #endif #define for_each_set_bit(bit, addr, size) \ for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_and_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_andnot_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_or_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ for ((bit) = 0; \ (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit) * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_bit((addr), (size), b), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_bit((addr), (size), (b)), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first unset bit) * @e: bit offset of end of current bitrange (first set bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bit_wrap - iterate over all set bits starting from @start, and * wrapping around the end of bitmap. * @bit: offset for current iteration * @addr: bitmap address to base the search on * @size: bitmap size in number of bits * @start: Starting bit for bitmap traversing, wrapping around the bitmap end */ #define for_each_set_bit_wrap(bit, addr, size, start) \ for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ (bit) < (size); \ (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset * @clump: location to store copy of current 8-bit clump * @bits: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_clump8(start, clump, bits, size) \ for ((start) = find_first_clump8(&(clump), (bits), (size)); \ (start) < (size); \ (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) #endif /*__LINUX_FIND_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ipi #if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IPI_H #include <linux/tracepoint.h> /** * ipi_raise - called when a smp cross call is made * * @mask: mask of recipient CPUs for the IPI * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string. */ TRACE_EVENT(ipi_raise, TP_PROTO(const struct cpumask *mask, const char *reason), TP_ARGS(mask, reason), TP_STRUCT__entry( __bitmask(target_cpus, nr_cpumask_bits) __field(const char *, reason) ), TP_fast_assign( __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); __entry->reason = reason; ), TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); TRACE_EVENT(ipi_send_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), TP_ARGS(cpu, callsite, callback), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpu=%u callsite=%pS callback=%pS", __entry->cpu, __entry->callsite, __entry->callback) ); TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), TP_ARGS(cpumask, callsite, callback), TP_STRUCT__entry( __cpumask(cpumask) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __assign_cpumask(cpumask, cpumask_bits(cpumask)); __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpumask=%s callsite=%pS callback=%pS", __get_cpumask(cpumask), __entry->callsite, __entry->callback) ); DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( __field(const char *, reason) ), TP_fast_assign( __entry->reason = reason; ), TP_printk("(%s)", __entry->reason) ); /** * ipi_entry - called immediately before the IPI handler * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise * for that IPI. */ DEFINE_EVENT(ipi_handler, ipi_entry, TP_PROTO(const char *reason), TP_ARGS(reason) ); /** * ipi_exit - called immediately after the IPI handler returns * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise for * that IPI. */ DEFINE_EVENT(ipi_handler, ipi_exit, TP_PROTO(const char *reason), TP_ARGS(reason) ); #endif /* _TRACE_IPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 23 122 221 23 23 23 46 46 46 46 46 45 46 46 46 46 46 46 46 4 4 5 5 5 4 4 4 45 46 46 45 4 9 5 4 4 4 122 122 122 122 122 2 122 122 122 2 2 2 2 2 152 151 152 140 140 23 23 23 23 23 196 152 152 196 215 215 215 214 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> #include <linux/nospec.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __ro_after_init; static unsigned int m_hash_shift __ro_after_init; static unsigned int mp_hash_mask __ro_after_init; static unsigned int mp_hash_shift __ro_after_init; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); /* Don't allow confusion with old 32bit mount ID */ static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32); static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; static struct kmem_cache *mnt_cache __ro_after_init; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; unsigned int propagation; unsigned int lookup_flags; bool recurse; struct user_namespace *mnt_userns; struct mnt_idmap *mnt_idmap; }; /* /sys/fs */ struct kobject *fs_kobj __ro_after_init; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr); return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL_ACCOUNT); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (READ_ONCE(mnt->mnt_sb->s_readonly_remount)) return 1; /* * The barrier pairs with the barrier in sb_start_ro_state_change() * making sure if we don't see s_readonly_remount set yet, we also will * not see any superblock / mount flag changes done by remount. * It also pairs with the barrier in sb_end_ro_state_change() * assuring that if we see s_readonly_remount already cleared, we will * see the values of superblock / mount flags updated by remount. */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * mnt_get_write_access - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, mnt_put_write_access() must be * called. This is effectively a refcount. */ int mnt_get_write_access(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); might_lock(&mount_lock.lock); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { cpu_relax(); } else { /* * This prevents priority inversion, if the task * setting MNT_WRITE_HOLD got preempted on a remote * CPU, and it prevents life lock if the task setting * MNT_WRITE_HOLD has a lower priority and is bound to * the same CPU as the task that is spinning here. */ preempt_enable(); lock_mount_hash(); unlock_mount_hash(); preempt_disable(); } } /* * The barrier pairs with the barrier sb_start_ro_state_change() making * sure that if we see MNT_WRITE_HOLD cleared, we will also see * s_readonly_remount set (or even SB_RDONLY / MNT_READONLY flags) in * mnt_is_readonly() and bail in case we are racing with remount * read-only. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(mnt_get_write_access); /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = mnt_get_write_access(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_get_write_access_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_get_write_access, but if @file is already open for write it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be * paired with mnt_put_write_access_file. */ int mnt_get_write_access_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* * Superblock may have become readonly while there are still * writable fd's, e.g. due to a fs error with errors=remount-ro */ if (__mnt_is_readonly(file->f_path.mnt)) return -EROFS; return 0; } return mnt_get_write_access(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but if the file is already open for writing it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the freeze protection and the check for emergency r/o * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = mnt_get_write_access_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * mnt_put_write_access - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * mnt_get_write_access() call above. */ void mnt_put_write_access(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } EXPORT_SYMBOL_GPL(mnt_put_write_access); /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { mnt_put_write_access(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void mnt_put_write_access_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) mnt_put_write_access(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { mnt_put_write_access_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); /** * mnt_hold_writers - prevent write access to the given mount * @mnt: mnt to prevent write access to * * Prevents write access to @mnt if there are no active writers for @mnt. * This function needs to be called and return successfully before changing * properties of @mnt that need to remain stable for callers with write access * to @mnt. * * After this functions has been called successfully callers must pair it with * a call to mnt_unhold_writers() in order to stop preventing write access to * @mnt. * * Context: This function expects lock_mount_hash() to be held serializing * setting MNT_WRITE_HOLD. * Return: On success 0 is returned. * On error, -EBUSY is returned. */ static inline int mnt_hold_writers(struct mount *mnt) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) return -EBUSY; return 0; } /** * mnt_unhold_writers - stop preventing write access to the given mount * @mnt: mnt to stop preventing write access to * * Stop preventing write access to @mnt allowing callers to gain write access * to @mnt again. * * This function can only be called after a successful call to * mnt_hold_writers(). * * Context: This function expects lock_mount_hash() to be held. */ static inline void mnt_unhold_writers(struct mount *mnt) { /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } static int mnt_make_readonly(struct mount *mnt) { int ret; ret = mnt_hold_writers(mnt); if (!ret) mnt->mnt.mnt_flags |= MNT_READONLY; mnt_unhold_writers(mnt); return ret; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { err = mnt_hold_writers(mnt); if (err) break; } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) sb_start_ro_state_change(sb); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { mnt_idmap_put(mnt_idmap(&mnt->mnt)); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } lock_mount_hash(); if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /** * __lookup_mnt - find first child mount * @mnt: parent mount * @dentry: mountpoint * * If @mnt has a child mount @c mounted @dentry find and return it. * * Note that the child mount @c need not be unique. There are cases * where shadow mounts are created. For example, during mount * propagation when a source mount @mnt whose root got overmounted by a * mount @o after path lookup but before @namespace_sem could be * acquired gets copied and propagated. So @mnt gets copied including * @o. When @mnt is propagated to a destination mount @d that already * has another mount @n mounted at the same mountpoint then the source * mount @mnt will be tucked beneath @n, i.e., @n will be mounted on * @mnt and @mnt mounted on @d. Now both @n and @o are mounted at @mnt * on @dentry. * * Return: The first child of @mnt mounted @dentry or NULL. */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt, *n; bool is_covered = false; down_read(&namespace_sem); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } /** * mnt_set_mountpoint_beneath - mount a mount beneath another one * * @new_parent: the source mount * @top_mnt: the mount beneath which @new_parent is mounted * @new_mp: the new mountpoint of @top_mnt on @new_parent * * Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and * parent @top_mnt->mnt_parent and mount it on top of @new_parent at * @new_mp. And mount @new_parent on the old parent and old * mountpoint of @top_mnt. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void mnt_set_mountpoint_beneath(struct mount *new_parent, struct mount *top_mnt, struct mountpoint *new_mp) { struct mount *old_top_parent = top_mnt->mnt_parent; struct mountpoint *old_top_mp = top_mnt->mnt_mp; mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent); mnt_change_mountpoint(new_parent, new_mp, top_mnt); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /** * attach_mnt - mount a mount, attach to @mount_hashtable and parent's * list of child mounts * @parent: the parent * @mnt: the new mount * @mp: the new mountpoint * @beneath: whether to mount @mnt beneath or on top of @parent * * If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt * to @parent's child mount list and to @mount_hashtable. * * If @beneath is true, remove @mnt from its current parent and * mountpoint and mount it on @mp on @parent, and mount @parent on the * old parent and old mountpoint of @mnt. Finally, attach @parent to * @mnt_hashtable and @parent->mnt_parent->mnt_mounts. * * Note, when __attach_mnt() is called @mnt->mnt_parent already points * to the correct parent. