| 5 5 5 5 5 89 2 131 132 132 132 2 2 2 2 1394 1394 1393 1393 1393 3 3 3 3 3 1391 1394 1393 1394 1394 1391 5 649 649 5 647 649 649 49 49 49 49 87 90 14 43 2 41 21 21 21 21 21 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, Inc * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky */ #include "cpuset-internal.h" #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/security.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <linux/task_work.h> #include <linux/llist.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* * There could be abnormal cpuset configurations for cpu or memory * node binding, add this key to provide a quick low-cost judgment * of the situation. */ DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); static const char * const perr_strings[] = { [PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus.exclusive", [PERR_INVPARENT] = "Parent is an invalid partition root", [PERR_NOTPART] = "Parent is not a partition root", [PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive", [PERR_NOCPUS] = "Parent unable to distribute cpu downstream", [PERR_HOTPLUG] = "No cpu available due to hotplug", [PERR_CPUSEMPTY] = "cpuset.cpus and cpuset.cpus.exclusive are empty", [PERR_HKEEPING] = "partition config conflicts with housekeeping setup", [PERR_ACCESS] = "Enable partition not permitted", [PERR_REMOTE] = "Have remote partition underneath", }; /* * CPUSET Locking Convention * ------------------------- * * Below are the four global/local locks guarding cpuset structures in lock * acquisition order: * - cpuset_top_mutex * - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock) * - cpuset_mutex * - callback_lock (raw spinlock) * * As cpuset will now indirectly flush a number of different workqueues in * housekeeping_update() to update housekeeping cpumasks when the set of * isolated CPUs is going to be changed, it may be vulnerable to deadlock * if we hold cpus_read_lock while calling into housekeeping_update(). * * The first cpuset_top_mutex will be held except when calling into * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock * and cpuset_mutex will be held instead. The main purpose of this mutex * is to prevent regular cpuset control file write actions from interfering * with the call to housekeeping_update(), though CPU hotplug operation can * still happen in parallel. This mutex also provides protection for some * internal variables. * * A task must hold all the remaining three locks to modify externally visible * or used fields of cpusets, though some of the internally used cpuset fields * and internal variables can be modified without holding callback_lock. If only * reliable read access of the externally used fields are needed, a task can * hold either cpuset_mutex or callback_lock which are exposed to other * external subsystems. * * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others, * ensuring that it is the only task able to also acquire callback_lock and * be able to modify cpusets. It can perform various checks on the cpuset * structure first, knowing nothing will change. It can also allocate memory * without holding callback_lock. While it is performing these checks, various * callback routines can briefly acquire callback_lock to query cpusets. Once * it is ready to make the changes, it takes callback_lock, blocking everyone * else. * * Calls to the kernel memory allocator cannot be made while holding * callback_lock which is a spinlock, as the memory allocator may sleep or * call back into cpuset code and acquire callback_lock. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_seq_show() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. */ static DEFINE_MUTEX(cpuset_top_mutex); static DEFINE_MUTEX(cpuset_mutex); /* * File level internal variables below follow one of the following exclusion * rules. * * RWCS: Read/write-able by holding either cpus_write_lock (and optionally * cpuset_mutex) or both cpus_read_lock and cpuset_mutex. * * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable * by holding both cpuset_mutex and callback_lock. * * T: Read/write-able by holding the cpuset_top_mutex. */ /* * For local partitions, update to subpartitions_cpus & isolated_cpus is done * in update_parent_effective_cpumask(). For remote partitions, it is done in * the remote_partition_*() and remote_cpus_update() helpers. */ /* * Exclusive CPUs distributed out to local or remote sub-partitions of * top_cpuset */ static cpumask_var_t subpartitions_cpus; /* RWCS */ /* * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated) */ static cpumask_var_t isolated_cpus; /* CSCB */ /* * Set if housekeeping cpumasks are to be updated. */ static bool update_housekeeping; /* RWCS */ /* * Copy of isolated_cpus to be passed to housekeeping_update() */ static cpumask_var_t isolated_hk_cpus; /* T */ /* * A flag to force sched domain rebuild at the end of an operation. * It can be set in * - update_partition_sd_lb() * - update_cpumasks_hier() * - cpuset_update_flag() * - cpuset_hotplug_update_tasks() * - cpuset_handle_hotplug() * * Protected by cpuset_mutex (with cpus_read_lock held) or cpus_write_lock. * * Note that update_relax_domain_level() in cpuset-v1.c can still call * rebuild_sched_domains_locked() directly without using this flag. */ static bool force_sd_rebuild; /* RWCS */ /* * Partition root states: * * 0 - member (not a partition root) * 1 - partition root * 2 - partition root without load balancing (isolated) * -1 - invalid partition root * -2 - invalid isolated partition root * * There are 2 types of partitions - local or remote. Local partitions are * those whose parents are partition root themselves. Setting of * cpuset.cpus.exclusive are optional in setting up local partitions. * Remote partitions are those whose parents are not partition roots. Passing * down exclusive CPUs by setting cpuset.cpus.exclusive along its ancestor * nodes are mandatory in creating a remote partition. * * For simplicity, a local partition can be created under a local or remote * partition but a remote partition cannot have any partition root in its * ancestor chain except the cgroup root. * * A valid partition can be formed by setting exclusive_cpus or cpus_allowed * if exclusive_cpus is not set. In the case of partition with empty * exclusive_cpus, all the conflicting exclusive CPUs specified in the * following cpumasks of sibling cpusets will be removed from its * cpus_allowed in determining its effective_xcpus. * - effective_xcpus * - exclusive_cpus * * The "cpuset.cpus.exclusive" control file should be used for setting up * partition if the users want to get as many CPUs as possible. */ #define PRS_MEMBER 0 #define PRS_ROOT 1 #define PRS_ISOLATED 2 #define PRS_INVALID_ROOT -1 #define PRS_INVALID_ISOLATED -2 /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; void inc_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); atomic_inc(&cs->nr_deadline_tasks); } void dec_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); atomic_dec(&cs->nr_deadline_tasks); } static inline bool is_partition_valid(const struct cpuset *cs) { return cs->partition_root_state > 0; } static inline bool is_partition_invalid(const struct cpuset *cs) { return cs->partition_root_state < 0; } static inline bool cs_is_member(const struct cpuset *cs) { return cs->partition_root_state == PRS_MEMBER; } /* * Callers should hold callback_lock to modify partition_root_state. */ static inline void make_partition_invalid(struct cpuset *cs) { if (cs->partition_root_state > 0) cs->partition_root_state = -cs->partition_root_state; } /* * Send notification event of whenever partition_root_state changes. */ static inline void notify_partition_change(struct cpuset *cs, int old_prs) { if (old_prs == cs->partition_root_state) return; cgroup_file_notify(&cs->partition_file); /* Reset prs_err if not invalid */ if (is_partition_valid(cs)) WRITE_ONCE(cs->prs_err, PERR_NONE); } /* * The top_cpuset is always synchronized to cpu_active_mask and we should avoid * using cpu_online_mask as much as possible. An active CPU is always an online * CPU, but not vice versa. cpu_active_mask and cpu_online_mask can differ * during hotplug operations. A CPU is marked active at the last stage of CPU * bringup (CPUHP_AP_ACTIVE). It is also the stage where cpuset hotplug code * will be called to update the sched domains so that the scheduler can move * a normal task to a newly active CPU or remove tasks away from a newly * inactivated CPU. The online bit is set much earlier in the CPU bringup * process and cleared much later in CPU teardown. * * If cpu_online_mask is used while a hotunplug operation is happening in * parallel, we may leave an offline CPU in cpu_allowed or some other masks. */ struct cpuset top_cpuset = { .flags = BIT(CS_CPU_EXCLUSIVE) | BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE), .partition_root_state = PRS_ROOT, .dl_bw_cpu = -1, }; /** * cpuset_lock - Acquire the global cpuset mutex * * This locks the global cpuset mutex to prevent modifications to cpuset * hierarchy and configurations. This helper is not enough to make modification. */ void cpuset_lock(void) { mutex_lock(&cpuset_mutex); } void cpuset_unlock(void) { mutex_unlock(&cpuset_mutex); } void lockdep_assert_cpuset_lock_held(void) { lockdep_assert_held(&cpuset_mutex); } /** * cpuset_full_lock - Acquire full protection for cpuset modification * * Takes both CPU hotplug read lock (cpus_read_lock()) and cpuset mutex * to safely modify cpuset data. */ void cpuset_full_lock(void) { mutex_lock(&cpuset_top_mutex); cpus_read_lock(); mutex_lock(&cpuset_mutex); } void cpuset_full_unlock(void) { mutex_unlock(&cpuset_mutex); cpus_read_unlock(); mutex_unlock(&cpuset_top_mutex); } #ifdef CONFIG_LOCKDEP bool lockdep_is_cpuset_held(void) { return lockdep_is_held(&cpuset_mutex) || lockdep_is_held(&cpuset_top_mutex); } #endif static DEFINE_SPINLOCK(callback_lock); void cpuset_callback_lock_irq(void) { spin_lock_irq(&callback_lock); } void cpuset_callback_unlock_irq(void) { spin_unlock_irq(&callback_lock); } static struct workqueue_struct *cpuset_migrate_mm_wq; static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); /* * Cpuset task attach context * Protected by cpuset_mutex */ static struct { int in_progress; bool cpus_updated; bool mems_updated; bool task_work_queued; bool many_dest_cs; /* Have many destination cpusets */ struct cpuset *old_cs; /* Source cpuset */ nodemask_t nodemask_to; } attach_ctx; static LLIST_HEAD(src_cs_head); static LLIST_HEAD(dst_cs_head); /* * Wait if task attach is in progress until it is done and then acquire * cpuset_mutex before returning. */ static void wait_attach_done_lock(void) __acquires(&cpuset_mutex) { for (;;) { mutex_lock(&cpuset_mutex); if (!attach_ctx.in_progress) return; mutex_unlock(&cpuset_mutex); /* Wait until attach operation is done to prevent racing */ wait_event(cpuset_attach_wq, attach_ctx.in_progress == 0); } } static inline void check_insane_mems_config(nodemask_t *nodes) { if (!cpusets_insane_config() && movable_only_nodes(nodes)) { static_branch_enable_cpuslocked(&cpusets_insane_config_key); pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" "Cpuset allocations might fail even with a lot of memory available.