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp, bool beneath) { if (beneath) mnt_set_mountpoint_beneath(mnt, parent, mp); else mnt_set_mountpoint(parent, mp, mnt); /* * Note, @mnt->mnt_parent has to be used. If @mnt was mounted * beneath @parent then @mnt will need to be attached to * @parent's old parent, not @parent. IOW, @mnt->mnt_parent * isn't the same mount as @parent. */ __attach_mnt(mnt, mnt->mnt_parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp, false); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } static inline struct mount *node_to_mount(struct rb_node *node) { return node ? rb_entry(node, struct mount, mnt_node) : NULL; } static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) { struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); mnt->mnt_ns = ns; while (*link) { parent = *link; if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); mnt->mnt.mnt_flags |= MNT_ONRB; } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); while (!list_empty(&head)) { m = list_first_entry(&head, typeof(*m), mnt_list); list_del(&m->mnt_list); mnt_add_to_ns(n, m); } n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong */ if (unlikely(m->mnt_expiry_mark)) WRITE_ONCE(m->mnt_expiry_mark, 0); mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* * Make a mount point inaccessible to new lookups. * Because there may still be current users, the caller MUST WAIT * for an RCU grace period before destroying the mount point. */ void mnt_make_shortterm(struct vfsmount *mnt) { if (mnt) real_mount(mnt)->mnt_ns = NULL; } /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } /* * Returns the mount which either has the specified mnt_id, or has the next * smallest id afer the specified one. */ static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id <= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_left; } else { node = node->rb_right; } } return ret; } #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; down_read(&namespace_sem); return mnt_find_id_at(p->ns, *pos); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct mount *next = NULL, *mnt = v; struct rb_node *node = rb_next(&mnt->mnt_node); ++*pos; if (node) { next = node_to_mount(node); *pos = next->mnt_id_unique; } return next; } static void m_stop(struct seq_file *m, void *v) { up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @m: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; if (p->mnt.mnt_flags & MNT_ONRB) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->nr_mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (mnt->mnt.mnt_flags & MNT_ONRB || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (mnt->mnt.mnt_flags & MNT_ONRB || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } /** * path_mounted - check whether path is mounted * @path: path to check * * Determine whether @path refers to the root of a mount. * * Return: true if @path is the root of a mount, false if not. */ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } static void warn_mandlock(void) { pr_warn_once("=======================================================\n" "WARNING: The mand mount option has been deprecated and\n" " and is ignored by this kernel. Remove the mand\n" " option from the mount to silence this warning.\n" "=======================================================\n"); } static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); if (!may_mount()) return -EPERM; if (!path_mounted(path)) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { struct mount *res, *p, *q, *r, *parent; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { if (s->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ q = ERR_PTR(-EPERM); goto out; } else { s = skip_mnt_tree(s); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; parent = q; q = clone_mnt(p, p->mnt.mnt_root, flag); if (IS_ERR(q)) goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, parent, p->mnt_mp, false); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } static bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * @path: path to clone * * This creates a new vfsmount, which will be the clone of @path. The new mount * will not be attached anywhere in the namespace and will be private (i.e. * changes to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0; struct mount *p; if (ns->nr_mounts >= max) return -ENOSPC; max -= ns->nr_mounts; if (ns->pending_mounts >= max) return -ENOSPC; max -= ns->pending_mounts; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; if (mounts > max) return -ENOSPC; ns->pending_mounts += mounts; return 0; } enum mnt_tree_flags_t { MNT_TREE_MOVE = BIT(0), MNT_TREE_BENEATH = BIT(1), }; /** * attach_recursive_mnt - attach a source mount tree * @source_mnt: mount tree to be attached * @top_mnt: mount that @source_mnt will be mounted on or mounted beneath * @dest_mp: the mountpoint @source_mnt will be mounted at * @flags: modify how @source_mnt is supposed to be attached * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. * * Context: The function expects namespace_lock() to be held. * Return: If @source_mnt was successfully attached 0 is returned. * Otherwise a negative error code is returned. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *top_mnt, struct mountpoint *dest_mp, enum mnt_tree_flags_t flags) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = top_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *dest_mnt, *p; struct hlist_node *n; int err = 0; bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH; /* * Preallocate a mountpoint in case the new mounts need to be * mounted beneath mounts on the same mountpoint. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (beneath) dest_mnt = top_mnt->mnt_parent; else dest_mnt = top_mnt; if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); } lock_mount_hash(); if (err) goto out_cleanup_ids; if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } if (moving) { if (beneath) dest_mp = smp; unhash_mnt(source_mnt); attach_mnt(source_mnt, top_mnt, dest_mp, beneath); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { LIST_HEAD(head); /* move from anon - the caller will destroy */ for (p = source_mnt; p; p = next_mnt(p, source_mnt)) move_from_ns(p, &head); list_del_init(&head); } if (beneath) mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp); else mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } /** * do_lock_mount - lock mount and mountpoint * @path: target path * @beneath: whether the intention is to mount beneath @path * * Follow the mount stack on @path until the top mount @mnt is found. If * the initial @path->{mnt,dentry} is a mountpoint lookup the first * mount stacked on top of it. Then simply follow @{mnt,mnt->mnt_root} * until nothing is stacked on top of it anymore. * * Acquire the inode_lock() on the top mount's ->mnt_root to protect * against concurrent removal of the new mountpoint from another mount * namespace. * * If @beneath is requested, acquire inode_lock() on @mnt's mountpoint * @mp on @mnt->mnt_parent must be acquired. This protects against a * concurrent unlink of @mp->mnt_dentry from another mount namespace * where @mnt doesn't have a child mount mounted @mp. A concurrent * removal of @mnt->mnt_root doesn't matter as nothing will be mounted * on top of it for @beneath. * * In addition, @beneath needs to make sure that @mnt hasn't been * unmounted or moved from its current mountpoint in between dropping * @mount_lock and acquiring @namespace_sem. For the !@beneath case @mnt * being unmounted would be detected later by e.g., calling * check_mnt(mnt) in the function it's called from. For the @beneath * case however, it's useful to detect it directly in do_lock_mount(). * If @mnt hasn't been unmounted then @mnt->mnt_mountpoint still points * to @mnt->mnt_mp->m_dentry. But if @mnt has been unmounted it will * point to @mnt->mnt_root and @mnt->mnt_mp will be NULL. * * Return: Either the target mountpoint on the top mount or the top * mount's mountpoint. */ static struct mountpoint *do_lock_mount(struct path *path, bool beneath) { struct vfsmount *mnt = path->mnt; struct dentry *dentry; struct mountpoint *mp = ERR_PTR(-ENOENT); for (;;) { struct mount *m; if (beneath) { m = real_mount(mnt); read_seqlock_excl(&mount_lock); dentry = dget(m->mnt_mountpoint); read_sequnlock_excl(&mount_lock); } else { dentry = path->dentry; } inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); goto out; } namespace_lock(); if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) { namespace_unlock(); inode_unlock(dentry->d_inode); goto out; } mnt = lookup_mnt(path); if (likely(!mnt)) break; namespace_unlock(); inode_unlock(dentry->d_inode); if (beneath) dput(dentry); path_put(path); path->mnt = mnt; path->dentry = dget(mnt->mnt_root); } mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); } out: if (beneath) dput(dentry); return mp; } static inline struct mountpoint *lock_mount(struct path *path) { return do_lock_mount(path, false); } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, 0); } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (!path_mounted(path)) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { mnt_add_to_ns(ns, p); ns->nr_mounts++; } ns->root = mnt; mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); mnt->mnt.mnt_flags &= ~MNT_READONLY; return 0; } static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf = (char *)__get_free_page(GFP_KERNEL); char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM); pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; /* * We're only checking whether the superblock is read-only not * changing it, so only take down_read(&sb->s_umount). */ down_read(&sb->s_umount); lock_mount_hash(); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); up_read(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) { lock_mount_hash(); set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); } } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_set_group(struct path *from_path, struct path *to_path) { struct mount *from, *to; int err; from = real_mount(from_path->mnt); to = real_mount(to_path->mnt); namespace_lock(); err = -EINVAL; /* To and From must be mounted */ if (!is_mounted(&from->mnt)) goto out; if (!is_mounted(&to->mnt)) goto out; err = -EPERM; /* We should be allowed to modify mount namespaces of both mounts */ if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; err = -EINVAL; /* To and From paths should be mount roots */ if (!path_mounted(from_path)) goto out; if (!path_mounted(to_path)) goto out; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) goto out; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) goto out; /* From mount should not have locked children in place of To's root */ if (has_locked_children(from, to->mnt.mnt_root)) goto out; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) goto out; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) goto out; if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; list_add(&to->mnt_slave, &m->mnt_slave_list); to->mnt_master = m; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); lock_mount_hash(); set_mnt_shared(to); unlock_mount_hash(); } err = 0; out: namespace_unlock(); return err; } /** * path_overmounted - check if path is overmounted * @path: path to check * * Check if path is overmounted, i.e., if there's a mount on top of * @path->mnt with @path->dentry as mountpoint. * * Context: This function expects namespace_lock() to be held. * Return: If path is overmounted true is returned, false if not. */ static inline bool path_overmounted(const struct path *path) { rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, path->dentry))) { rcu_read_unlock(); return true; } rcu_read_unlock(); return false; } /** * can_move_mount_beneath - check that we can mount beneath the top mount * @from: mount to mount beneath * @to: mount under which to mount * @mp: mountpoint of @to * * - Make sure that @to->dentry is actually the root of a mount under * which we can mount another mount. * - Make sure that nothing can be mounted beneath the caller's current * root or the rootfs of the namespace. * - Make sure that the caller can unmount the topmost mount ensuring * that the caller could reveal the underlying mountpoint. * - Ensure that nothing has been mounted on top of @from before we * grabbed @namespace_sem to avoid creating pointless shadow mounts. * - Prevent mounting beneath a mount if the propagation relationship * between the source mount, parent mount, and top mount would lead to * nonsensical mount trees. * * Context: This function expects namespace_lock() to be held. * Return: On success 0, and on error a negative error code is returned. */ static int can_move_mount_beneath(const struct path *from, const struct path *to, const struct mountpoint *mp) { struct mount *mnt_from = real_mount(from->mnt), *mnt_to = real_mount(to->mnt), *parent_mnt_to = mnt_to->mnt_parent; if (!mnt_has_parent(mnt_to)) return -EINVAL; if (!path_mounted(to)) return -EINVAL; if (IS_MNT_LOCKED(mnt_to)) return -EINVAL; /* Avoid creating shadow mounts during mount propagation. */ if (path_overmounted(from)) return -EINVAL; /* * Mounting beneath the rootfs only makes sense when the * semantics of pivot_root(".", ".") are used. */ if (&mnt_to->mnt == current->fs->root.mnt) return -EINVAL; if (parent_mnt_to == current->nsproxy->mnt_ns->root) return -EINVAL; for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent) if (p == mnt_to) return -EINVAL; /* * If the parent mount propagates to the child mount this would * mean mounting @mnt_from on @mnt_to->mnt_parent and then * propagating a copy @c of @mnt_from on top of @mnt_to. This * defeats the whole purpose of mounting beneath another mount. */ if (propagation_would_overmount(parent_mnt_to, mnt_to, mp)) return -EINVAL; /* * If @mnt_to->mnt_parent propagates to @mnt_from this would * mean propagating a copy @c of @mnt_from on top of @mnt_from. * Afterwards @mnt_from would be mounted on top of * @mnt_to->mnt_parent and @mnt_to would be unmounted from * @mnt->mnt_parent and remounted on @mnt_from. But since @c is * already mounted on @mnt_from, @mnt_to would ultimately be * remounted on top of @c. Afterwards, @mnt_from would be * covered by a copy @c of @mnt_from and @c would be covered by * @mnt_from itself. This defeats the whole purpose of mounting * @mnt_from beneath @mnt_to. */ if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) return -EINVAL; return 0; } static int do_move_mount(struct path *old_path, struct path *new_path, bool beneath) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; enum mnt_tree_flags_t flags = 0; mp = do_lock_mount(new_path, beneath); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); if (attached) flags |= MNT_TREE_MOVE; old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (!path_mounted(old_path)) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; if (beneath) { err = can_move_mount_beneath(old_path, new_path, mp); if (err) goto out; err = -EINVAL; p = p->mnt_parent; flags |= MNT_TREE_BENEATH; } /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path, false); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, const struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path_mounted(path)) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, const struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } if (path_overmounted(path)) { err = 0; goto discard_locked; } mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if (flags & SB_MANDLOCK) warn_mandlock(); /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kfree(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); refcount_set(&new_ns->ns.count, 1); new_ns->mounts = RB_ROOT; init_waitqueue_head(&new_ns->poll); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { mnt_add_to_ns(new_ns, q); new_ns->nr_mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; // an mntns binding we'd skipped? while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(skip_mnt_tree(p), old); } namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } ns->root = mnt; ns->nr_mounts++; mnt_add_to_ns(ns, mnt); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } #define FSMOUNT_VALID_FLAGS \ (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \ MOUNT_ATTR_NOSYMFOLLOW) #define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; return mnt_flags; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~FSMOUNT_VALID_FLAGS) return -EINVAL; mnt_flags = attr_flags_to_mnt_flags(attr_flags); switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; if (fc->sb_flags & SB_MANDLOCK) warn_mandlock(); newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); ns->root = mnt; ns->nr_mounts = 1; mnt_add_to_ns(ns, mnt); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) == (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else ret = do_move_mount(&from_path, &to_path, (flags & MOVE_MOUNT_BENEATH)); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (!path_mounted(&root)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (!path_mounted(&new)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp, false); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp, false); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) { unsigned int flags = mnt->mnt.mnt_flags; /* flags to clear */ flags &= ~kattr->attr_clr; /* flags to raise */ flags |= kattr->attr_set; return flags; } static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; struct user_namespace *fs_userns = m->mnt_sb->s_user_ns; if (!kattr->mnt_idmap) return 0; /* * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ if (kattr->mnt_userns == m->mnt_sb->s_user_ns) return -EINVAL; /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create * another bind-mount they can idmap if they want to. */ if (is_idmapped_mnt(m)) return -EPERM; /* The underlying filesystem doesn't support idmapped mounts yet. */ if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; /* We're not controlling the superblock. */ if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; /* Mount has already been visible in the filesystem hierarchy. */ if (!is_anon_ns(mnt->mnt_ns)) return -EINVAL; return 0; } /** * mnt_allow_writers() - check whether the attribute change allows writers * @kattr: the new mount attributes * @mnt: the mount to which @kattr will be applied * * Check whether thew new mount attributes in @kattr allow concurrent writers. * * Return: true if writers need to be held, false if not */ static inline bool mnt_allow_writers(const struct mount_kattr *kattr, const struct mount *mnt) { return (!(kattr->attr_set & MNT_READONLY) || (mnt->mnt.mnt_flags & MNT_READONLY)) && !kattr->mnt_idmap; } static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; int err; for (m = mnt; m; m = next_mnt(m, mnt)) { if (!can_change_locked_flags(m, recalc_flags(kattr, m))) { err = -EPERM; break; } err = can_idmap_mount(kattr, m); if (err) break; if (!mnt_allow_writers(kattr, m)) { err = mnt_hold_writers(m); if (err) break; } if (!kattr->recurse) return 0; } if (err) { struct mount *p; /* * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all * mounts and needs to take care to include the first mount. */ for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); /* * We're done once the first mount we changed got * MNT_WRITE_HOLD unset. */ if (p == m) break; } } return err; } static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { if (!kattr->mnt_idmap) return; /* * Pairs with smp_load_acquire() in mnt_idmap(). * * Since we only allow a mount to change the idmapping once and * verified this in can_idmap_mount() we know that the mount has * @nop_mnt_idmap attached to it. So there's no need to drop any * references. */ smp_store_release(&mnt->mnt.mnt_idmap, mnt_idmap_get(kattr->mnt_idmap)); } static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; for (m = mnt; m; m = next_mnt(m, mnt)) { unsigned int flags; do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); /* If we had to hold writers unblock them. */ if (m->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(m); if (kattr->propagation) change_mnt_propagation(m, kattr->propagation); if (!kattr->recurse) break; } touch_mnt_namespace(mnt->mnt_ns); } static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) { struct mount *mnt = real_mount(path->mnt); int err = 0; if (!path_mounted(path)) return -EINVAL; if (kattr->mnt_userns) { struct mnt_idmap *mnt_idmap; mnt_idmap = alloc_mnt_idmap(kattr->mnt_userns); if (IS_ERR(mnt_idmap)) return PTR_ERR(mnt_idmap); kattr->mnt_idmap = mnt_idmap; } if (kattr->propagation) { /* * Only take namespace_lock() if we're actually changing * propagation. */ namespace_lock(); if (kattr->propagation == MS_SHARED) { err = invent_group_ids(mnt, kattr->recurse); if (err) { namespace_unlock(); return err; } } } err = -EINVAL; lock_mount_hash(); /* Ensure that this isn't anything purely vfs internal. */ if (!is_mounted(&mnt->mnt)) goto out; /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. * * If this mount doesn't have a parent it's most often simply a * detached mount with an anonymous mount namespace. IOW, something * that's simply not attached yet. But there are apparently also users * that do change mount properties on the rootfs itself. That obviously * neither has a parent nor is it a detached mount so we cannot * unconditionally check for detached mounts. */ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* * First, we get the mount tree in a shape where we can change mount * properties without failure. If we succeeded to do so we commit all * changes and if we failed we clean up. */ err = mount_setattr_prepare(kattr, mnt); if (!err) mount_setattr_commit(kattr, mnt); out: unlock_mount_hash(); if (kattr->propagation) { if (err) cleanup_group_ids(mnt, NULL); namespace_unlock(); } return err; } static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { int err = 0; struct ns_common *ns; struct user_namespace *mnt_userns; struct fd f; if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) return 0; /* * We currently do not support clearing an idmapped mount. If this ever * is a use-case we can revisit this but for now let's keep it simple * and not allow it. */ if (attr->attr_clr & MOUNT_ATTR_IDMAP) return -EINVAL; if (attr->userns_fd > INT_MAX) return -EINVAL; f = fdget(attr->userns_fd); if (!f.file) return -EBADF; if (!proc_ns_file(f.file)) { err = -EINVAL; goto out_fput; } ns = get_proc_ns(file_inode(f.file)); if (ns->ops->type != CLONE_NEWUSER) { err = -EINVAL; goto out_fput; } /* * The initial idmapping cannot be used to create an idmapped * mount. We use the initial idmapping as an indicator of a mount * that is not idmapped. It can simply be passed into helpers that * are aware of idmapped mounts as a convenient shortcut. A user * can just create a dedicated identity mapping to achieve the same * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); if (mnt_userns == &init_user_ns) { err = -EPERM; goto out_fput; } /* We're not controlling the target namespace. */ if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { err = -EPERM; goto out_fput; } kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: fdput(f); return err; } static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; *kattr = (struct mount_kattr) { .lookup_flags = lookup_flags, .recurse = !!