\n", nodemask_pr_args(nodes)); } } /* * decrease attach_ctx.in_progress. * wake_up cpuset_attach_wq if attach_ctx.in_progress==0. */ static inline void dec_attach_in_progress_locked(void) { lockdep_assert_cpuset_lock_held(); attach_ctx.in_progress--; if (!attach_ctx.in_progress) wake_up(&cpuset_attach_wq); } static inline void dec_attach_in_progress(void) { mutex_lock(&cpuset_mutex); dec_attach_in_progress_locked(); mutex_unlock(&cpuset_mutex); } static inline bool cpuset_v2(void) { return !IS_ENABLED(CONFIG_CPUSETS_V1) || cgroup_subsys_on_dfl(cpuset_cgrp_subsys); } /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. * With v2 behavior, "cpus" and "mems" are always what the users have * requested and won't be changed by hotplug events. Only the effective * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { return cpuset_v2() || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /** * partition_is_populated - check if partition has tasks * @cs: partition root to be checked * @excluded_child: a child cpuset to be excluded in task checking * Return: true if there are tasks, false otherwise * * @cs should be a valid partition root or going to become a partition root. * @excluded_child should be non-NULL when this cpuset is going to become a * partition itself. * * Note that a remote partition is not allowed underneath a valid local * or remote partition. So if a non-partition root child is populated, * the whole partition is considered populated. */ static inline bool partition_is_populated(struct cpuset *cs, struct cpuset *excluded_child) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; /* * We cannot call cs_is_populated(cs) directly, as * nr_populated_domain_children may include populated * csets from descendants that are partitions. */ if (cgroup_has_tasks(cs->css.cgroup)) return true; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { if (cp == cs || cp == excluded_child) continue; if (is_partition_valid(cp)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (cpuset_is_populated(cp)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } /* * Return in pmask the portion of a task's cpusets's cpus_allowed that * are online and are capable of running the task. If none are found, * walk up the cpuset hierarchy until we find one that does have some * appropriate cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_active_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_active_cpus(struct task_struct *tsk, struct cpumask *pmask) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); struct cpuset *cs; if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_active_mask))) cpumask_copy(pmask, cpu_active_mask); rcu_read_lock(); cs = task_cs(tsk); while (!cpumask_intersects(cs->effective_cpus, pmask)) cs = parent_cs(cs); cpumask_and(pmask, pmask, cs->effective_cpus); rcu_read_unlock(); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. With v2, * effective_mems should always contain online memory nodes except * during the transition period where a memory node hotunplug operation * is in progress. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); } /** * alloc_cpumasks - Allocate an array of cpumask variables * @pmasks: Pointer to array of cpumask_var_t pointers * @size: Number of cpumasks to allocate * Return: 0 if successful, -ENOMEM otherwise. * * Allocates @size cpumasks and initializes them to empty. Returns 0 on * success, -ENOMEM on allocation failure. On failure, any previously * allocated cpumasks are freed. */ static inline int alloc_cpumasks(cpumask_var_t *pmasks[], u32 size) { int i; for (i = 0; i < size; i++) { if (!zalloc_cpumask_var(pmasks[i], GFP_KERNEL)) { while (--i >= 0) free_cpumask_var(*pmasks[i]); return -ENOMEM; } } return 0; } /** * alloc_tmpmasks - Allocate temporary cpumasks for cpuset operations. * @tmp: Pointer to tmpmasks structure to populate * Return: 0 on success, -ENOMEM on allocation failure */ static inline int alloc_tmpmasks(struct tmpmasks *tmp) { /* * Array of pointers to the three cpumask_var_t fields in tmpmasks. * Note: Array size must match actual number of masks (3) */ cpumask_var_t *pmask[3] = { &tmp->new_cpus, &tmp->addmask, &tmp->delmask }; return alloc_cpumasks(pmask, ARRAY_SIZE(pmask)); } /** * free_tmpmasks - free cpumasks in a tmpmasks structure * @tmp: the tmpmasks structure pointer */ static inline void free_tmpmasks(struct tmpmasks *tmp) { if (!tmp) return; free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } /** * dup_or_alloc_cpuset - Duplicate or allocate a new cpuset * @cs: Source cpuset to duplicate (NULL for a fresh allocation) * * Creates a new cpuset by either: * 1. Duplicating an existing cpuset (if @cs is non-NULL), or * 2. Allocating a fresh cpuset with zero-initialized masks (if @cs is NULL) * * Return: Pointer to newly allocated cpuset on success, NULL on failure */ static struct cpuset *dup_or_alloc_cpuset(struct cpuset *cs) { struct cpuset *trial; /* Allocate base structure */ trial = cs ? kmemdup(cs, sizeof(*cs), GFP_KERNEL) : kzalloc_obj(*cs); if (!trial) return NULL; trial->dl_bw_cpu = -1; init_llist_node(&trial->attach_node); /* Setup cpumask pointer array */ cpumask_var_t *pmask[4] = { &trial->cpus_allowed, &trial->effective_cpus, &trial->effective_xcpus, &trial->exclusive_cpus }; if (alloc_cpumasks(pmask, ARRAY_SIZE(pmask))) { kfree(trial); return NULL; } /* Copy masks if duplicating */ if (cs) { cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->effective_cpus, cs->effective_cpus); cpumask_copy(trial->effective_xcpus, cs->effective_xcpus); cpumask_copy(trial->exclusive_cpus, cs->exclusive_cpus); } return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->effective_xcpus); free_cpumask_var(cs->exclusive_cpus); kfree(cs); } /* Return user specified exclusive CPUs */ static inline struct cpumask *user_xcpus(struct cpuset *cs) { return cpumask_empty(cs->exclusive_cpus) ? cs->cpus_allowed : cs->exclusive_cpus; } static inline bool xcpus_empty(struct cpuset *cs) { return cpumask_empty(cs->cpus_allowed) && cpumask_empty(cs->exclusive_cpus); } /* * cpusets_are_exclusive() - check if two cpusets are exclusive * * Return true if exclusive, false if not */ static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2) { struct cpumask *xcpus1 = user_xcpus(cs1); struct cpumask *xcpus2 = user_xcpus(cs2); if (cpumask_intersects(xcpus1, xcpus2)) return false; return true; } /** * cpus_excl_conflict - Check if two cpusets have exclusive CPU conflicts * @trial: the trial cpuset to be checked * @sibling: a sibling cpuset to be checked against * @xcpus_changed: set if exclusive_cpus has been set * * Returns: true if CPU exclusivity conflict exists, false otherwise * * Conflict detection rules: * o cgroup v1 * See cpuset1_cpus_excl_conflict() * o cgroup v2 * - The exclusive_cpus values cannot overlap. * - New exclusive_cpus cannot be a superset of a sibling's cpus_allowed. */ static inline bool cpus_excl_conflict(struct cpuset *trial, struct cpuset *sibling, bool xcpus_changed) { if (!cpuset_v2()) return cpuset1_cpus_excl_conflict(trial, sibling); /* The cpus_allowed of a sibling cpuset cannot be a subset of the new exclusive_cpus */ if (xcpus_changed && !cpumask_empty(sibling->cpus_allowed) && cpumask_subset(sibling->cpus_allowed, trial->exclusive_cpus)) return true; /* Exclusive_cpus cannot intersect */ return cpumask_intersects(trial->exclusive_cpus, sibling->exclusive_cpus); } static inline bool mems_excl_conflict(struct cpuset *cs1, struct cpuset *cs2) { if ((is_mem_exclusive(cs1) || is_mem_exclusive(cs2))) return nodes_intersects(cs1->mems_allowed, cs2->mems_allowed); return false; } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; bool xcpus_changed; int ret = 0; rcu_read_lock(); if (!is_in_v2_mode()) ret = cpuset1_validate_change(cur, trial); if (ret) goto out; /* Remaining checks don't apply to root cpuset */ if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. This check is not done when scheduling is disabled as the * users should know what they are doing. * * For v1, effective_cpus == cpus_allowed & user_xcpus() returns * cpus_allowed. * * For v2, is_cpu_exclusive() & is_sched_load_balance() are true only * for non-isolated partition root. At this point, the target * effective_cpus isn't computed yet. user_xcpus() is the best * approximation. * * TBD: May need to precompute the real effective_cpus here in case * incorrect scheduling of SCHED_DEADLINE tasks in a partition * becomes an issue. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && is_sched_load_balance(cur) && !cpuset_cpumask_can_shrink(cur->effective_cpus, user_xcpus(trial))) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap. exclusive_cpus cannot overlap with each other if set. */ ret = -EINVAL; xcpus_changed = !cpumask_equal(cur->exclusive_cpus, trial->exclusive_cpus); cpuset_for_each_child(c, css, par) { if (c == cur) continue; if (cpus_excl_conflict(trial, c, xcpus_changed)) goto out; if (mems_excl_conflict(trial, c)) goto out; } ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int i, j; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ struct cgroup_subsys_state *pos_css; if (!cpuset_v2()) return cpuset1_generate_sched_domains(domains, attributes); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (cpumask_empty(subpartitions_cpus)) { ndoms = 1; /* !csa will be checked and can be correctly handled */ goto generate_doms; } csa = kmalloc_objs(cp, nr_cpusets()); if (!csa) goto done; /* Find how many partitions and cache them to csa[] */ rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { /* * Only valid partition roots that are not isolated and with * non-empty effective_cpus will be saved into csa[]. */ if ((cp->partition_root_state == PRS_ROOT) && !cpumask_empty(cp->effective_cpus)) csa[ndoms++] = cp; /* * Skip @cp's subtree if not a partition root and has no * exclusive CPUs to be granted to child cpusets. */ if (!is_partition_valid(cp) && cpumask_empty(cp->exclusive_cpus)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); for (i = 0; i < ndoms; i++) { for (j = i + 1; j < ndoms; j++) { if (cpusets_overlap(csa[i], csa[j])) /* * Cgroup v2 shouldn't pass down overlapping * partition root cpusets. */ WARN_ON_ONCE(1); } } generate_doms: doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_objs(struct sched_domain_attr, ndoms); /* * Cgroup v2 doesn't support domain attributes, just set all of them * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a * subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs. */ for (i = 0; i < ndoms; i++) { /* * The top cpuset may contain some boot time isolated * CPUs that need to be excluded from the sched domain. */ if (!csa || csa[i] == &top_cpuset) cpumask_and(doms[i], top_cpuset.effective_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)); else cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) dattr[i] = SD_ATTR_INIT; } done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; if (atomic_read(&cs->nr_deadline_tasks) == 0) return; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; int cpu; u64 cookie = ++dl_cookie; lockdep_assert_cpuset_lock_held(); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); rcu_read_lock(); for_each_possible_cpu(cpu) { if (dl_bw_visited(cpu, cookie)) continue; dl_clear_root_domain_cpu(cpu); } cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes cpus_read_lock(). */ void rebuild_sched_domains_locked(void) { struct sched_domain_attr *attr; cpumask_var_t *doms; int ndoms; int i; lockdep_assert_cpus_held(); lockdep_assert_cpuset_lock_held(); force_sd_rebuild = false; /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* * cpuset_hotplug_workfn is invoked synchronously now, thus this * function should not race with CPU hotplug. And the effective CPUs * must not include any offline CPUs. Passing an offline CPU in the * doms to partition_sched_domains() will trigger a kernel panic. * * We perform a final check here: if the doms contains any * offline CPUs, a warning is emitted and we return directly to * prevent the panic. */ for (i = 0; doms && i < ndoms; i++) { if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) { free_sched_domains(doms, ndoms); kfree(attr); return; } } /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ static void rebuild_sched_domains_cpuslocked(void) { mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); } void rebuild_sched_domains(void) { cpus_read_lock(); rebuild_sched_domains_cpuslocked(); cpus_read_unlock(); } void cpuset_reset_sched_domains(void) { mutex_lock(&cpuset_mutex); partition_sched_domains(1, NULL, NULL); mutex_unlock(&cpuset_mutex); } /** * cpuset_update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. * * For top_cpuset, task_cpu_possible_mask() is used instead of effective_cpus * to make sure all offline CPUs are also included as hotplug code won't * update cpumasks for tasks in top_cpuset. * * As task_cpu_possible_mask() can be task dependent in arm64, we have to * do cpu masking per task instead of doing it once for all. */ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { const struct cpumask *possible_mask = task_cpu_possible_mask(task); if (top_cs) { /* * PF_KTHREAD tasks are handled by housekeeping. * PF_NO_SETAFFINITY tasks are ignored. */ if (task->flags & (PF_KTHREAD | PF_NO_SETAFFINITY)) continue; cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus); } else { cpumask_and(new_cpus, possible_mask, cs->effective_cpus); } set_cpus_allowed_ptr(task, new_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * For v2, the parent's effective_cpus is inherited if cpumask is empty. * The result is valid only if the given cpuset isn't a partition root. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { bool has_cpus; has_cpus = cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus); if (!has_cpus && is_in_v2_mode()) cpumask_copy(new_cpus, parent->effective_cpus); } /** * compute_effective_nodemask - Compute the effective nodemask of the cpuset * @new_mems: the temp variable for the new effective_mems mask * @cs: the cpuset the need to recompute the new effective_mems mask * @parent: the parent cpuset * * For v2, the parent's effective_mems is inherited if nodemask is empty. */ static void compute_effective_nodemask(nodemask_t *new_mems, struct cpuset *cs, struct cpuset *parent) { bool has_mems; has_mems = nodes_and(*new_mems, cs->mems_allowed, parent->effective_mems); if (!has_mems && is_in_v2_mode()) nodes_copy(*new_mems, parent->effective_mems); } /* * Commands for update_parent_effective_cpumask */ enum partition_cmd { partcmd_enable, /* Enable partition root */ partcmd_enablei, /* Enable isolated partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's effective_cpus */ partcmd_invalidate, /* Make partition invalid */ }; static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp); /* * Update partition exclusive flag * * Return: 0 if successful, an error code otherwise */ static int update_partition_exclusive_flag(struct cpuset *cs, int new_prs) { bool exclusive = (new_prs > PRS_MEMBER); if (exclusive && !is_cpu_exclusive(cs)) { if (cpuset_update_flag(CS_CPU_EXCLUSIVE, cs, 1)) return PERR_NOTEXCL; } else if (!exclusive && is_cpu_exclusive(cs)) { /* Turning off CS_CPU_EXCLUSIVE will not return error */ cpuset_update_flag(CS_CPU_EXCLUSIVE, cs, 0); } return 0; } /* * Update partition load balance flag and/or rebuild sched domain * * Changing load balance flag will automatically call * rebuild_sched_domains_locked(). * This function is for cgroup v2 only. */ static void update_partition_sd_lb(struct cpuset *cs, int old_prs) { int new_prs = cs->partition_root_state; bool rebuild_domains = (new_prs > 0) || (old_prs > 0); bool new_lb; /* * If cs is not a valid partition root, the load balance state * will follow its parent. */ if (new_prs > 0) { new_lb = (new_prs != PRS_ISOLATED); } else { new_lb = is_sched_load_balance(parent_cs(cs)); } if (new_lb != !!is_sched_load_balance(cs)) { rebuild_domains = true; if (new_lb) set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); else clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } if (rebuild_domains) cpuset_force_rebuild(); } /* * tasks_nocpu_error - Return true if tasks will have no effective_cpus */ static bool tasks_nocpu_error(struct cpuset *parent, struct cpuset *cs, struct cpumask *xcpus) { /* * A populated partition (cs or parent) can't have empty effective_cpus */ return (cpumask_subset(parent->effective_cpus, xcpus) && partition_is_populated(parent, cs)) || (!cpumask_intersects(xcpus, cpu_active_mask) && partition_is_populated(cs, NULL)); } static void reset_partition_data(struct cpuset *cs) { struct cpuset *parent = parent_cs(cs); if (!cpuset_v2()) return; lockdep_assert_held(&callback_lock); if (cpumask_empty(cs->exclusive_cpus)) { cpumask_clear(cs->effective_xcpus); if (is_cpu_exclusive(cs)) clear_bit(CS_CPU_EXCLUSIVE, &cs->flags); } if (!cpumask_and(cs->effective_cpus, parent->effective_cpus, cs->cpus_allowed)) cpumask_copy(cs->effective_cpus, parent->effective_cpus); } /* Return true if isolated_cpus changes. */ static bool isolated_cpu_update(int new_prs, int cpu) { lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); if (new_prs == PRS_ISOLATED) { if (cpumask_test_cpu(cpu, isolated_cpus)) return false; cpumask_set_cpu(cpu, isolated_cpus); return true; } /* CPUs isolated at boot must remain isolated. */ if (!cpumask_test_cpu(cpu, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)) || !cpumask_test_cpu(cpu, isolated_cpus)) return false; cpumask_clear_cpu(cpu, isolated_cpus); return true; } /* * isolated_cpus_update - Update the isolated_cpus mask * @old_prs: old partition_root_state * @new_prs: new partition_root_state * @xcpus: exclusive CPUs with state change */ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { bool updated = false; int cpu; WARN_ON_ONCE(old_prs == new_prs); lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); for_each_cpu(cpu, xcpus) updated |= isolated_cpu_update(new_prs, cpu); if (updated) update_housekeeping = true; } /* * partition_xcpus_add - Add new exclusive CPUs to partition * @new_prs: new partition_root_state * @parent: parent cpuset * @xcpus: exclusive CPUs to be added * * Remote partition if parent == NULL */ static void partition_xcpus_add(int new_prs, struct cpuset *parent, struct cpumask *xcpus) { WARN_ON_ONCE(new_prs < 0); lockdep_assert_held(&callback_lock); if (!parent) parent = &top_cpuset; if (parent == &top_cpuset) cpumask_or(subpartitions_cpus, subpartitions_cpus, xcpus); if (new_prs != parent->partition_root_state) isolated_cpus_update(parent->partition_root_state, new_prs, xcpus); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, xcpus); } /* * partition_xcpus_del - Remove exclusive CPUs from partition * @old_prs: old partition_root_state * @parent: parent cpuset * @xcpus: exclusive CPUs to be removed * * Remote partition if parent == NULL */ static void partition_xcpus_del(int old_prs, struct cpuset *parent, struct cpumask *xcpus) { WARN_ON_ONCE(old_prs < 0); lockdep_assert_held(&callback_lock); if (!parent) parent = &top_cpuset; if (parent == &top_cpuset) cpumask_andnot(subpartitions_cpus, subpartitions_cpus, xcpus); if (old_prs != parent->partition_root_state) isolated_cpus_update(old_prs, parent->partition_root_state, xcpus); cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask); } /* * isolated_cpus_can_update - check for isolated & nohz_full conflicts * @add_cpus: cpu mask for cpus that are going to be isolated * @del_cpus: cpu mask for cpus that are no longer isolated, can be NULL * Return: false if there is conflict, true otherwise * * If nohz_full is enabled and we have isolated CPUs, their combination must * still leave housekeeping CPUs. * * TBD: Should consider merging this function into * prstate_housekeeping_conflict(). */ static bool isolated_cpus_can_update(struct cpumask *add_cpus, struct cpumask *del_cpus) { cpumask_var_t full_hk_cpus; int res = true; if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE)) return true; if (del_cpus && cpumask_weight_and(del_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE))) return true; if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL)) return false; cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE), housekeeping_cpumask(HK_TYPE_DOMAIN)); cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus); cpumask_and(full_hk_cpus, full_hk_cpus, cpu_active_mask); if (!cpumask_weight_andnot(full_hk_cpus, add_cpus)) res = false; free_cpumask_var(full_hk_cpus); return res; } /* * prstate_housekeeping_conflict - check for partition & housekeeping conflicts * @prstate: partition root state to be checked * @new_cpus: cpu mask * Return: true if there is conflict, false otherwise * * CPUs outside of HK_TYPE_DOMAIN_BOOT, if defined, can only be used in an * isolated partition. */ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) { if (!housekeeping_enabled(HK_TYPE_DOMAIN_BOOT)) return false; if ((prstate != PRS_ISOLATED) && !cpumask_subset(new_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT))) return true; return false; } /* * cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock * * Update housekeeping cpumasks and rebuild sched domains if necessary and * then do a cpuset_full_unlock(). * This should be called at the end of cpuset operation. */ static void cpuset_update_sd_hk_unlock(void) __releases(&cpuset_mutex) __releases(&cpuset_top_mutex) { /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ if (force_sd_rebuild) rebuild_sched_domains_locked(); if (update_housekeeping) { update_housekeeping = false; cpumask_copy(isolated_hk_cpus, isolated_cpus); /* * housekeeping_update() is now called without holding * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex * is still being held for mutual exclusion. */ mutex_unlock(&cpuset_mutex); cpus_read_unlock(); WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); mutex_unlock(&cpuset_top_mutex); } else { cpuset_full_unlock(); } } /* * Work function to invoke cpuset_update_sd_hk_unlock() */ static void hk_sd_workfn(struct work_struct *work) { cpuset_full_lock(); cpuset_update_sd_hk_unlock(); } /** * rm_siblings_excl_cpus - Remove exclusive CPUs that are used by sibling cpusets * @parent: Parent cpuset containing all siblings * @cs: Current cpuset (will be skipped) * @excpus: exclusive effective CPU mask to modify * * This function ensures the given @excpus mask doesn't include any CPUs that * are exclusively allocated to sibling cpusets. It walks through all siblings * of @cs under @parent and removes their exclusive CPUs from @excpus. */ static int rm_siblings_excl_cpus(struct cpuset *parent, struct cpuset *cs, struct cpumask *excpus) { struct cgroup_subsys_state *css; struct cpuset *sibling; int retval = 0; if (cpumask_empty(excpus)) return 0; /* * Remove exclusive CPUs from siblings */ rcu_read_lock(); cpuset_for_each_child(sibling, css, parent) { struct cpumask *sibling_xcpus; if (sibling == cs) continue; /* * If exclusive_cpus is defined, effective_xcpus will always * be a subset. Otherwise, effective_xcpus will only be set * in a valid partition root. */ sibling_xcpus = cpumask_empty(sibling->exclusive_cpus) ? sibling->effective_xcpus : sibling->exclusive_cpus; if (cpumask_intersects(excpus, sibling_xcpus)) { cpumask_andnot(excpus, excpus, sibling_xcpus); retval++; } } rcu_read_unlock(); return retval; } /* * compute_excpus - compute effective exclusive CPUs * @cs: cpuset * @xcpus: effective exclusive CPUs value to be set * Return: 0 if there is no sibling conflict, > 0 otherwise * * If exclusive_cpus isn't explicitly set , we have to scan the sibling cpusets * and exclude their exclusive_cpus or effective_xcpus as well. */ static int compute_excpus(struct cpuset *cs, struct cpumask *excpus) { struct cpuset *parent = parent_cs(cs); cpumask_and(excpus, user_xcpus(cs), parent->effective_xcpus); if (!cpumask_empty(cs->exclusive_cpus)) return 0; return rm_siblings_excl_cpus(parent, cs, excpus); } /* * compute_trialcs_excpus - Compute effective exclusive CPUs for a trial cpuset * @trialcs: The trial cpuset containing the proposed new configuration * @cs: The original cpuset that the trial configuration is based on * Return: 0 if successful with no sibling conflict, >0 if a conflict is found * * Computes the effective_xcpus for a trial configuration. @cs is provided to represent * the real cs. */ static int compute_trialcs_excpus(struct cpuset *trialcs, struct cpuset *cs) { struct cpuset *parent = parent_cs(trialcs); struct cpumask *excpus = trialcs->effective_xcpus; /* trialcs is member, cpuset.cpus has no impact to excpus */ if (cs_is_member(cs)) cpumask_and(excpus, trialcs->exclusive_cpus, parent->effective_xcpus); else cpumask_and(excpus, user_xcpus(trialcs), parent->effective_xcpus); return rm_siblings_excl_cpus(parent, cs, excpus); } static inline bool is_remote_partition(struct cpuset *cs) { return cs->remote_partition; } static inline bool is_local_partition(struct cpuset *cs) { return is_partition_valid(cs) && !is_remote_partition(cs); } /* * remote_partition_enable - Enable current cpuset as a remote partition root * @cs: the cpuset to update * @new_prs: new partition_root_state * @tmp: temporary masks * Return: 0 if successful, errcode if error * * Enable the current cpuset to become a remote partition root taking CPUs * directly from the top cpuset. cpuset_mutex must be held by the caller. */ static int remote_partition_enable(struct cpuset *cs, int new_prs, struct tmpmasks *tmp) { /* * The user must have sysadmin privilege. */ if (!capable(CAP_SYS_ADMIN)) return PERR_ACCESS; /* * The requested exclusive_cpus must not be allocated to other * partitions and it can't use up all the root's effective_cpus. * * The