(flags & AT_RECURSIVE), }; if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) return -EINVAL; if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) return -EINVAL; kattr->propagation = attr->propagation; if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); /* * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap, * users wanting to transition to a different atime setting cannot * simply specify the atime setting in @attr_set, but must also * specify MOUNT_ATTR__ATIME in the @attr_clr field. * So ensure that MOUNT_ATTR__ATIME can't be partially set in * @attr_clr and that @attr_set can't have any atime bits set if * MOUNT_ATTR__ATIME isn't set in @attr_clr. */ if (attr->attr_clr & MOUNT_ATTR__ATIME) { if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) return -EINVAL; /* * Clear all previous time settings as they are mutually * exclusive. */ kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; switch (attr->attr_set & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_RELATIME: kattr->attr_set |= MNT_RELATIME; break; case MOUNT_ATTR_NOATIME: kattr->attr_set |= MNT_NOATIME; break; case MOUNT_ATTR_STRICTATIME: break; default: return -EINVAL; } } else { if (attr->attr_set & MOUNT_ATTR__ATIME) return -EINVAL; } return build_mount_idmapped(attr, usize, kattr, flags); } static void finish_mount_kattr(struct mount_kattr *kattr) { put_user_ns(kattr->mnt_userns); kattr->mnt_userns = NULL; if (kattr->mnt_idmap) mnt_idmap_put(kattr->mnt_idmap); } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, unsigned int, flags, struct mount_attr __user *, uattr, size_t, usize) { int err; struct path target; struct mount_attr attr; struct mount_kattr kattr; BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); if (flags & ~(AT_EMPTY_PATH | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) return -EINVAL; if (!may_mount()) return -EPERM; err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); if (err) return err; /* Don't bother walking through the mounts if this is a nop. */ if (attr.attr_set == 0 && attr.attr_clr == 0 && attr.propagation == 0) return 0; err = build_mount_kattr(&attr, usize, &kattr, flags); if (err) return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); if (!err) { err = do_mount_setattr(&target, &kattr); path_put(&target); } finish_mount_kattr(&kattr); return err; } int show_path(struct seq_file *m, struct dentry *root) { if (root->d_sb->s_op->show_path) return root->d_sb->s_op->show_path(m, root); seq_dentry(m, root, " \t\n\\"); return 0; } static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns) { struct mount *mnt = mnt_find_id_at(ns, id); if (!mnt || mnt->mnt_id_unique != id) return NULL; return &mnt->mnt; } struct kstatmount { struct statmount __user *buf; size_t bufsize; struct vfsmount *mnt; u64 mask; struct path root; struct statmount sm; struct seq_file seq; }; static u64 mnt_to_attr_flags(struct vfsmount *mnt) { unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags); u64 attr_flags = 0; if (mnt_flags & MNT_READONLY) attr_flags |= MOUNT_ATTR_RDONLY; if (mnt_flags & MNT_NOSUID) attr_flags |= MOUNT_ATTR_NOSUID; if (mnt_flags & MNT_NODEV) attr_flags |= MOUNT_ATTR_NODEV; if (mnt_flags & MNT_NOEXEC) attr_flags |= MOUNT_ATTR_NOEXEC; if (mnt_flags & MNT_NODIRATIME) attr_flags |= MOUNT_ATTR_NODIRATIME; if (mnt_flags & MNT_NOSYMFOLLOW) attr_flags |= MOUNT_ATTR_NOSYMFOLLOW; if (mnt_flags & MNT_NOATIME) attr_flags |= MOUNT_ATTR_NOATIME; else if (mnt_flags & MNT_RELATIME) attr_flags |= MOUNT_ATTR_RELATIME; else attr_flags |= MOUNT_ATTR_STRICTATIME; if (is_idmapped_mnt(mnt)) attr_flags |= MOUNT_ATTR_IDMAP; return attr_flags; } static u64 mnt_to_propagation_flags(struct mount *m) { u64 propagation = 0; if (IS_MNT_SHARED(m)) propagation |= MS_SHARED; if (IS_MNT_SLAVE(m)) propagation |= MS_SLAVE; if (IS_MNT_UNBINDABLE(m)) propagation |= MS_UNBINDABLE; if (!propagation) propagation |= MS_PRIVATE; return propagation; } static void statmount_sb_basic(struct kstatmount *s) { struct super_block *sb = s->mnt->mnt_sb; s->sm.mask |= STATMOUNT_SB_BASIC; s->sm.sb_dev_major = MAJOR(sb->s_dev); s->sm.sb_dev_minor = MINOR(sb->s_dev); s->sm.sb_magic = sb->s_magic; s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME); } static void statmount_mnt_basic(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_MNT_BASIC; s->sm.mnt_id = m->mnt_id_unique; s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique; s->sm.mnt_id_old = m->mnt_id; s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id; s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt); s->sm.mnt_propagation = mnt_to_propagation_flags(m); s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0; s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0; } static void statmount_propagate_from(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_PROPAGATE_FROM; if (IS_MNT_SLAVE(m)) s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root); } static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq) { int ret; size_t start = seq->count; ret = show_path(seq, s->mnt->mnt_root); if (ret) return ret; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; /* * Unescape the result. It would be better if supplied string was not * escaped in the first place, but that's a pretty invasive change. */ seq->buf[seq->count] = '\0'; seq->count = start; seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); return 0; } static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; int err; err = seq_path_root(seq, &mnt_path, &s->root, ""); return err == SEQ_SKIP ? 0 : err; } static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) { struct super_block *sb = s->mnt->mnt_sb; seq_puts(seq, sb->s_type->name); return 0; } static int statmount_string(struct kstatmount *s, u64 flag) { int ret; size_t kbufsize; struct seq_file *seq = &s->seq; struct statmount *sm = &s->sm; switch (flag) { case STATMOUNT_FS_TYPE: sm->fs_type = seq->count; ret = statmount_fs_type(s, seq); break; case STATMOUNT_MNT_ROOT: sm->mnt_root = seq->count; ret = statmount_mnt_root(s, seq); break; case STATMOUNT_MNT_POINT: sm->mnt_point = seq->count; ret = statmount_mnt_point(s, seq); break; default: WARN_ON_ONCE(true); return -EINVAL; } if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize))) return -EOVERFLOW; if (kbufsize >= s->bufsize) return -EOVERFLOW; /* signal a retry */ if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (ret) return ret; seq->buf[seq->count++] = '\0'; sm->mask |= flag; return 0; } static int copy_statmount_to_user(struct kstatmount *s) { struct statmount *sm = &s->sm; struct seq_file *seq = &s->seq; char __user *str = ((char __user *)s->buf) + sizeof(*sm); size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm)); if (seq->count && copy_to_user(str, seq->buf, seq->count)) return -EFAULT; /* Return the number of bytes copied to the buffer */ sm->size = copysize + seq->count; if (copy_to_user(s->buf, sm, copysize)) return -EFAULT; return 0; } static int do_statmount(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); int err; /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) && !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) return -EPERM; err = security_sb_statfs(s->mnt->mnt_root); if (err) return err; if (s->mask & STATMOUNT_SB_BASIC) statmount_sb_basic(s); if (s->mask & STATMOUNT_MNT_BASIC) statmount_mnt_basic(s); if (s->mask & STATMOUNT_PROPAGATE_FROM) statmount_propagate_from(s); if (s->mask & STATMOUNT_FS_TYPE) err = statmount_string(s, STATMOUNT_FS_TYPE); if (!err && s->mask & STATMOUNT_MNT_ROOT) err = statmount_string(s, STATMOUNT_MNT_ROOT); if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); if (err) return err; return 0; } static inline bool retry_statmount(const long ret, size_t *seq_size) { if (likely(ret != -EAGAIN)) return false; if (unlikely(check_mul_overflow(*seq_size, 2, seq_size))) return false; if (unlikely(*seq_size > MAX_RW_COUNT)) return false; return true; } static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, struct statmount __user *buf, size_t bufsize, size_t seq_size) { if (!access_ok(buf, bufsize)) return -EFAULT; memset(ks, 0, sizeof(*ks)); ks->mask = kreq->param; ks->buf = buf; ks->bufsize = bufsize; ks->seq.size = seq_size; ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT); if (!ks->seq.buf) return -ENOMEM; return 0; } static int copy_mnt_id_req(const struct mnt_id_req __user *req, struct mnt_id_req *kreq) { int ret; size_t usize; BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0); ret = get_user(usize, &req->size); if (ret) return -EFAULT; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MNT_ID_REQ_SIZE_VER0)) return -EINVAL; memset(kreq, 0, sizeof(*kreq)); ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; if (kreq->spare != 0) return -EINVAL; return 0; } SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) { struct vfsmount *mnt; struct mnt_id_req kreq; struct kstatmount ks; /* We currently support retrieval of 3 strings. */ size_t seq_size = 3 * PATH_MAX; int ret; if (flags) return -EINVAL; ret = copy_mnt_id_req(req, &kreq); if (ret) return ret; retry: ret = prepare_kstatmount(&ks, &kreq, buf, bufsize, seq_size); if (ret) return ret; down_read(&namespace_sem); mnt = lookup_mnt_in_ns(kreq.mnt_id, current->nsproxy->mnt_ns); if (!mnt) { up_read(&namespace_sem); kvfree(ks.seq.buf); return -ENOENT; } ks.mnt = mnt; get_fs_root(current->fs, &ks.root); ret = do_statmount(&ks); path_put(&ks.root); up_read(&namespace_sem); if (!ret) ret = copy_statmount_to_user(&ks); kvfree(ks.seq.buf); if (retry_statmount(ret, &seq_size)) goto retry; return ret; } static struct mount *listmnt_next(struct mount *curr) { return node_to_mount(rb_next(&curr->mnt_node)); } static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_parent_id, u64 __user *mnt_ids, size_t nr_mnt_ids, const struct path *root) { struct mount *r; ssize_t ret; /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) && !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) return -EPERM; ret = security_sb_statfs(orig->dentry); if (ret) return ret; for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) { if (r->mnt_id_unique == mnt_parent_id) continue; if (!is_path_reachable(r, r->mnt.mnt_root, orig)) continue; if (put_user(r->mnt_id_unique, mnt_ids)) return -EFAULT; mnt_ids++; nr_mnt_ids--; ret++; } return ret; } SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mnt_id_req kreq; struct mount *first; struct path root, orig; u64 mnt_parent_id, last_mnt_id; const size_t maxcount = (size_t)-1 >> 3; ssize_t ret; if (flags) return -EINVAL; if (unlikely(nr_mnt_ids > maxcount)) return -EFAULT; if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids))) return -EFAULT; ret = copy_mnt_id_req(req, &kreq); if (ret) return ret; mnt_parent_id = kreq.mnt_id; last_mnt_id = kreq.param; down_read(&namespace_sem); get_fs_root(current->fs, &root); if (mnt_parent_id == LSMT_ROOT) { orig = root; } else { ret = -ENOENT; orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns); if (!orig.mnt) goto err; orig.dentry = orig.mnt->mnt_root; } if (!last_mnt_id) first = node_to_mount(rb_first(&ns->mounts)); else first = mnt_find_id_at(ns, last_mnt_id + 1); ret = do_listmount(first, &orig, mnt_parent_id, mnt_ids, nr_mnt_ids, &root); err: path_put(&root); up_read(&namespace_sem); return ret; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); ns->root = m; ns->nr_mounts = 1; mnt_add_to_ns(ns, m); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!refcount_dec_and_test(&ns->ns.count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR(mnt)) { mnt_make_shortterm(mnt); synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) mnt_make_shortterm(mnt[i]); synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt, *n; bool visible = false; down_read(&namespace_sem); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { struct mount *child; int mnt_flags; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; #ifdef CONFIG_SYSCTL static struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, }; static int __init init_fs_namespace_sysctls(void) { register_sysctl_init("fs", fs_namespace_sysctls); return 0; } fs_initcall(init_fs_namespace_sysctls); #endif /* CONFIG_SYSCTL */ |