effective_xcpus mask can contain offline CPUs, but there must * be at least one or more online CPUs present before it can be enabled. * * Note that creating a remote partition with any local partition root * above it or remote partition root underneath it is not allowed. */ compute_excpus(cs, tmp->new_cpus); WARN_ON_ONCE(cpumask_intersects(tmp->new_cpus, subpartitions_cpus)); if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) || cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus)) return PERR_INVCPUS; if (((new_prs == PRS_ISOLATED) && !isolated_cpus_can_update(tmp->new_cpus, NULL)) || prstate_housekeeping_conflict(new_prs, tmp->new_cpus)) return PERR_HKEEPING; spin_lock_irq(&callback_lock); partition_xcpus_add(new_prs, NULL, tmp->new_cpus); cs->remote_partition = true; cpumask_copy(cs->effective_xcpus, tmp->new_cpus); spin_unlock_irq(&callback_lock); cpuset_force_rebuild(); WRITE_ONCE(cs->prs_err, 0); /* * Propagate changes in top_cpuset's effective_cpus down the hierarchy. */ cpuset_update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); return 0; } /* * remote_partition_disable - Remove current cpuset from remote partition list * @cs: the cpuset to update * @tmp: temporary masks * * The effective_cpus is also updated. * * cpuset_mutex must be held by the caller. */ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) { WARN_ON_ONCE(!is_remote_partition(cs)); /* * When a CPU is offlined, top_cpuset may end up with no available CPUs, * which should clear subpartitions_cpus. We should not emit a warning for this * scenario: the hierarchy is updated from top to bottom, so subpartitions_cpus * may already be cleared when disabling the partition. */ WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus) && !cpumask_empty(subpartitions_cpus)); spin_lock_irq(&callback_lock); cs->remote_partition = false; partition_xcpus_del(cs->partition_root_state, NULL, cs->effective_xcpus); if (cs->prs_err) cs->partition_root_state = -cs->partition_root_state; else cs->partition_root_state = PRS_MEMBER; /* effective_xcpus may need to be changed */ compute_excpus(cs, cs->effective_xcpus); reset_partition_data(cs); spin_unlock_irq(&callback_lock); cpuset_force_rebuild(); /* * Propagate changes in top_cpuset's effective_cpus down the hierarchy. */ cpuset_update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); } /* * remote_cpus_update - cpus_exclusive change of remote partition * @cs: the cpuset to be updated * @xcpus: the new exclusive_cpus mask, if non-NULL * @excpus: the new effective_xcpus mask * @tmp: temporary masks * * top_cpuset and subpartitions_cpus will be updated or partition can be * invalidated. */ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus, struct cpumask *excpus, struct tmpmasks *tmp) { bool adding, deleting; int prs = cs->partition_root_state; if (WARN_ON_ONCE(!is_remote_partition(cs))) return; WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus)); if (cpumask_empty(excpus)) { WRITE_ONCE(cs->prs_err, PERR_CPUSEMPTY); goto invalidate; } adding = cpumask_andnot(tmp->addmask, excpus, cs->effective_xcpus); deleting = cpumask_andnot(tmp->delmask, cs->effective_xcpus, excpus); /* * Additions of remote CPUs is only allowed if those CPUs are * not allocated to other partitions and there are effective_cpus * left in the top cpuset. */ if (adding) { WARN_ON_ONCE(cpumask_intersects(tmp->addmask, subpartitions_cpus)); if (!capable(CAP_SYS_ADMIN)) WRITE_ONCE(cs->prs_err, PERR_ACCESS); else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) || cpumask_subset(top_cpuset.effective_cpus, tmp->addmask)) WRITE_ONCE(cs->prs_err, PERR_NOCPUS); else if ((prs == PRS_ISOLATED) && !isolated_cpus_can_update(tmp->addmask, tmp->delmask)) WRITE_ONCE(cs->prs_err, PERR_HKEEPING); if (cs->prs_err) goto invalidate; } spin_lock_irq(&callback_lock); if (adding) partition_xcpus_add(prs, NULL, tmp->addmask); if (deleting) partition_xcpus_del(prs, NULL, tmp->delmask); /* * Need to update effective_xcpus and exclusive_cpus now as * update_sibling_cpumasks() below may iterate back to the same cs. */ cpumask_copy(cs->effective_xcpus, excpus); if (xcpus) cpumask_copy(cs->exclusive_cpus, xcpus); spin_unlock_irq(&callback_lock); if (adding || deleting) cpuset_force_rebuild(); /* * Propagate changes in top_cpuset's effective_cpus down the hierarchy. */ cpuset_update_tasks_cpumask(&top_cpuset, tmp->new_cpus); update_sibling_cpumasks(&top_cpuset, NULL, tmp); return; invalidate: remote_partition_disable(cs, tmp); } /** * update_parent_effective_cpumask - update effective_cpus mask of parent cpuset * @cs: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0 or a partition root state error code * * For partcmd_enable*, the cpuset is being transformed from a non-partition * root to a partition root. The effective_xcpus (cpus_allowed if * effective_xcpus not set) mask of the given cpuset will be taken away from * parent's effective_cpus. The function will return 0 if all the CPUs listed * in effective_xcpus can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transformed from a partition * root back to a non-partition root. Any CPUs in effective_xcpus will be * given back to parent's effective_cpus. 0 will always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu list is * to be changed from effective_xcpus to newmask. Otherwise, effective_xcpus is * assumed to remain the same. The cpuset should either be a valid or invalid * partition root. The partition root state may change from valid to invalid * or vice versa. An error code will be returned if transitioning from * invalid to valid violates the exclusivity rule. * * For partcmd_invalidate, the current partition will be made invalid. * * The partcmd_enable* and partcmd_disable commands are used by * update_prstate(). An error code may be returned and the caller will check * for error. * * The partcmd_update command is used by update_cpumasks_hier() with newmask * NULL and update_cpumask() with newmask set. The partcmd_invalidate is used * by update_cpumask() with NULL newmask. In both cases, the callers won't * check for error and so partition_root_state and prs_err will be updated * directly. */ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cs); int adding; /* Adding cpus to parent's effective_cpus */ int deleting; /* Deleting cpus from parent's effective_cpus */ int old_prs, new_prs; int part_error = PERR_NONE; /* Partition error? */ struct cpumask *xcpus = user_xcpus(cs); int parent_prs = parent->partition_root_state; bool nocpu; lockdep_assert_cpuset_lock_held(); WARN_ON_ONCE(is_remote_partition(cs)); /* For local partition only */ /* * new_prs will only be changed for the partcmd_update and * partcmd_invalidate commands. */ adding = deleting = false; old_prs = new_prs = cs->partition_root_state; if (cmd == partcmd_invalidate) { if (is_partition_invalid(cs)) return 0; /* * Make the current partition invalid. */ if (is_partition_valid(parent)) adding = cpumask_and(tmp->addmask, cs->effective_xcpus, parent->effective_xcpus); if (old_prs > 0) new_prs = -old_prs; goto write_error; } /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_valid(parent)) { return is_partition_invalid(parent) ? PERR_INVPARENT : PERR_NOTPART; } if (!newmask && xcpus_empty(cs)) return PERR_CPUSEMPTY; nocpu = tasks_nocpu_error(parent, cs, xcpus); if ((cmd == partcmd_enable) || (cmd == partcmd_enablei)) { /* * Need to call compute_excpus() in case * exclusive_cpus not set. Sibling conflict should only happen * if exclusive_cpus isn't set. */ xcpus = tmp->delmask; if (compute_excpus(cs, xcpus)) WARN_ON_ONCE(!cpumask_empty(cs->exclusive_cpus)); new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED; /* * Enabling partition root is not allowed if its * effective_xcpus is empty. */ if (cpumask_empty(xcpus)) return PERR_INVCPUS; if (prstate_housekeeping_conflict(new_prs, xcpus)) return PERR_HKEEPING; if ((new_prs == PRS_ISOLATED) && (new_prs != parent_prs) && !isolated_cpus_can_update(xcpus, NULL)) return PERR_HKEEPING; if (tasks_nocpu_error(parent, cs, xcpus)) return PERR_NOCPUS; /* * This function will only be called when all the preliminary * checks have passed. At this point, the following condition * should hold. * * (cs->effective_xcpus & cpu_active_mask) ⊆ parent->effective_cpus * * Warn if it is not the case. */ cpumask_and(tmp->new_cpus, xcpus, cpu_active_mask); WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, parent->effective_cpus)); deleting = true; } else if (cmd == partcmd_disable) { /* * May need to add cpus back to parent's effective_cpus * (and maybe removed from subpartitions_cpus/isolated_cpus) * for valid partition root. xcpus may contain CPUs that * shouldn't be removed from the two global cpumasks. */ if (is_partition_valid(cs)) { cpumask_copy(tmp->addmask, cs->effective_xcpus); adding = true; } new_prs = PRS_MEMBER; } else if (newmask) { /* * Empty cpumask is not allowed */ if (cpumask_empty(newmask)) { part_error = PERR_CPUSEMPTY; goto write_error; } /* Check newmask again, whether cpus are available for parent/cs */ nocpu |= tasks_nocpu_error(parent, cs, newmask); /* * partcmd_update with newmask: * * Compute add/delete mask to/from effective_cpus * * For valid partition: * addmask = effective_xcpus & ~newmask * & parent->effective_xcpus * delmask = newmask & ~effective_xcpus * & parent->effective_xcpus * * For invalid partition: * delmask = newmask & parent->effective_xcpus * The partition may become valid soon. */ if (is_partition_invalid(cs)) { adding = false; deleting = cpumask_and(tmp->delmask, newmask, parent->effective_xcpus); } else { cpumask_andnot(tmp->addmask, cs->effective_xcpus, newmask); adding = cpumask_and(tmp->addmask, tmp->addmask, parent->effective_xcpus); cpumask_andnot(tmp->delmask, newmask, cs->effective_xcpus); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->effective_xcpus); } /* * TBD: Invalidate a currently valid child root partition may * still break isolated_cpus_can_update() rule if parent is an * isolated partition. */ if (is_partition_valid(cs) && (old_prs != parent_prs)) { if ((parent_prs == PRS_ROOT) && /* Adding to parent means removing isolated CPUs */ !isolated_cpus_can_update(tmp->delmask, tmp->addmask)) part_error = PERR_HKEEPING; if ((parent_prs == PRS_ISOLATED) && /* Adding to parent means adding isolated CPUs */ !isolated_cpus_can_update(tmp->addmask, tmp->delmask)) part_error = PERR_HKEEPING; } /* * The new CPUs to be removed from parent's effective CPUs * must be present. */ if (deleting) { cpumask_and(tmp->new_cpus, tmp->delmask, cpu_active_mask); WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, parent->effective_cpus)); } /* * Make partition invalid if parent's effective_cpus could * become empty and there are tasks in the parent. */ if (nocpu && (!adding || !cpumask_intersects(tmp->addmask, cpu_active_mask))) { part_error = PERR_NOCPUS; deleting = false; adding = cpumask_and(tmp->addmask, cs->effective_xcpus, parent->effective_xcpus); } } else { /* * partcmd_update w/o newmask * * delmask = effective_xcpus & parent->effective_cpus * * This can be called from: * 1) update_cpumasks_hier() * 2) cpuset_hotplug_update_tasks() * * Check to see if it can be transitioned from valid to * invalid partition or vice versa. * * A partition error happens when parent has tasks and all * its effective CPUs will have to be distributed out. */ if (nocpu) { part_error = PERR_NOCPUS; if (is_partition_valid(cs)) adding = cpumask_and(tmp->addmask, cs->effective_xcpus, parent->effective_xcpus); } else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) && cpumask_subset(xcpus, parent->effective_xcpus)) { struct cgroup_subsys_state *css; struct cpuset *child; bool exclusive = true; /* * Convert invalid partition to valid has to * pass the cpu exclusivity test. */ rcu_read_lock(); cpuset_for_each_child(child, css, parent) { if (child == cs) continue; if (!cpusets_are_exclusive(cs, child)) { exclusive = false; break; } } rcu_read_unlock(); if (exclusive) deleting = cpumask_and(tmp->delmask, xcpus, parent->effective_cpus); else part_error = PERR_NOTEXCL; } } write_error: if (part_error) WRITE_ONCE(cs->prs_err, part_error); if (cmd == partcmd_update) { /* * Check for possible transition between valid and invalid * partition root. */ switch (cs->partition_root_state) { case PRS_ROOT: case