| 64 64 64 64 63 64 64 64 65 65 64 64 64 64 64 64 64 65 65 65 64 65 5 4 4 5 98 98 98 98 87 87 28 86 97 97 97 28 97 97 97 98 98 97 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/mmu_notifier.c * * Copyright (C) 2008 Qumranet, Inc. * Copyright (C) 2008 SGI * Christoph Lameter <cl@linux.com> */ #include <linux/rculist.h> #include <linux/mmu_notifier.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/err.h> #include <linux/interval_tree.h> #include <linux/srcu.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/slab.h> /* global SRCU for all MMs */ DEFINE_STATIC_SRCU(srcu); #ifdef CONFIG_LOCKDEP struct lockdep_map __mmu_notifier_invalidate_range_start_map = { .name = "mmu_notifier_invalidate_range_start" }; #endif /* * The mmu_notifier_subscriptions structure is allocated and installed in * mm->notifier_subscriptions inside the mm_take_all_locks() protected * critical section and it's released only when mm_count reaches zero * in mmdrop(). */ struct mmu_notifier_subscriptions { /* all mmu notifiers registered in this mm are queued in this list */ struct hlist_head list; bool has_itree; /* to serialize the list modifications and hlist_unhashed */ spinlock_t lock; unsigned long invalidate_seq; unsigned long active_invalidate_ranges; struct rb_root_cached itree; wait_queue_head_t wq; struct hlist_head deferred_list; }; /* * This is a collision-retry read-side/write-side 'lock', a lot like a * seqcount, however this allows multiple write-sides to hold it at * once. Conceptually the write side is protecting the values of the PTEs in * this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any * writer exists. * * Note that the core mm creates nested invalidate_range_start()/end() regions * within the same thread, and runs invalidate_range_start()/end() in parallel * on multiple CPUs. This is designed to not reduce concurrency or block * progress on the mm side. * * As a secondary function, holding the full write side also serves to prevent * writers for the itree, this is an optimization to avoid extra locking * during invalidate_range_start/end notifiers. * * The write side has two states, fully excluded: * - mm->active_invalidate_ranges != 0 * - subscriptions->invalidate_seq & 1 == True (odd) * - some range on the mm_struct is being invalidated * - the itree is not allowed to change * * And partially excluded: * - mm->active_invalidate_ranges != 0 * - subscriptions->invalidate_seq & 1 == False (even) * - some range on the mm_struct is being invalidated * - the itree is allowed to change * * Operations on notifier_subscriptions->invalidate_seq (under spinlock): * seq |= 1 # Begin writing * seq++ # Release the writing state * seq & 1 # True if a writer exists * * The later state avoids some expensive work on inv_end in the common case of * no mmu_interval_notifier monitoring the VA. */ static bool mn_itree_is_invalidating(struct mmu_notifier_subscriptions *subscriptions) { lockdep_assert_held(&subscriptions->lock); return subscriptions->invalidate_seq & 1; } static struct mmu_interval_notifier * mn_itree_inv_start_range(struct mmu_notifier_subscriptions *subscriptions, const struct mmu_notifier_range *range, unsigned long *seq) { struct interval_tree_node *node; struct mmu_interval_notifier *res = NULL; spin_lock(&subscriptions->lock); subscriptions->active_invalidate_ranges++; node = interval_tree_iter_first(&subscriptions->itree, range->start, range->end - 1); if (node) { subscriptions->invalidate_seq |= 1; res = container_of(node, struct mmu_interval_notifier, interval_tree); } *seq = subscriptions->invalidate_seq; spin_unlock(&subscriptions->lock); return res; } static struct mmu_interval_notifier * mn_itree_inv_next(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range) { struct interval_tree_node *node; node = interval_tree_iter_next(&interval_sub->interval_tree, range->start, range->end - 1); if (!node) return NULL; return container_of(node, struct mmu_interval_notifier, interval_tree); } static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions) { struct mmu_interval_notifier *interval_sub; struct hlist_node *next; spin_lock(&subscriptions->lock); if (--subscriptions->active_invalidate_ranges || !mn_itree_is_invalidating(subscriptions)) { spin_unlock(&subscriptions->lock); return; } /* Make invalidate_seq even */ subscriptions->invalidate_seq++; /* * The inv_end incorporates a deferred mechanism like rtnl_unlock(). * Adds and removes are queued until the final inv_end happens then * they are progressed. This arrangement for tree updates is used to * avoid using a blocking lock during invalidate_range_start. */ hlist_for_each_entry_safe(interval_sub, next, &subscriptions->deferred_list, deferred_item) { if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) interval_tree_insert(&interval_sub->interval_tree, &subscriptions->itree); else interval_tree_remove(&interval_sub->interval_tree, &subscriptions->itree); hlist_del(&interval_sub->deferred_item); } spin_unlock(&subscriptions->lock); wake_up_all(&subscriptions->wq); } /** * mmu_interval_read_begin - Begin a read side critical section against a VA * range * @interval_sub: The interval subscription * * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a * collision-retry scheme similar to seqcount for the VA range under * subscription. If the mm invokes invalidation during the critical section * then mmu_interval_read_retry() will return true. * * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs * require a blocking context. The critical region formed by this can sleep, * and the required 'user_lock' can also be a sleeping lock. * * The caller is required to provide a 'user_lock' to serialize both teardown * and setup. * * The return value should be passed to mmu_interval_read_retry(). */ unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub) { struct mmu_notifier_subscriptions *subscriptions = interval_sub->mm->notifier_subscriptions; unsigned long seq; bool is_invalidating; /* * If the subscription has a different seq value under the user_lock * than we started with then it has collided. * * If the subscription currently has the same seq value as the * subscriptions seq, then it is currently between * invalidate_start/end and is colliding. * * The locking looks broadly like this: * mn_itree_inv_start(): mmu_interval_read_begin(): * spin_lock * seq = READ_ONCE(interval_sub->invalidate_seq); * seq == subs->invalidate_seq * spin_unlock * spin_lock * seq = ++subscriptions->invalidate_seq * spin_unlock * op->invalidate(): * user_lock * mmu_interval_set_seq() * interval_sub->invalidate_seq = seq * user_unlock * * [Required: mmu_interval_read_retry() == true] * * mn_itree_inv_end(): * spin_lock * seq = ++subscriptions->invalidate_seq * spin_unlock * * user_lock * mmu_interval_read_retry(): * interval_sub->invalidate_seq != seq * user_unlock * * Barriers are not needed here as any races here are closed by an * eventual mmu_interval_read_retry(), which provides a barrier via the * user_lock. */ spin_lock(&subscriptions->lock); /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ seq = READ_ONCE(interval_sub->invalidate_seq); is_invalidating = seq == subscriptions->invalidate_seq; spin_unlock(&subscriptions->lock); /* * interval_sub->invalidate_seq must always be set to an odd value via * mmu_interval_set_seq() using the provided cur_seq from * mn_itree_inv_start_range(). This ensures that if seq does wrap we * will always clear the below sleep in some reasonable time as * subscriptions->invalidate_seq is even in the idle state. */ lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (is_invalidating) wait_event(subscriptions->wq, READ_ONCE(subscriptions->invalidate_seq) != seq); /* * Notice that mmu_interval_read_retry() can already be true at this * point, avoiding loops here allows the caller to provide a global * time bound. */ return seq; } EXPORT_SYMBOL_GPL(mmu_interval_read_begin); static void mn_itree_release(struct mmu_notifier_subscriptions *subscriptions, struct mm_struct *mm) { struct mmu_notifier_range range = { .flags = MMU_NOTIFIER_RANGE_BLOCKABLE, .event = MMU_NOTIFY_RELEASE, .mm = mm, .start = 0, .end = ULONG_MAX, }; struct mmu_interval_notifier *interval_sub; unsigned long cur_seq; bool ret; for (interval_sub = mn_itree_inv_start_range(subscriptions, &range, &cur_seq); interval_sub; interval_sub = mn_itree_inv_next(interval_sub, &range)) { ret = interval_sub->ops->invalidate(interval_sub, &range, cur_seq); WARN_ON(!ret); } mn_itree_inv_end(subscriptions); } /* * This function can't run concurrently against mmu_notifier_register * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap * runs with mm_users == 0. Other tasks may still invoke mmu notifiers * in parallel despite there being no task using this mm any more, * through the vmas outside of the exit_mmap context, such as with * vmtruncate. This serializes against mmu_notifier_unregister with * the notifier_subscriptions->lock in addition to SRCU and it serializes * against the other mmu notifiers with SRCU. struct mmu_notifier_subscriptions * can't go away from under us as exit_mmap holds an mm_count pin * itself. */ static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions, struct mm_struct *mm) { struct mmu_notifier *subscription; int id; /* * SRCU here will block mmu_notifier_unregister until * ->release returns. */ id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) /* * If ->release runs before mmu_notifier_unregister it must be * handled, as it's the only way for the driver to flush all * existing sptes and stop the driver from establishing any more * sptes before all the pages in the mm are freed. */ if (subscription->ops->release) subscription->ops->release(subscription, mm); spin_lock(&subscriptions->lock); while (unlikely(!hlist_empty(&subscriptions->list))) { subscription = hlist_entry(subscriptions->list.first, struct mmu_notifier, hlist); /* * We arrived before mmu_notifier_unregister so * mmu_notifier_unregister will do nothing other than to wait * for ->release to finish and for mmu_notifier_unregister to * return. */ hlist_del_init_rcu(&subscription->hlist); } spin_unlock(&subscriptions->lock); srcu_read_unlock(&srcu, id); /* * synchronize_srcu here prevents mmu_notifier_release from returning to * exit_mmap (which would proceed with freeing all pages in the mm) * until the ->release method returns, if it was invoked by * mmu_notifier_unregister. * * The notifier_subscriptions can't go away from under us because * one mm_count is held by exit_mmap. */ synchronize_srcu(&srcu); } void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier_subscriptions *subscriptions = mm->notifier_subscriptions; if (subscriptions->has_itree) mn_itree_release(subscriptions, mm); if (!hlist_empty(&subscriptions->list)) mn_hlist_release(subscriptions, mm); } /* * If no young bitflag is supported by the hardware, ->clear_flush_young can * unmap the address and return 1 or 0 depending if the mapping previously * existed or not. */ int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *subscription; int young = 0, id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->clear_flush_young) young |= subscription->ops->clear_flush_young( subscription, mm, start, end); } srcu_read_unlock(&srcu, id); return young; } int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *subscription; int young = 0, id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->clear_young) young |= subscription->ops->clear_young(subscription, mm, start, end); } srcu_read_unlock(&srcu, id); return young; } int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { struct mmu_notifier *subscription; int young = 0, id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->test_young) { young = subscription->ops->test_young(subscription, mm, address); if (young) break; } } srcu_read_unlock(&srcu, id); return young; } static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions, const struct mmu_notifier_range *range) { struct mmu_interval_notifier *interval_sub; unsigned long cur_seq; for (interval_sub = mn_itree_inv_start_range(subscriptions, range, &cur_seq); interval_sub; interval_sub = mn_itree_inv_next(interval_sub, range)) { bool ret; ret = interval_sub->ops->invalidate(interval_sub, range, cur_seq); if (!ret) { if (WARN_ON(mmu_notifier_range_blockable(range))) continue; goto out_would_block; } } return 0; out_would_block: /* * On -EAGAIN the non-blocking caller is not allowed to call * invalidate_range_end() */ mn_itree_inv_end(subscriptions); return -EAGAIN; } static int mn_hlist_invalidate_range_start( struct mmu_notifier_subscriptions *subscriptions, struct mmu_notifier_range *range) { struct mmu_notifier *subscription; int ret = 0; int id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { const struct mmu_notifier_ops *ops = subscription->ops; if (ops->invalidate_range_start) { int _ret; if (!mmu_notifier_range_blockable(range)) non_block_start(); _ret = ops->invalidate_range_start(subscription, range); if (!mmu_notifier_range_blockable(range)) non_block_end(); if (_ret) { pr_info("%pS callback failed with %d in %sblockable context.\n", ops->invalidate_range_start, _ret, !mmu_notifier_range_blockable(range) ? "non-" : ""); WARN_ON(mmu_notifier_range_blockable(range) || _ret != -EAGAIN); /* * We call all the notifiers on any EAGAIN, * there is no way for a notifier to know if * its start method failed, thus a start that * does EAGAIN can't also do end. */ WARN_ON(ops->invalidate_range_end); ret = _ret; } } } if (ret) { /* * Must be non-blocking to get here. If there are multiple * notifiers and one or more failed start, any that succeeded * start are expecting their end to be called. Do so now. */ hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (!subscription->ops->invalidate_range_end) continue; subscription->ops->invalidate_range_end(subscription, range); } } srcu_read_unlock(&srcu, id); return ret; } int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { struct mmu_notifier_subscriptions *subscriptions = range->mm->notifier_subscriptions; int ret; if (subscriptions->has_itree) { ret = mn_itree_invalidate(subscriptions, range); if (ret) return ret; } if (!hlist_empty(&subscriptions->list)) return mn_hlist_invalidate_range_start(subscriptions, range); return 0; } static void mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions, struct mmu_notifier_range *range) { struct mmu_notifier *subscription; int id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->invalidate_range_end) { if (!mmu_notifier_range_blockable(range)) non_block_start(); subscription->ops->invalidate_range_end(subscription, range); if (!mmu_notifier_range_blockable(range)) non_block_end(); } } srcu_read_unlock(&srcu, id); } void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { struct mmu_notifier_subscriptions *subscriptions = range->mm->notifier_subscriptions; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (subscriptions->has_itree) mn_itree_inv_end(subscriptions); if (!hlist_empty(&subscriptions->list)) mn_hlist_invalidate_end(subscriptions, range); lock_map_release(&__mmu_notifier_invalidate_range_start_map); } void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_notifier *subscription; int id; id = srcu_read_lock(&srcu); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, srcu_read_lock_held(&srcu)) { if (subscription->ops->arch_invalidate_secondary_tlbs) subscription->ops->arch_invalidate_secondary_tlbs( subscription, mm, start, end); } srcu_read_unlock(&srcu, id); } /* * Same as mmu_notifier_register but here the caller must hold the mmap_lock in * write mode. A NULL mn signals the notifier is being registered for itree * mode. */ int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm) { struct mmu_notifier_subscriptions *subscriptions = NULL; int ret; mmap_assert_write_locked(mm); BUG_ON(atomic_read(&mm->mm_users) <= 0); /* * Subsystems should only register for invalidate_secondary_tlbs() or * invalidate_range_start()/end() callbacks, not both. */ if (WARN_ON_ONCE(subscription && (subscription->ops->arch_invalidate_secondary_tlbs && (subscription->ops->invalidate_range_start || subscription->ops->invalidate_range_end)))) return -EINVAL; if (!mm->notifier_subscriptions) { /* * kmalloc cannot be called under mm_take_all_locks(), but we * know that mm->notifier_subscriptions can't change while we * hold the write side of the mmap_lock. */ subscriptions = kzalloc( sizeof(struct mmu_notifier_subscriptions), GFP_KERNEL); if (!subscriptions) return -ENOMEM; INIT_HLIST_HEAD(&subscriptions->list); spin_lock_init(&subscriptions->lock); subscriptions->invalidate_seq = 2; subscriptions->itree = RB_ROOT_CACHED; init_waitqueue_head(&subscriptions->wq); INIT_HLIST_HEAD(&subscriptions->deferred_list); } ret = mm_take_all_locks(mm); if (unlikely(ret)) goto out_clean; /* * Serialize the update against mmu_notifier_unregister. A * side note: mmu_notifier_release can't run concurrently with * us because we hold the mm_users pin (either implicitly as * current->mm or explicitly with get_task_mm() or similar). * We can't race against any other mmu notifier method either * thanks to mm_take_all_locks(). * * release semantics on the initialization of the * mmu_notifier_subscriptions's contents are provided for unlocked * readers. acquire can only be used while holding the mmgrab or * mmget, and is safe because once created the * mmu_notifier_subscriptions is not freed until the mm is destroyed. * As above, users holding the mmap_lock or one of the * mm_take_all_locks() do not need to use acquire semantics. */ if (subscriptions) smp_store_release(&mm->notifier_subscriptions, subscriptions); if (subscription) { /* Pairs with the mmdrop in mmu_notifier_unregister_* */ mmgrab(mm); subscription->mm = mm; subscription->users = 1; spin_lock(&mm->notifier_subscriptions->lock); hlist_add_head_rcu(&subscription->hlist, &mm->notifier_subscriptions->list); spin_unlock(&mm->notifier_subscriptions->lock); } else mm->notifier_subscriptions->has_itree = true; mm_drop_all_locks(mm); BUG_ON(atomic_read(&mm->mm_users) <= 0); return 0; out_clean: kfree(subscriptions); return ret; } EXPORT_SYMBOL_GPL(__mmu_notifier_register); /** * mmu_notifier_register - Register a notifier on a mm * @subscription: The notifier to attach * @mm: The mm to attach the notifier to * * Must not hold mmap_lock nor any other VM related lock when calling * this registration function. Must also ensure mm_users can't go down * to zero while this runs to avoid races with mmu_notifier_release, * so mm has to be current->mm or the mm should be pinned safely such * as with get_task_mm(). If the mm is not current->mm, the mm_users * pin should be released by calling mmput after mmu_notifier_register * returns. * * mmu_notifier_unregister() or mmu_notifier_put() must be always called to * unregister the notifier. * * While the caller has a mmu_notifier get the subscription->mm pointer will remain * valid, and can be converted to an active mm pointer via mmget_not_zero(). */ int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm) { int ret; mmap_write_lock(mm); ret = __mmu_notifier_register(subscription, mm); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(mmu_notifier_register); static struct mmu_notifier * find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops) { struct mmu_notifier *subscription; spin_lock(&mm->notifier_subscriptions->lock); hlist_for_each_entry_rcu(subscription, &mm->notifier_subscriptions->list, hlist, lockdep_is_held(&mm->notifier_subscriptions->lock)) { if (subscription->ops != ops) continue; if (likely(subscription->users != UINT_MAX)) subscription->users++; else subscription = ERR_PTR(-EOVERFLOW); spin_unlock(&mm->notifier_subscriptions->lock); return subscription; } spin_unlock(&mm->notifier_subscriptions->lock); return NULL; } /** * mmu_notifier_get_locked - Return the single struct mmu_notifier for * the mm & ops * @ops: The operations struct being subscribe with * @mm : The mm to attach notifiers too * * This function either allocates a new mmu_notifier via * ops->alloc_notifier(), or returns an already existing notifier on the * list. The value of the ops pointer is used to determine when two notifiers * are the same. * * Each call to mmu_notifier_get() must be paired with a call to * mmu_notifier_put(). The caller must hold the write side of mm->mmap_lock. * * While the caller has a mmu_notifier get the mm pointer will remain valid, * and can be converted to an active mm pointer via mmget_not_zero(). */ struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *subscription; int ret; mmap_assert_write_locked(mm); if (mm->notifier_subscriptions) { subscription = find_get_mmu_notifier(mm, ops); if (subscription) return subscription; } subscription = ops->alloc_notifier(mm); if (IS_ERR(subscription)) return subscription; subscription->ops = ops; ret = __mmu_notifier_register(subscription, mm); if (ret) goto out_free; return subscription; out_free: subscription->ops->free_notifier(subscription); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(mmu_notifier_get_locked); /* this is called after the last mmu_notifier_unregister() returned */ void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { BUG_ON(!hlist_empty(&mm->notifier_subscriptions->list)); kfree(mm->notifier_subscriptions); mm->notifier_subscriptions = LIST_POISON1; /* debug */ } /* * This releases the mm_count pin automatically and frees the mm * structure if it was the last user of it. It serializes against * running mmu notifiers with SRCU and against mmu_notifier_unregister * with the unregister lock + SRCU. All sptes must be dropped before * calling mmu_notifier_unregister. ->release or any other notifier * method may be invoked concurrently with mmu_notifier_unregister, * and only after mmu_notifier_unregister returned we're guaranteed * that ->release or any other method can't run anymore. */ void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); if (!hlist_unhashed(&subscription->hlist)) { /* * SRCU here will force exit_mmap to wait for ->release to * finish before freeing the pages. */ int id; id = srcu_read_lock(&srcu); /* * exit_mmap will block in mmu_notifier_release to guarantee * that ->release is called before freeing the pages. */ if (subscription->ops->release) subscription->ops->release(subscription, mm); srcu_read_unlock(&srcu, id); spin_lock(&mm->notifier_subscriptions->lock); /* * Can not use list_del_rcu() since __mmu_notifier_release * can delete it before we hold the lock. */ hlist_del_init_rcu(&subscription->hlist); spin_unlock(&mm->notifier_subscriptions->lock); } /* * Wait for any running method to finish, of course including * ->release if it was run by mmu_notifier_release instead of us. */ synchronize_srcu(&srcu); BUG_ON(atomic_read(&mm->mm_count) <= 0); mmdrop(mm); } EXPORT_SYMBOL_GPL(mmu_notifier_unregister); static void mmu_notifier_free_rcu(struct rcu_head *rcu) { struct mmu_notifier *subscription = container_of(rcu, struct mmu_notifier, rcu); struct mm_struct *mm = subscription->mm; subscription->ops->free_notifier(subscription); /* Pairs with the get in __mmu_notifier_register() */ mmdrop(mm); } /** * mmu_notifier_put - Release the reference on the notifier * @subscription: The notifier to act on * * This function must be paired with each mmu_notifier_get(), it releases the * reference obtained by the get. If this is the last reference then process * to free the notifier will be run asynchronously. * * Unlike mmu_notifier_unregister() the get/put flow only calls ops->release * when the mm_struct is destroyed. Instead free_notifier is always called to * release