PRS_ISOLATED: if (part_error) new_prs = -old_prs; break; case PRS_INVALID_ROOT: case PRS_INVALID_ISOLATED: if (!part_error) new_prs = -old_prs; break; } } if (!adding && !deleting && (new_prs == old_prs)) return 0; /* * Transitioning between invalid to valid or vice versa may require * changing CS_CPU_EXCLUSIVE. In the case of partcmd_update, * validate_change() has already been successfully called and * CPU lists in cs haven't been updated yet. So defer it to later. */ if ((old_prs != new_prs) && (cmd != partcmd_update)) { int err = update_partition_exclusive_flag(cs, new_prs); if (err) return err; } /* * Change the parent's effective_cpus & effective_xcpus (top cpuset * only). * * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (old_prs != new_prs) cs->partition_root_state = new_prs; /* * Adding to parent's effective_cpus means deletion CPUs from cs * and vice versa. */ if (adding) partition_xcpus_del(old_prs, parent, tmp->addmask); if (deleting) partition_xcpus_add(new_prs, parent, tmp->delmask); spin_unlock_irq(&callback_lock); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive_flag(cs, new_prs); if (adding || deleting) { cpuset_update_tasks_cpumask(parent, tmp->addmask); update_sibling_cpumasks(parent, cs, tmp); } /* * For partcmd_update without newmask, it is being called from * cpuset_handle_hotplug(). Update the load balance flag and * scheduling domain accordingly. */ if ((cmd == partcmd_update) && !newmask) update_partition_sd_lb(cs, old_prs); notify_partition_change(cs, old_prs); return 0; } /** * compute_partition_effective_cpumask - compute effective_cpus for partition * @cs: partition root cpuset * @new_ecpus: previously computed effective_cpus to be updated * * Compute the effective_cpus of a partition root by scanning effective_xcpus * of child partition roots and excluding their effective_xcpus. * * This has the side effect of invalidating valid child partition roots, * if necessary. Since it is called from either cpuset_hotplug_update_tasks() * or update_cpumasks_hier() where parent and children are modified * successively, we don't need to call update_parent_effective_cpumask() * and the child's effective_cpus will be updated in later iterations. * * Note that rcu_read_lock() is assumed to be held. */ static void compute_partition_effective_cpumask(struct cpuset *cs, struct cpumask *new_ecpus) { struct cgroup_subsys_state *css; struct cpuset *child; bool populated = partition_is_populated(cs, NULL); /* * Check child partition roots to see if they should be * invalidated when * 1) child effective_xcpus not a subset of new * excluisve_cpus * 2) All the effective_cpus will be used up and cp * has tasks */ compute_excpus(cs, new_ecpus); cpumask_and(new_ecpus, new_ecpus, cpu_active_mask); rcu_read_lock(); cpuset_for_each_child(child, css, cs) { if (!is_partition_valid(child)) continue; /* * There shouldn't be a remote partition underneath another * partition root. */ WARN_ON_ONCE(is_remote_partition(child)); WRITE_ONCE(child->prs_err, 0); if (!cpumask_subset(child->effective_xcpus, cs->effective_xcpus)) WRITE_ONCE(child->prs_err, PERR_INVCPUS); else if (populated && cpumask_subset(new_ecpus, child->effective_xcpus)) WRITE_ONCE(child->prs_err, PERR_NOCPUS); if (child->prs_err) { int old_prs = child->partition_root_state; /* * Invalidate child partition */ spin_lock_irq(&callback_lock); make_partition_invalid(child); spin_unlock_irq(&callback_lock); notify_partition_change(child, old_prs); continue; } cpumask_andnot(new_ecpus, new_ecpus, child->effective_xcpus); } rcu_read_unlock(); } /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * @force: don't skip any descendant cpusets if set * * When configured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp, bool force) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; int old_prs, new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); bool remote = is_remote_partition(cp); bool update_parent = false; old_prs = new_prs = cp->partition_root_state; /* * For child remote partition root (!= cs), we need to call * remote_cpus_update() if effective_xcpus will be changed. * Otherwise, we can skip the whole subtree. * * remote_cpus_update() will reuse tmp->new_cpus only after * its value is being processed. */ if (remote && (cp != cs)) { compute_excpus(cp, tmp->new_cpus); if (cpumask_equal(cp->effective_xcpus, tmp->new_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } rcu_read_unlock(); remote_cpus_update(cp, NULL, tmp->new_cpus, tmp); rcu_read_lock(); /* Remote partition may be invalidated */ new_prs = cp->partition_root_state; remote = (new_prs == old_prs); } if (remote || (is_partition_valid(parent) && is_partition_valid(cp))) compute_partition_effective_cpumask(cp, tmp->new_cpus); else compute_effective_cpumask(tmp->new_cpus, cp, parent); if (remote) goto get_css; /* Ready to update cpuset data */ /* * A partition with no effective_cpus is allowed as long as * there is no task associated with it. Call * update_parent_effective_cpumask() to check it. */ if (is_partition_valid(cp) && cpumask_empty(tmp->new_cpus)) { update_parent = true; goto update_parent_effective; } /* * Skip the whole subtree if * 1) the cpumask remains the same, * 2) has no partition root state, * 3) force flag not set, and * 4) for v2 load balance state same as its parent. */ if (!cp->partition_root_state && !force && cpumask_equal(tmp->new_cpus, cp->effective_cpus) && (!cpuset_v2() || (is_sched_load_balance(parent) == is_sched_load_balance(cp)))) { pos_css = css_rightmost_descendant(pos_css); continue; } update_parent_effective: /* * update_parent_effective_cpumask() should have been called * for cs already in update_cpumask(). We should also call * cpuset_update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's effective_cpus changes. */ if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_ROOT: case PRS_ISOLATED: update_parent = true; break; default: /* * When parent is not a partition root or is * invalid, child partition roots become * invalid too. */ if (is_partition_valid(cp)) new_prs = -cp->partition_root_state; WRITE_ONCE(cp->prs_err, is_partition_invalid(parent) ? PERR_INVPARENT : PERR_NOTPART); break; } } get_css: if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); if (update_parent) { update_parent_effective_cpumask(cp, partcmd_update, NULL, tmp); /* * The cpuset partition_root_state may become * invalid. Capture it. */ new_prs = cp->partition_root_state; } spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); cp->partition_root_state = new_prs; /* * Need to compute effective_xcpus if either exclusive_cpus * is non-empty or it is a valid partition root. */ if ((new_prs > 0) || !cpumask_empty(cp->exclusive_cpus)) compute_excpus(cp, cp->effective_xcpus); if (new_prs <= 0) reset_partition_data(cp); spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); cpuset_update_tasks_cpumask(cp, tmp->new_cpus); /* * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE * from parent if current cpuset isn't a valid partition root * and their load balance states differ. */ if (cpuset_v2() && !is_partition_valid(cp) && (is_sched_load_balance(parent) != is_sched_load_balance(cp))) { if (is_sched_load_balance(parent)) set_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); else clear_bit(CS_SCHED_LOAD_BALANCE, &cp->flags); } /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cpuset_v2() || is_partition_valid(cp))) cpuset_force_rebuild(); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; lockdep_assert_cpuset_lock_held(); /* * Check all its siblings and call update_cpumasks_hier() * if their effective_cpus will need to be changed. * * It is possible a change in parent's effective_cpus * due to a change in a child partition's effective_xcpus will impact * its siblings even if they do not inherit parent's effective_cpus * directly. It should not impact valid partition. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs || is_partition_valid(sibling)) continue; compute_effective_cpumask(tmp->new_cpus, sibling, parent); if (cpumask_equal(tmp->new_cpus, sibling->effective_cpus)) continue; if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp, false); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } static int parse_cpuset_cpulist(const char *buf, struct cpumask *out_mask) { int retval; retval = cpulist_parse(buf, out_mask); if (retval < 0) return retval; if (!cpumask_subset(out_mask, top_cpuset.cpus_allowed)) return -EINVAL; return 0; } /** * validate_partition - Validate a cpuset partition configuration * @cs: The cpuset to validate * @trialcs: The trial cpuset containing proposed configuration changes * * If any validation check fails, the appropriate error code is set in the * cpuset's prs_err field. * * Return: PRS error code (0 if valid, non-zero error code if invalid) */ static enum prs_errcode validate_partition(struct cpuset *cs, struct cpuset *trialcs) { struct cpuset *parent = parent_cs(cs); if (cs_is_member(trialcs)) return PERR_NONE; if (cpumask_empty(trialcs->effective_xcpus)) return PERR_INVCPUS; if (prstate_housekeeping_conflict(trialcs->partition_root_state, trialcs->effective_xcpus)) return PERR_HKEEPING; if (tasks_nocpu_error(parent, cs, trialcs->effective_xcpus)) return PERR_NOCPUS; return PERR_NONE; } /** * partition_cpus_change - Handle partition state changes due to CPU mask updates * @cs: The target cpuset being modified * @trialcs: The trial cpuset containing proposed configuration changes * @tmp: Temporary masks for intermediate calculations * * This function handles partition state transitions triggered by CPU mask changes. * CPU modifications may cause a partition to be disabled or require state updates. */ static void partition_cpus_change(struct cpuset *cs, struct cpuset *trialcs, struct tmpmasks *tmp) { enum prs_errcode prs_err; if (cs_is_member(cs)) return; prs_err = validate_partition(cs, trialcs); if (prs_err) { WRITE_ONCE(cs->prs_err, prs_err); trialcs->prs_err = prs_err; } if (is_remote_partition(cs)) { if (trialcs->prs_err) remote_partition_disable(cs, tmp); else remote_cpus_update(cs, trialcs->exclusive_cpus, trialcs->effective_xcpus, tmp); } else { if (trialcs->prs_err) update_parent_effective_cpumask(cs, partcmd_invalidate, NULL, tmp); else update_parent_effective_cpumask(cs, partcmd_update, trialcs->effective_xcpus, tmp); } } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; bool force = false; int old_prs = cs->partition_root_state; retval = parse_cpuset_cpulist(buf, trialcs->cpus_allowed); if (retval < 0) return retval; /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; compute_trialcs_excpus(trialcs, cs); trialcs->prs_err = PERR_NONE; retval = validate_change(cs, trialcs); if (retval < 0) return retval; if (alloc_tmpmasks(&tmp)) return -ENOMEM; /* * Check all the descendants in update_cpumasks_hier() if * effective_xcpus is to be changed. */ force = !cpumask_equal(cs->effective_xcpus, trialcs->effective_xcpus); partition_cpus_change(cs, trialcs, &tmp); spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); cpumask_copy(cs->effective_xcpus, trialcs->effective_xcpus); if ((old_prs > 0) && !is_partition_valid(cs)) reset_partition_data(cs); spin_unlock_irq(&callback_lock); /* effective_cpus/effective_xcpus will be updated here */ update_cpumasks_hier(cs, &tmp, force); /* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */ if (cs->partition_root_state) update_partition_sd_lb(cs, old_prs); free_tmpmasks(&tmp); return retval; } /** * update_exclusive_cpumask - update the exclusive_cpus mask of a cpuset * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset * * The tasks' cpumask will be updated if cs is a valid partition root. */ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; bool force = false; int old_prs = cs->partition_root_state; retval = parse_cpuset_cpulist(buf, trialcs->exclusive_cpus); if (retval < 0) return retval; /* Nothing to do if the CPUs didn't change */ if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus)) return 0; /* * Reject the change if there is exclusive CPUs conflict with * the siblings. */ if (compute_trialcs_excpus(trialcs, cs)) return -EINVAL; /* * Check all the descendants in update_cpumasks_hier() if * effective_xcpus is to be changed. */ force = !cpumask_equal(cs->effective_xcpus, trialcs->effective_xcpus); retval = validate_change(cs, trialcs); if (retval) return retval; if (alloc_tmpmasks(&tmp)) return -ENOMEM; trialcs->prs_err = PERR_NONE; partition_cpus_change(cs, trialcs, &tmp); spin_lock_irq(&callback_lock); cpumask_copy(cs->exclusive_cpus, trialcs->exclusive_cpus); cpumask_copy(cs->effective_xcpus, trialcs->effective_xcpus); if ((old_prs > 0) && !is_partition_valid(cs)) reset_partition_data(cs); spin_unlock_irq(&callback_lock); /* * Call update_cpumasks_hier() to update effective_cpus/effective_xcpus * of the subtree when it is a valid partition root or effective_xcpus * is updated. */ if (is_partition_valid(cs) || force) update_cpumasks_hier(cs, &tmp, force); /* Update CS_SCHED_LOAD_BALANCE and/or sched_domains, if necessary */ if (cs->partition_root_state) update_partition_sd_lb(cs, old_prs); free_tmpmasks(&tmp); return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; if (nodes_equal(*from, *to)) { mmput(mm); return; } mwork = kzalloc_obj(*mwork); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void flush_migrate_mm_task_workfn(struct callback_head *head) { flush_workqueue(cpuset_migrate_mm_wq); kfree(head); } static void schedule_flush_migrate_mm(void) { struct callback_head *flush_cb; flush_cb = kzalloc_obj(struct callback_head); if (!flush_cb) return; init_task_work(flush_cb, flush_migrate_mm_task_workfn); if (task_work_add(current, flush_cb, TWA_RESUME)) kfree(flush_cb); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * cpuset_update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. * * - cpuset_change_task_nodemask(): guarantee_online_mems() * - mpol_rebind_mm(): effective_mems * - cpuset_migrate_mm(): guarantee_online_mems() * - old_mems_allowed: guarantee_online_mems() * * For v2, guarantee_online_mems() should return a node mask that is the same * as the effective_mems of current cpuset. */ void cpuset_update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); /* Rebind and migrate mm only for thread group leader */ if (!thread_group_leader(task)) continue; mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); /* * For v1 we can have empty effective_mems, but we cannot * attach any tasks (see cpuset_can_attach_check()). For v2, * effective_mems is guaranteed to not be empty. */ mpol_rebind_mm(mm, &cs->effective_mems); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); compute_effective_nodemask(new_mems, cp, parent); /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); cpuset_update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * The validate_change() call ensures that cpusets with tasks have memory. */ retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) return retval; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) return -EINVAL; /* No change? nothing to do */ if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) return 0; retval = validate_change(cs, trialcs); if (retval < 0) return retval; check_insane_mems_config(&trialcs->mems_allowed); spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); return 0; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } /* * cpuset_update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ int cpuset_update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_page_changed; int err; trialcs = dup_or_alloc_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_page_changed = is_spread_page(cs) != is_spread_page(trialcs); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) { if (cpuset_v2()) cpuset_force_rebuild(); else rebuild_sched_domains_locked(); } if (spread_page_changed) cpuset1_update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /** * update_prstate - update partition_root_state * @cs: the cpuset to update * @new_prs: new partition root state * Return: 0 if successful, != 0 if error * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { int err = PERR_NONE, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; bool isolcpus_updated = false; if (old_prs == new_prs) return 0; /* * Treat a previously invalid partition root as if it is a "member". */ if (new_prs && is_partition_invalid(cs)) old_prs = PRS_MEMBER; if (alloc_tmpmasks(&tmpmask)) return -ENOMEM; err = update_partition_exclusive_flag(cs, new_prs); if (err) goto out; if (!old_prs) { /* * cpus_allowed and exclusive_cpus cannot be both empty. */ if (xcpus_empty(cs)) { err = PERR_CPUSEMPTY; goto out; } /* * We don't support the creation of a new local partition with * a remote partition underneath it. This unsupported * setting can happen only if parent is the top_cpuset because * a remote partition cannot be created underneath an existing * local or remote partition. */ if ((parent == &top_cpuset) && cpumask_intersects(cs->exclusive_cpus, subpartitions_cpus)) { err = PERR_REMOTE; goto out; } /* * If parent is valid partition, enable local partiion. * Otherwise, enable a remote partition. */ if (is_partition_valid(parent)) { enum partition_cmd cmd = (new_prs == PRS_ROOT) ? partcmd_enable : partcmd_enablei; err = update_parent_effective_cpumask(cs, cmd, NULL, &tmpmask); } else { err = remote_partition_enable(cs, new_prs, &tmpmask); } } else if (old_prs && new_prs) { /* * A change in load balance state only, no change in cpumasks. * Need to update isolated_cpus. */ if (((new_prs == PRS_ISOLATED) && !isolated_cpus_can_update(cs->effective_xcpus, NULL)) || prstate_housekeeping_conflict(new_prs, cs->effective_xcpus)) err = PERR_HKEEPING; else isolcpus_updated = true; } else { /* * Switching back to member is always allowed even if it * disables child partitions. */ if (is_remote_partition(cs)) remote_partition_disable(cs, &tmpmask); else update_parent_effective_cpumask(cs, partcmd_disable, NULL, &tmpmask); /* * Invalidation of child partitions will be done in * update_cpumasks_hier(). */ } out: /* * Make partition invalid & disable CS_CPU_EXCLUSIVE if an error * happens. */ if (err) { new_prs = -new_prs; update_partition_exclusive_flag(cs, new_prs); } spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; WRITE_ONCE(cs->prs_err, err); if (!is_partition_valid(cs)) reset_partition_data(cs); else if (isolcpus_updated) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); /* Force update if switching back to member & update effective_xcpus */ update_cpumasks_hier(cs, &tmpmask, !new_prs); /* A newly created partition must have effective_xcpus set */ WARN_ON_ONCE(!old_prs && (new_prs > 0) && cpumask_empty(cs->effective_xcpus)); /* Update sched domains and load balance flag */ update_partition_sd_lb(cs, old_prs); notify_partition_change(cs, old_prs); if (force_sd_rebuild) rebuild_sched_domains_locked(); free_tmpmasks(&tmpmask); return 0; } /* * Check to see if a cpuset can accept a new task * For v1, cpus_allowed and mems_allowed can't be empty. * For v2, effective_cpus can't be empty. * Note that in v1, effective_cpus = cpus_allowed. * * Also set the boolean flag passed in by @psetsched depending on if * security_task_setscheduler() call is needed and @oldcs is not NULL. */ static int cpuset_can_attach_check(struct cpuset *cs, struct cpuset *oldcs, bool *psetsched) { bool cpus_updated, mems_updated; if (cpumask_empty(cs->effective_cpus) || (!is_in_v2_mode() && nodes_empty(cs->mems_allowed))) return -ENOSPC; if (!oldcs) return 0; if (!llist_on_list(&oldcs->attach_node)) llist_add(&oldcs->attach_node, &src_cs_head); if (!llist_on_list(&cs->attach_node)) llist_add(&cs->attach_node, &dst_cs_head); cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus); mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems); if (cpus_updated) attach_ctx.cpus_updated = true; if (mems_updated) attach_ctx.mems_updated = true; /* * Skip rights over task setsched check in v2 when nothing changes for * the current oldcs/cs pair, migration permission derives from * hierarchy ownership in cgroup_procs_write_permission()). */ *psetsched = !cpuset_v2() || cpus_updated || mems_updated; /* * A v1 cpuset with tasks will have no CPU left only when CPU hotplug * brings the last online CPU offline as users are not allowed to empty * cpuset.cpus when there are active tasks inside. When that happens, * we should allow tasks to migrate out without security check to make * sure they will be able to run after migration. */ if (!is_in_v2_mode() && cpumask_empty(oldcs->effective_cpus)) *psetsched = false; return 0; } static int cpuset_reserve_dl_bw(void) { struct cpuset *cs; int cpu, ret; llist_for_each_entry(cs, dst_cs_head.first, attach_node) { if (!cs->sum_migrate_dl_bw) continue; cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) return -EINVAL; ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); if (ret) return ret; cs->dl_bw_cpu = cpu; } return 0; } /* * Clear and optionally apply (@cancel is false) the attach related data in the * source or destination cpuset. */ static void clear_attach_data(struct llist_head *head, bool cancel) { struct cpuset *cs, *next; struct llist_node *lnode = __llist_del_all(head); llist_for_each_entry_safe(cs, next, lnode, attach_node) { init_llist_node(&cs->attach_node); if (cs->nr_migrate_dl_tasks) { if (!cancel) atomic_add(cs->nr_migrate_dl_tasks, &cs->nr_deadline_tasks); else if (cs->dl_bw_cpu >= 0) /* && cancel */ dl_bw_free(cs->dl_bw_cpu, cs->sum_migrate_dl_bw); cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; cs->dl_bw_cpu = -1; } } } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; bool setsched_check; int ret; cs = oldcs = NULL; mutex_lock(&cpuset_mutex); attach_ctx.old_cs = NULL; /* Used later in cpuset_attach_task() */ attach_ctx.cpus_updated = false; attach_ctx.mems_updated = false; attach_ctx.many_dest_cs = false; /* * The attach_ctx.old_cs is used mainly by cpuset_migrate_mm() to get * the old_mems_allowed value. There are two ways that many-to-one * cpuset migration can happen: * 1) A multithread application with threads in different cpusets is * wholely migrated to a new cpuset. * 2) Disabling v2 cpuset controller will move all the tasks in child * cpusets to the parent cpuset. * * In the former case, it is the mm setting of the group leader that * really matters. So attach_ctx.old_cs should track the oldcs of the * group leader. It falls back to the oldcs of the first task if there * is no group leader in the taskset. In the latter case, effective_mems * of child cpusets must always be a subset of the parent. So no real * page migration will be necessary no matter which child cpuset is * selected as attach_ctx.old_cs. * * For a v2 threaded subtree where cpuset isn't enabled in some of the * cgroups, it is possible that oldcs == cs for some of the tasks. * In this case, we can skip checking on those tasks as there is no * actual migration wrt cpuset. */ cgroup_taskset_for_each(task, css, tset) { struct cpuset *new_cs = css_cs(css); struct cpuset *new_oldcs = task_cs(task); if ((new_oldcs != oldcs) || (new_cs != cs)) { if (cs && (new_cs != cs)) attach_ctx.many_dest_cs = true; cs = new_cs; oldcs = new_oldcs; if (oldcs == cs) continue; if (!attach_ctx.old_cs) attach_ctx.old_cs = oldcs; ret = cpuset_can_attach_check(cs, oldcs, &setsched_check); if (ret) goto out_unlock; } if (oldcs == cs) continue; ret = task_can_attach(task); if (ret) goto out_unlock; /* Update attach_ctx.old_cs to the latest group leader */ if (task == task->group_leader) attach_ctx.old_cs = task_cs(task); if (setsched_check) { ret = security_task_setscheduler(task); if (ret) goto out_unlock; } if (dl_task(task)) { /* * Count all migrating DL tasks for cpuset task accounting. * Only tasks that need a root-domain bandwidth move * contribute to sum_migrate_dl_bw. */ cs->nr_migrate_dl_tasks++; oldcs->nr_migrate_dl_tasks--; if (dl_task_needs_bw_move(task, cs->effective_cpus)) cs->sum_migrate_dl_bw += task->dl.dl_bw; } } /* * The only case where there are multiple destination cpusets for * task migration is when enabling a v2 cpuset controllers where * tasks will be migrated to multiple child cpusets from a parent * cpuset with the same effective CPUs and memory nodes. IOW, * both attach_cpus_updated and attach_mems_updated should be false. * If not, it is a condition that the current code cannot handle. * Print a warning and abort the attach operation as further code * change may be needed. */ if (WARN_ON_ONCE(attach_ctx.many_dest_cs && (!cpuset_v2() || attach_ctx.cpus_updated || attach_ctx.mems_updated))) { ret = -EINVAL; goto