any resources held by the user. * * As ops->release is not guaranteed to be called, the user must ensure that * all sptes are dropped, and no new sptes can be established before * mmu_notifier_put() is called. * * This function can be called from the ops->release callback, however the * caller must still ensure it is called pairwise with mmu_notifier_get(). * * Modules calling this function must call mmu_notifier_synchronize() in * their __exit functions to ensure the async work is completed. */ void mmu_notifier_put(struct mmu_notifier *subscription) { struct mm_struct *mm = subscription->mm; spin_lock(&mm->notifier_subscriptions->lock); if (WARN_ON(!subscription->users) || --subscription->users) goto out_unlock; hlist_del_init_rcu(&subscription->hlist); spin_unlock(&mm->notifier_subscriptions->lock); call_srcu(&srcu, &subscription->rcu, mmu_notifier_free_rcu); return; out_unlock: spin_unlock(&mm->notifier_subscriptions->lock); } EXPORT_SYMBOL_GPL(mmu_notifier_put); static int __mmu_interval_notifier_insert( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, struct mmu_notifier_subscriptions *subscriptions, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops) { interval_sub->mm = mm; interval_sub->ops = ops; RB_CLEAR_NODE(&interval_sub->interval_tree.rb); interval_sub->interval_tree.start = start; /* * Note that the representation of the intervals in the interval tree * considers the ending point as contained in the interval. */ if (length == 0 || check_add_overflow(start, length - 1, &interval_sub->interval_tree.last)) return -EOVERFLOW; /* Must call with a mmget() held */ if (WARN_ON(atomic_read(&mm->mm_users) <= 0)) return -EINVAL; /* pairs with mmdrop in mmu_interval_notifier_remove() */ mmgrab(mm); /* * If some invalidate_range_start/end region is going on in parallel * we don't know what VA ranges are affected, so we must assume this * new range is included. * * If the itree is invalidating then we are not allowed to change * it. Retrying until invalidation is done is tricky due to the * possibility for live lock, instead defer the add to * mn_itree_inv_end() so this algorithm is deterministic. * * In all cases the value for the interval_sub->invalidate_seq should be * odd, see mmu_interval_read_begin() */ spin_lock(&subscriptions->lock); if (subscriptions->active_invalidate_ranges) { if (mn_itree_is_invalidating(subscriptions)) hlist_add_head(&interval_sub->deferred_item, &subscriptions->deferred_list); else { subscriptions->invalidate_seq |= 1; interval_tree_insert(&interval_sub->interval_tree, &subscriptions->itree); } interval_sub->invalidate_seq = subscriptions->invalidate_seq; } else { WARN_ON(mn_itree_is_invalidating(subscriptions)); /* * The starting seq for a subscription not under invalidation * should be odd, not equal to the current invalidate_seq and * invalidate_seq should not 'wrap' to the new seq any time * soon. */ interval_sub->invalidate_seq = subscriptions->invalidate_seq - 1; interval_tree_insert(&interval_sub->interval_tree, &subscriptions->itree); } spin_unlock(&subscriptions->lock); return 0; } /** * mmu_interval_notifier_insert - Insert an interval notifier * @interval_sub: Interval subscription to register * @start: Starting virtual address to monitor * @length: Length of the range to monitor * @mm: mm_struct to attach to * @ops: Interval notifier operations to be called on matching events * * This function subscribes the interval notifier for notifications from the * mm. Upon return the ops related to mmu_interval_notifier will be called * whenever an event that intersects with the given range occurs. * * Upon return the range_notifier may not be present in the interval tree yet. * The caller must use the normal interval notifier read flow via * mmu_interval_read_begin() to establish SPTEs for this range. */ int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops) { struct mmu_notifier_subscriptions *subscriptions; int ret; might_lock(&mm->mmap_lock); subscriptions = smp_load_acquire(&mm->notifier_subscriptions); if (!subscriptions || !subscriptions->has_itree) { ret = mmu_notifier_register(NULL, mm); if (ret) return ret; subscriptions = mm->notifier_subscriptions; } return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions, start, length, ops); } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops) { struct mmu_notifier_subscriptions *subscriptions = mm->notifier_subscriptions; int ret; mmap_assert_write_locked(mm); if (!subscriptions || !subscriptions->has_itree) { ret = __mmu_notifier_register(NULL, mm); if (ret) return ret; subscriptions = mm->notifier_subscriptions; } return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions, start, length, ops); } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); static bool mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions, unsigned long seq) { bool ret; spin_lock(&subscriptions->lock); ret = subscriptions->invalidate_seq != seq; spin_unlock(&subscriptions->lock); return ret; } /** * mmu_interval_notifier_remove - Remove a interval notifier * @interval_sub: Interval subscription to unregister * * This function must be paired with mmu_interval_notifier_insert(). It cannot * be called from any ops callback. * * Once this returns ops callbacks are no longer running on other CPUs and * will not be called in future. */ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub) { struct mm_struct *mm = interval_sub->mm; struct mmu_notifier_subscriptions *subscriptions = mm->notifier_subscriptions; unsigned long seq = 0; might_sleep(); spin_lock(&subscriptions->lock); if (mn_itree_is_invalidating(subscriptions)) { /* * remove is being called after insert put this on the * deferred list, but before the deferred list was processed. */ if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) { hlist_del(&interval_sub->deferred_item); } else { hlist_add_head(&interval_sub->deferred_item, &subscriptions->deferred_list); seq = subscriptions->invalidate_seq; } } else { WARN_ON(RB_EMPTY_NODE(&interval_sub->interval_tree.rb)); interval_tree_remove(&interval_sub->interval_tree, &subscriptions->itree); } spin_unlock(&subscriptions->lock); /* * The possible sleep on progress in the invalidation requires the * caller not hold any locks held by invalidation callbacks. */ lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (seq) wait_event(subscriptions->wq, mmu_interval_seq_released(subscriptions, seq)); /* pairs with mmgrab in mmu_interval_notifier_insert() */ mmdrop(mm); } EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove); /** * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed * * This function ensures that all outstanding async SRU work from * mmu_notifier_put() is completed. After it returns any mmu_notifier_ops * associated with an unused mmu_notifier will no longer be called. * * Before using the caller must ensure that all of its mmu_notifiers have been * fully released via mmu_notifier_put(). * * Modules using the mmu_notifier_put() API should call this in their __exit * function to avoid module unloading races. */ void mmu_notifier_synchronize(void) { synchronize_srcu(&srcu); } EXPORT_SYMBOL_GPL(mmu_notifier_synchronize); |
| 2 1 2 2 1 1 3 3 1 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | // SPDX-License-Identifier: GPL-2.0-only /* * VFIO-KVM bridge pseudo device * * Copyright (C) 2013 Red Hat, Inc. All rights reserved. * Author: Alex Williamson <alex.williamson@redhat.com> */ #include <linux/errno.h> #include <linux/file.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/vfio.h> #include "vfio.h" #ifdef CONFIG_SPAPR_TCE_IOMMU #include <asm/kvm_ppc.h> #endif struct kvm_vfio_file { struct list_head node; struct file *file; #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *iommu_group; #endif }; struct kvm_vfio { struct list_head file_list; struct mutex lock; bool noncoherent; }; static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm) { void (*fn)(struct file *file, struct kvm *kvm); fn = symbol_get(vfio_file_set_kvm); if (!fn) return; fn(file, kvm); symbol_put(vfio_file_set_kvm); } static bool kvm_vfio_file_enforced_coherent(struct file *file) { bool (*fn)(struct file *file); bool ret; fn = symbol_get(vfio_file_enforced_coherent); if (!fn) return false; ret = fn(file); symbol_put(vfio_file_enforced_coherent); return ret; } static bool kvm_vfio_file_is_valid(struct file *file) { bool (*fn)(struct file *file); bool ret; fn = symbol_get(vfio_file_is_valid); if (!fn) return false; ret = fn(file); symbol_put(vfio_file_is_valid); return ret; } #ifdef CONFIG_SPAPR_TCE_IOMMU static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file) { struct iommu_group *(*fn)(struct file *file); struct iommu_group *ret; fn = symbol_get(vfio_file_iommu_group); if (!fn) return NULL; ret = fn(file); symbol_put(vfio_file_iommu_group); return ret; } static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm, struct kvm_vfio_file *kvf) { if (WARN_ON_ONCE(!kvf->iommu_group)) return; kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group); iommu_group_put(kvf->iommu_group); kvf->iommu_group = NULL; } #endif /* * Groups/devices can use the same or different IOMMU domains. If the same * then adding a new group/device may change the coherency of groups/devices * we've previously been told about. We don't want to care about any of * that so we retest each group/device and bail as soon as we find one that's * noncoherent. This means we only ever [un]register_noncoherent_dma once * for the whole device. */ static void kvm_vfio_update_coherency(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; bool noncoherent = false; struct kvm_vfio_file *kvf; list_for_each_entry(kvf, &kv->file_list, node) { if (!kvm_vfio_file_enforced_coherent(kvf->file)) { noncoherent = true; break; } } if (noncoherent != kv->noncoherent) { kv->noncoherent = noncoherent; if (kv->noncoherent) kvm_arch_register_noncoherent_dma(dev->kvm); else kvm_arch_unregister_noncoherent_dma(dev->kvm); } } static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; struct file *filp; int ret = 0; filp = fget(fd); if (!filp) return -EBADF; /* Ensure the FD is a vfio FD. */ if (!kvm_vfio_file_is_valid(filp)) { ret = -EINVAL; goto out_fput; } mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file == filp) { ret = -EEXIST; goto out_unlock; } } kvf = kzalloc(sizeof(*kvf), GFP_KERNEL_ACCOUNT); if (!kvf) { ret = -ENOMEM; goto out_unlock; } kvf->file = get_file(filp); list_add_tail(&kvf->node, &kv->file_list); kvm_arch_start_assignment(dev->kvm); kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); out_unlock: mutex_unlock(&kv->lock); out_fput: fput(filp); return ret; } static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; struct fd f; int ret; f = fdget(fd); if (!f.file) return -EBADF; ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != f.file) continue; list_del(&kvf->node); kvm_arch_end_assignment(dev->kvm); #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif kvm_vfio_file_set_kvm(kvf->file, NULL); fput(kvf->file); kfree(kvf); ret = 0; break; } kvm_vfio_update_coherency(dev); mutex_unlock(&kv->lock); fdput(f); return ret; } #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, void __user *arg) { struct kvm_vfio_spapr_tce param; struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; struct fd f; int ret; if (copy_from_user(¶m, arg, sizeof(struct kvm_vfio_spapr_tce))) return -EFAULT; f = fdget(param.groupfd); if (!f.file) return -EBADF; ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != f.file) continue; if (!kvf->iommu_group) { kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file); if (WARN_ON_ONCE(!kvf->iommu_group)) { ret = -EIO; goto err_fdput; } } ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd, kvf->iommu_group); break; } err_fdput: mutex_unlock(&kv->lock); fdput(f); return ret; } #endif static int kvm_vfio_set_file(struct kvm_device *dev, long attr, void __user *arg) { int32_t __user *argp = arg; int32_t fd; switch (attr) { case KVM_DEV_VFIO_FILE_ADD: if (get_user(fd, argp)) return -EFAULT; return kvm_vfio_file_add(dev, fd); case KVM_DEV_VFIO_FILE_DEL: if (get_user(fd, argp)) return -EFAULT; return kvm_vfio_file_del(dev, fd); #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: return kvm_vfio_file_set_spapr_tce(dev, arg); #endif } return -ENXIO; } static int kvm_vfio_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_VFIO_FILE: return kvm_vfio_set_file(dev, attr->attr, u64_to_user_ptr(attr->addr)); } return -ENXIO; } static int kvm_vfio_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_VFIO_FILE: switch (attr->attr) { case KVM_DEV_VFIO_FILE_ADD: case KVM_DEV_VFIO_FILE_DEL: #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: #endif return 0; } break; } return -ENXIO; } static void kvm_vfio_release(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf, *tmp; list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) { #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif kvm_vfio_file_set_kvm(kvf->file, NULL); fput(kvf->file); list_del(&kvf->node); kfree(kvf); kvm_arch_end_assignment(dev->kvm); } kvm_vfio_update_coherency(dev); kfree(kv); kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */ } static int kvm_vfio_create(struct kvm_device *dev, u32 type); static struct kvm_device_ops kvm_vfio_ops = { .name = "kvm-vfio", .create = kvm_vfio_create, .release = kvm_vfio_release, .set_attr = kvm_vfio_set_attr, .has_attr = kvm_vfio_has_attr, }; static int kvm_vfio_create(struct kvm_device *dev, u32 type) { struct kvm_device *tmp; struct kvm_vfio *kv; lockdep_assert_held(&dev->kvm->lock); /* Only one VFIO "device" per VM */ list_for_each_entry(tmp, &dev->kvm->devices, vm_node) if (tmp->ops == &kvm_vfio_ops) return -EBUSY; kv = kzalloc(sizeof(*kv), GFP_KERNEL_ACCOUNT); if (!kv) return -ENOMEM; INIT_LIST_HEAD(&kv->file_list); mutex_init(&kv->lock); dev->private = kv; return 0; } int kvm_vfio_ops_init(void) { return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO); } void kvm_vfio_ops_exit(void) { kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO); } |
| 153 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU #ifdef CONFIG_SWAP #include <linux/swapfile.h> #endif /* CONFIG_SWAP */ /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS #define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ #define SWP_PFN_BITS min_t(int, \ sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ #define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: * * |----------+--------------------| * | swp_type | swp_offset | * |----------+--------+-+-+-------| * | | resv |D|A| PFN | * |----------+--------+-+-+-------| * * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) * * Note: A/D bits will be stored in migration entries iff there're enough * free bits in arch specific swp offset. By default we'll ignore A/D bits * when migrating a page. Please refer to migration_entry_supports_ad() * for more information. If there're more bits besides PFN and A/D bits, * they should be reserved and always be zeros. */ #define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) #define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) #define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) #define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) #define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) static inline bool is_pfn_swap_entry(swp_entry_t entry); /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { if (pte_swp_exclusive(pte)) pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) pte = pte_swp_clear_uffd_wp(pte); return pte; } /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* * This should only be called upon a pfn swap entry to get the PFN stored * in the swap entry. Please refers to is_pfn_swap_entry() for definition * of pfn swap entry. */ static inline unsigned long swp_offset_pfn(swp_entry_t entry) { VM_BUG_ON(!is_pfn_swap_entry(entry)); return swp_offset(entry) & SWP_PFN_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_READ, offset); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_readable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ); } static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); } static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); } /* * Returns whether the host has large enough swap offset field to support * carrying over pgtable A/D bits for page migrations. The result is * pretty much arch specific. */ static inline bool migration_entry_supports_ad(void) { #ifdef CONFIG_SWAP return swap_migration_ad_supported; #else /* CONFIG_SWAP */ return false; #endif /* CONFIG_SWAP */ } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_YOUNG); return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_YOUNG; /* Keep the old behavior of aging page after migration */ return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_DIRTY); return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_DIRTY; /* Keep the old behavior of clean page after migration */ return false; } extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } static inline int is_readable_migration_entry(swp_entry_t entry) { return 0; } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { return false; } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } #endif typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) /* * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. */ #define PTE_MARKER_POISONED BIT(1) #define PTE_MARKER_MASK (BIT(2) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { return swp_entry(SWP_PTE_MARKER, marker); } static inline bool is_pte_marker_entry(swp_entry_t entry) { return swp_type(entry) == SWP_PTE_MARKER; } static inline pte_marker pte_marker_get(swp_entry_t entry) { return swp_offset(entry) & PTE_MARKER_MASK; } static inline bool is_pte_marker(pte_t pte) { return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); } static inline pte_t make_pte_marker(pte_marker marker) { return swp_entry_to_pte(make_pte_marker_entry(marker)); } static inline swp_entry_t make_poisoned_swp_entry(void) { return make_pte_marker_entry(PTE_MARKER_POISONED); } static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); } /* * This is a special version to check pte_none() just to cover the case when * the pte is a pte marker. It existed because in many cases the pte marker * should be seen as a none pte; it's just that we have stored some information * onto the none pte so it becomes not-none any more. * * It should be used when the pte is file-backed, ram-based and backing * userspace pages, like shmem. It is not needed upon pgtables that do not * support pte markers at all. For example, it's not needed on anonymous * memory, kernel-only memory (including when the system is during-boot), * non-ram based generic file-system. It's fine to be used even there, but the * extra pte marker check will be pure overhead. */ static inline int pte_none_mostly(pte_t pte) { return pte_none(pte) || is_pte_marker(pte); } static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(is_migration_entry(entry) && !PageLocked(p)); return p; } static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) { struct folio *folio = pfn_folio(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding folio is locked */ BUG_ON(is_migration_entry(entry) && !folio_test_locked(folio)); return folio; } /* * A pfn swap entry is a special type of swap entry that always has a pfn stored * in the swap offset. They can either be used to represent unaddressable device * memory, to restrict access to a page undergoing migration or to represent a * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { /* Make sure the swp offset can always store the needed fields */ BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |
| 32 32 32 32 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static fsnotify_connp_t *fsnotify_object_connp(void *obj, enum fsnotify_obj_type obj_type) { switch (obj_type) { case FSNOTIFY_OBJ_TYPE_INODE: return &((struct inode *)obj)->i_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_VFSMOUNT: return &real_mount(obj)->mnt_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_SB: return fsnotify_sb_marks(obj); default: return NULL; } } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return *fsnotify_conn_mask_p(conn); } static void fsnotify_get_sb_watched_objects(struct super_block *sb) { atomic_long_inc(fsnotify_sb_watched_objects(sb)); } static void fsnotify_put_sb_watched_objects(struct super_block *sb) { if (atomic_long_dec_and_test(fsnotify_sb_watched_objects(sb))) wake_up_var(fsnotify_sb_watched_objects(sb)); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); fsnotify_get_sb_watched_objects(inode->i_sb); } static void fsnotify_put_inode_ref(struct inode *inode) { fsnotify_put_sb_watched_objects(inode->i_sb); iput(inode); } /* * Grab or drop watched objects reference depending on whether the connector * is attached and has any marks attached. */ static void fsnotify_update_sb_watchers(struct super_block *sb, struct fsnotify_mark_connector *conn) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); bool is_watched = conn->flags & FSNOTIFY_CONN_FLAG_IS_WATCHED; struct fsnotify_mark *first_mark = NULL; unsigned int highest_prio = 0; if (conn->obj) first_mark = hlist_entry_safe(conn->list.first, struct fsnotify_mark, obj_list); if (first_mark) highest_prio = first_mark->group->priority; if (WARN_ON(highest_prio >= __FSNOTIFY_PRIO_NUM)) highest_prio = 0; /* * If the highest priority of group watching this object is prio, * then watched object has a reference on counters [0..prio]. * Update priority >= 1 watched objects counters. */ for (unsigned int p = conn->prio + 1; p <= highest_prio; p++) atomic_long_inc(&sbinfo->watched_objects[p]); for (unsigned int p = conn->prio; p > highest_prio; p--) atomic_long_dec(&sbinfo->watched_objects[p]); conn->prio = highest_prio; /* Update priority >= 0 (a.k.a total) watched objects counter */ BUILD_BUG_ON(FSNOTIFY_PRIO_NORMAL != 0); if (first_mark && !is_watched) { conn->flags |= FSNOTIFY_CONN_FLAG_IS_WATCHED; fsnotify_get_sb_watched_objects(sb); } else if (!first_mark && is_watched) { conn->flags &= ~FSNOTIFY_CONN_FLAG_IS_WATCHED; fsnotify_put_sb_watched_objects(sb); } } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; return fsnotify_update_iref(conn, want_iref); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { if (!conn) return; spin_lock(&conn->lock); __fsnotify_recalc_mask(conn); spin_unlock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) __fsnotify_update_child_dentry_flags( fsnotify_conn_inode(conn)); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { fsnotify_connp_t *connp = fsnotify_object_connp(conn->obj, conn->type); struct super_block *sb = fsnotify_connector_sb(conn); struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } rcu_assign_pointer(*connp, NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; fsnotify_update_sb_watchers(sb, conn); return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { struct super_block *sb = fsnotify_connector_sb(conn); /* Update watched objects after detaching mark */ if (sb) fsnotify_update_sb_watchers(sb, conn); objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_info_to_sb(struct super_block *sb) { struct fsnotify_sb_info *sbinfo; /* sb info is freed on fsnotify_sb_delete() */ sbinfo = kzalloc(sizeof(*sbinfo), GFP_KERNEL); if (!sbinfo) return -ENOMEM; /* * cmpxchg() provides the barrier so that callers of fsnotify_sb_info() * will observe an initialized structure */ if (cmpxchg(&sb->s_fsnotify_info, NULL, sbinfo)) { /* Someone else created sbinfo for us */ kfree(sbinfo); } return 0; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, void *obj, unsigned int obj_type) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->prio = 0; conn->type = obj_type; conn->obj = obj; /* * |