out_unlock; } ret = cpuset_reserve_dl_bw(); out_unlock: if (ret) { clear_attach_data(&src_cs_head, true); clear_attach_data(&dst_cs_head, true); } else { attach_ctx.in_progress++; } mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { mutex_lock(&cpuset_mutex); dec_attach_in_progress_locked(); clear_attach_data(&src_cs_head, true); clear_attach_data(&dst_cs_head, true); mutex_unlock(&cpuset_mutex); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task) { struct mm_struct *mm; lockdep_assert_cpuset_lock_held(); if (cs != &top_cpuset) guarantee_active_cpus(task, cpus_attach); else cpumask_andnot(cpus_attach, task_cpu_possible_mask(task), subpartitions_cpus); /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); if (cpuset_v2() && !attach_ctx.mems_updated) return; cpuset_change_task_nodemask(task, &attach_ctx.nodemask_to); cpuset1_update_task_spread_flags(cs, task); if ((task != task->group_leader) || !attach_ctx.mems_updated) return; /* * Change mm for threadgroup leader. This is expensive and may * sleep and should be moved outside migration path proper. */ mm = get_task_mm(task); if (mm) { struct cpuset *oldcs = attach_ctx.old_cs; mpol_rebind_mm(mm, &cs->effective_mems); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) { cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &attach_ctx.nodemask_to); attach_ctx.task_work_queued = true; } else { mmput(mm); } } } static void cpuset_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); attach_ctx.task_work_queued = false; guarantee_online_mems(cs, &attach_ctx.nodemask_to); /* * attach_ctx.old_cs can only be NULL if no task is actually migrating. * This is highly unlikely. If it happens at all, we can skip task * iteration and setting old_mems_allowed. */ if (unlikely(!attach_ctx.old_cs)) goto out; /* * In the default hierarchy, enabling cpuset in the child cgroups * will trigger a cpuset_attach() call with no change in effective cpus * and mems. In that case, we can optimize out by skipping the task * iteration and the destination cpuset list is iterated to set * old_mems_allowed. */ if (cpuset_v2() && !attach_ctx.cpus_updated && !attach_ctx.mems_updated) { llist_for_each_entry(cs, dst_cs_head.first, attach_node) cs->old_mems_allowed = attach_ctx.nodemask_to; goto out; } cgroup_taskset_for_each(task, css, tset) cpuset_attach_task(cs, task); if (attach_ctx.task_work_queued) schedule_flush_migrate_mm(); cs->old_mems_allowed = attach_ctx.nodemask_to; out: clear_attach_data(&src_cs_head, false); clear_attach_data(&dst_cs_head, false); dec_attach_in_progress_locked(); mutex_unlock(&cpuset_mutex); } /* * Common handling for a write to a "cpus" or "mems" file. */ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; /* root is read-only */ if (cs == &top_cpuset) return -EACCES; buf = strstrip(buf); /* cpuset_mutex acquired in wait_attach_done_lock() */ mutex_lock(&cpuset_top_mutex); cpus_read_lock(); wait_attach_done_lock(); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = dup_or_alloc_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_EXCLUSIVE_CPULIST: retval = update_exclusive_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: cpuset_update_sd_hk_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_EXCLUSIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->exclusive_cpus)); break; case FILE_EFFECTIVE_XCPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_xcpus)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(subpartitions_cpus)); break; case FILE_ISOLATED_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(isolated_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static int cpuset_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); const char *err, *type = NULL; switch (cs->partition_root_state) { case PRS_ROOT: seq_puts(seq, "root\n"); break; case PRS_ISOLATED: seq_puts(seq, "isolated\n"); break; case PRS_MEMBER: seq_puts(seq, "member\n"); break; case PRS_INVALID_ROOT: type = "root"; fallthrough; case PRS_INVALID_ISOLATED: if (!type) type = "isolated"; err = perr_strings[READ_ONCE(cs->prs_err)]; if (err) seq_printf(seq, "%s invalid (%s)\n", type, err); else seq_printf(seq, "%s invalid\n", type); break; } return 0; } static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); if (!strcmp(buf, "root")) val = PRS_ROOT; else if (!strcmp(buf, "member")) val = PRS_MEMBER; else if (!strcmp(buf, "isolated")) val = PRS_ISOLATED; else return -EINVAL; mutex_lock(&cpuset_top_mutex); cpus_read_lock(); wait_attach_done_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); cpuset_update_sd_hk_unlock(); return retval ?: nbytes; } /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = cpuset_partition_show, .write = cpuset_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cpuset, partition_file), }, { .name = "cpus.exclusive", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_EXCLUSIVE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.exclusive.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_XCPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_ONLY_ON_ROOT | CFTYPE_DEBUG, }, { .name = "cpus.isolated", .seq_show = cpuset_common_seq_show, .private = FILE_ISOLATED_CPULIST, .flags = CFTYPE_ONLY_ON_ROOT, }, { } /* terminate */ }; /** * cpuset_css_alloc - Allocate a cpuset css * @parent_css: Parent css of the control group that the new cpuset will be * part of * Return: cpuset css on success, -ENOMEM on failure. * * Allocate and initialize a new cpuset css, for non-NULL @parent_css, return * top cpuset css otherwise. */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = dup_or_alloc_cpuset(NULL); if (!cs) return ERR_PTR(-ENOMEM); __set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpuset1_init(cs); /* Set CS_MEMORY_MIGRATE for default hierarchy */ if (cpuset_v2()) __set_bit(CS_MEMORY_MIGRATE, &cs->flags); return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); if (!parent) return 0; cpuset_full_lock(); /* * For v2, clear CS_SCHED_LOAD_BALANCE if parent is isolated */ if (cpuset_v2() && !is_sched_load_balance(parent)) clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; } spin_unlock_irq(&callback_lock); cpuset1_online_css(css); cpuset_full_unlock(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); cpuset_full_lock(); if (!cpuset_v2() && is_sched_load_balance(cs)) cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); cpuset_dec(); cpuset_full_unlock(); } /* * If a dying cpuset has the 'cpus.partition' enabled, turn it off by * changing it back to member to free its exclusive CPUs back to the pool to * be used by other online cpusets. */ static void cpuset_css_killed(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); cpuset_full_lock(); /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); cpuset_update_sd_hk_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); cpumask_copy(top_cpuset.effective_xcpus, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } /* * In case the child is cloned into a cpuset different from its parent, * additional checks are done to see if the move is allowed. */ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) { struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); bool same_cs; int ret; rcu_read_lock(); same_cs = (cs == task_cs(current)); rcu_read_unlock(); if (same_cs) return 0; lockdep_assert_held(&cgroup_mutex); mutex_lock(&cpuset_mutex); /* Check to see if task is allowed in the cpuset */ ret = cpuset_can_attach_check(cs, NULL, NULL); if (ret) goto out_unlock; ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; attach_ctx.in_progress++; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) { struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); bool same_cs; rcu_read_lock(); same_cs = (cs == task_cs(current)); rcu_read_unlock(); if (same_cs) return; dec_attach_in_progress(); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { struct cpuset *cs, *oldcs; rcu_read_lock(); cs = task_cs(task); oldcs = task_cs(current); rcu_read_unlock(); if (cs == oldcs) { if (cs == &top_cpuset) return; set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; return; } /* CLONE_INTO_CGROUP */ mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &attach_ctx.nodemask_to); cs->old_mems_allowed = attach_ctx.nodemask_to; /* * Assume CPUs and memory nodes are updated * A CLONE_INTO_CGROUP operation should have taken the cgroup mutex * and so there shouldn't be a competing cpuset_attach() operation. */ attach_ctx.cpus_updated = attach_ctx.mems_updated = true; attach_ctx.task_work_queued = false; attach_ctx.old_cs = oldcs; cpuset_attach_task(cs, task); if (attach_ctx.task_work_queued) schedule_flush_migrate_mm(); dec_attach_in_progress_locked(); mutex_unlock(&cpuset_mutex); } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_killed = cpuset_css_killed, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .bind = cpuset_bind, .can_fork = cpuset_can_fork, .cancel_fork = cpuset_cancel_fork, .fork = cpuset_fork, #ifdef CONFIG_CPUSETS_V1 .legacy_cftypes = cpuset1_files, #endif .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_xcpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); cpumask_setall(top_cpuset.effective_xcpus); cpumask_setall(top_cpuset.exclusive_cpus); nodes_setall(top_cpuset.effective_mems); init_llist_node(&top_cpuset.attach_node); cpuset1_init(&top_cpuset); BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); if (housekeeping_enabled(HK_TYPE_DOMAIN_BOOT)) cpumask_andnot(isolated_cpus, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)); return 0; } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { /* A partition root is allowed to have empty effective cpus */ if (cpumask_empty(new_cpus) && !is_partition_valid(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) cpuset_update_tasks_cpumask(cs, new_cpus); if (mems_updated) cpuset_update_tasks_nodemask(cs); } void cpuset_force_rebuild(void) { force_sd_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; bool remote; int partcmd = -1; struct cpuset *parent; wait_attach_done_lock(); parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); compute_effective_nodemask(&new_mems, cs, parent); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * Compute effective_cpus for valid partition root, may invalidate * child partition roots if necessary. */ remote = is_remote_partition(cs); if (remote || (is_partition_valid(cs) && is_partition_valid(parent))) compute_partition_effective_cpumask(cs, &new_cpus); if (remote && (cpumask_empty(subpartitions_cpus) || (cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)))) { WRITE_ONCE(cs->prs_err, PERR_HOTPLUG); remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); remote = false; } /* * Force the partition to become invalid if either one of * the following conditions hold: * 1) empty effective cpus but not valid empty partition. * 2) parent is invalid or doesn't grant any cpus to child * partitions. * 3) subpartitions_cpus is empty. */ if (is_local_partition(cs) && (!is_partition_valid(parent) || tasks_nocpu_error(parent, cs, &new_cpus) || cpumask_empty(subpartitions_cpus))) partcmd = partcmd_invalidate; /* * On the other hand, an invalid partition root may be transitioned * back to a regular one with a non-empty effective xcpus. */ else if (is_partition_valid(parent) && is_partition_invalid(cs) && !cpumask_empty(cs->effective_xcpus)) partcmd = partcmd_update; if (partcmd >= 0) { update_parent_effective_cpumask(cs, partcmd, NULL, tmp); if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) { compute_partition_effective_cpumask(cs, &new_cpus); cpuset_force_rebuild(); } } update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (!cpus_updated && !mems_updated) goto unlock; /* Hotplug doesn't affect this cpuset */ if (mems_updated) check_insane_mems_config(&new_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else cpuset1_hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); unlock: mutex_unlock(&cpuset_mutex); } /** * cpuset_handle_hotplug - handle CPU/memory hot{,un}plug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. * * CPU / memory hotplug is handled synchronously. */ static void cpuset_handle_hotplug(void) { static DECLARE_WORK(hk_sd_work, hk_sd_workfn); static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_tmpmasks(&tmp)) ptmp = &tmp; lockdep_assert_cpus_held(); mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subpartitions_cpus is populated, it is likely that the check * below will produce a false positive on cpus_updated when the cpu * list isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus) || !cpumask_empty(subpartitions_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* For v1, synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { cpuset_force_rebuild(); spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subpartitions_cpus & let the child partitions * fight for the CPUs again. */ if (!cpumask_empty(subpartitions_cpus)) { if (cpumask_subset(&new_cpus, subpartitions_cpus)) { cpumask_clear(subpartitions_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, subpartitions_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); cpuset_update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* * rebuild_sched_domains() will always be called directly if needed * to make sure that newly added or removed CPU will be reflected in * the sched domains. However, if isolated partition invalidation * or recreation is being done (update_housekeeping set), a work item * will be queued to call housekeeping_update() to update the * corresponding housekeeping cpumasks after some slight delay. * * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that * is still pending. Before the pending bit is cleared, the work data * is copied out and work item dequeued. So it is possible to queue * the work again before the hk_sd_workfn() is invoked to process the * previously queued work. Since hk_sd_workfn() doesn't use the work * item at all, this is not a problem. */ if (force_sd_rebuild) rebuild_sched_domains_cpuslocked(); if (update_housekeeping) queue_work(system_dfl_wq, &hk_sd_work); free_tmpmasks(ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ cpuset_handle_hotplug(); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { cpuset_handle_hotplug(); return NOTIFY_OK; } /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; hotplug_node_notifier(cpuset_track_online_nodes, CPUSET_CALLBACK_PRI); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /* * Return cpus_allowed mask from a task's cpuset. */ static void __cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask) { struct cpuset *cs; cs = task_cs(tsk); if (cs != &top_cpuset) guarantee_active_cpus(tsk, pmask); /* * Tasks in the top cpuset won't get update to their cpumasks * when a hotplug online/offline event happens. So we include all * offline cpus in the allowed cpu list. */ if ((cs == &top_cpuset) || cpumask_empty(pmask)) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); /* * We first exclude cpus allocated to partitions. If there is no * allowable online cpu left, we fall back to all possible cpus. */ cpumask_andnot(pmask, possible_mask, subpartitions_cpus); if (!cpumask_intersects(pmask, cpu_active_mask)) cpumask_copy(pmask, possible_mask); } } /** * cpuset_cpus_allowed_locked - return cpus_allowed mask from a task's cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Similir to cpuset_cpus_allowed() except that the caller must have acquired * cpuset_mutex. */ void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask) { lockdep_assert_cpuset_lock_held(); __cpuset_cpus_allowed_locked(tsk, pmask); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a task's cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_active_mask, even if this means going outside the * tasks cpuset, except when the task is in the top cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; spin_lock_irqsave(&callback_lock, flags); __cpuset_cpus_allowed_locked(tsk, pmask); spin_unlock_irqrestore(&callback_lock, flags); } /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. * * Returns true if the affinity of @tsk was changed, false otherwise. **/ bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); const struct cpumask *cs_mask; bool changed = false; rcu_read_lock(); cs_mask = task_cs(tsk)->cpus_allowed; if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { set_cpus_allowed_force(tsk, cs_mask); changed = true; } rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ return changed; } /* * Returns the number of CPUs available for this cgroup. * * This only really works for cgroup-v2 where all the controllers are mounted * in the same hierarchy. If not cgroup-v2 or no cpuset controller is * configured it reverts to num_online_cpus(). */ int cpuset_num_cpus(struct cgroup *cgrp) { int nr = num_online_cpus(); struct cpuset *cs; if (is_in_v2_mode()) { guard(rcu)(); cs = css_cs(cgroup_e_css(cgrp, &cpuset_cgrp_subsys)); if (cs) nr = cpumask_weight(cs->effective_cpus); } return nr; } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); guarantee_online_mems(task_cs(tsk), &mask); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(const nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /* * cpuset_current_node_allowed - Can current task allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * If the current task is PF_EXITING, yes. Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed or is exiting. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * page allocator only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). The PF_EXITING check must therefore * come before the __GFP_HARDWALL check, otherwise a dying task * would be blocked on the fast path. * * The second pass through get_page_from_freelist() doesn't even call here for * GFP_ATOMIC calls. That, and the checks below have the combined affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * PF_EXITING - any node ok (let dying task exit quickly) * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ bool allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (cpuset_v2()) return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_nodes_allowed - return effective_mems mask from a cgroup cpuset. * @cgroup: pointer to struct cgroup. * @mask: pointer to struct nodemask_t to be returned. * * Returns effective_mems mask from a cgroup cpuset if it is cgroup v2 and * has cpuset subsys. Otherwise, returns node_states[N_MEMORY]. * * This function intentionally avoids taking the cpuset_mutex or callback_lock * when accessing effective_mems. This is because the obtained effective_mems * is stale immediately after the query anyway (e.g., effective_mems is updated * immediately after releasing the lock but before returning). * * As a result, returned @mask may be empty because cs->effective_mems can be * rebound during this call. Besides, nodes in @mask are not guaranteed to be * online due to hot plugins. Callers should check the mask for validity on * return based on its subsequent use. **/ void cpuset_nodes_allowed(struct cgroup *cgroup, nodemask_t *mask) { struct cgroup_subsys_state *css; struct cpuset *cs; /* * In v1, mem_cgroup and cpuset are unlikely in the same hierarchy * and mems_allowed is likely to be empty even if we could get to it, * so return directly to avoid taking a global lock on the empty check. */ if (!cgroup || !cpuset_v2()) { nodes_copy(*mask, node_states[N_MEMORY]); return; } css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys); if (!css) { nodes_copy(*mask, node_states[N_MEMORY]); return; } /* * The reference taken via cgroup_get_e_css is sufficient to * protect css, but it does not imply safe accesses to effective_mems. * * Normally, accessing effective_mems would require the cpuset_mutex * or callback_lock - but the correctness of this information is stale * immediately after the query anyway. We do not acquire the lock * during this process to save lock contention in exchange for racing * against mems_allowed rebinds. */ cs = container_of(css, struct cpuset, css); nodes_copy(*mask, cs->effective_mems); css_put(css); } /** * cpuset_spread_node() - On which node to begin search for a page * @rotor: round robin rotor * * If a task is marked PFA_SPREAD_PAGE and a page cache allocation uses * cpuset_mem_spread_node() to determine where to start looking, spread the * starting node around the task's mems_allowed nodes instead of starting on * the local node. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist used by * the allocator will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } /** * cpuset_mem_spread_node() - On which node to begin search for a file page */ int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 307 145 214 307 41 40 41 6201 6124 5938 5908 15 121 5828 12 65 1 1569 1570 1569 287 287 287 38 38 108 95 11 4262 1397 4130 28 3 1 1 1844 43 43 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kdebug.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/vmalloc.h> #define CREATE_TRACE_POINTS #include <trace/events/notifier.h> /* * Notifier chain core routines. The exported routines below * are layered on top of these, with appropriate locking added. */ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n, bool unique_priority) { while ((*nl) != NULL) { if (unlikely((*nl) == n)) { WARN(1, "notifier callback %ps already registered", n->notifier_call); return -EEXIST; } if (n->priority > (*nl)->priority) break; if (n->priority == (*nl)->priority && unique_priority) return -EBUSY; nl = &((*nl)->next); } n->next = *nl; rcu_assign_pointer(*nl, n); trace_notifier_register((void *)n->notifier_call); return 0; } static int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { if ((*nl) == n) { rcu_assign_pointer(*nl, n->next); trace_notifier_unregister((void *)n->notifier_call); return 0; } nl = &((*nl)->next); } return -ENOENT; } /** * notifier_call_chain - Informs the registered notifiers about an event. * @nl: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * @nr_to_call: Number of notifier functions to be called. Don't care * value of this parameter is -1. * @nr_calls: Records the number of notifications sent. Don't care * value of this field is NULL. * Return: notifier_call_chain returns the value returned by the * last notifier function called. */ static int notifier_call_chain(struct notifier_block **nl, unsigned long val, void *v, int nr_to_call, int *nr_calls) { int ret = NOTIFY_DONE; struct notifier_block *nb, *next_nb; nb = rcu_dereference_raw(*nl); while (nb && nr_to_call) { next_nb = rcu_dereference_raw(nb->next); #ifdef CONFIG_DEBUG_NOTIFIERS if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { WARN(1, "Invalid notifier called!"); nb = next_nb; continue; } #endif trace_notifier_run((void *)nb->notifier_call); ret = nb->notifier_call(nb, val, v); if (nr_calls) (*nr_calls)++; if (ret & NOTIFY_STOP_MASK) break; nb = next_nb; nr_to_call--; } return ret; } NOKPROBE_SYMBOL(notifier_call_chain); /** * notifier_call_chain_robust - Inform the registered notifiers about an event * and rollback on error. * @nl: Pointer to head of the blocking notifier chain * @val_up: Value passed unmodified to the notifier function * @val_down: Value passed unmodified to the notifier function when recovering * from an error on @val_up * @v: Pointer passed unmodified to the notifier function * * NOTE: It is important the @nl chain doesn't change between the two * invocations of notifier_call_chain() such that we visit the * exact same notifier callbacks; this rules out any RCU usage. * * Return: the return value of the @val_up call. */ static int notifier_call_chain_robust(struct notifier_block **nl, unsigned long val_up, unsigned long val_down, void *v) { int ret, nr = 0; ret = notifier_call_chain(nl, val_up, v, -1, &nr); if (ret & NOTIFY_STOP_MASK) notifier_call_chain(nl, val_down, v, nr-1, NULL); return ret; } /* * Atomic notifier chain routines. Registration and unregistration * use a spinlock, and call_chain is synchronized by RCU (no locks). */ /** * atomic_notifier_chain_register - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain. * * Returns 0 on success, %-EEXIST on error. */ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, false); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); /** * atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, true); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio); /** * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an atomic notifier chain. * * Returns zero on success or %-ENOENT on failure. */ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_unregister(&nh->head, n); spin_unlock_irqrestore(&nh->lock, flags); synchronize_rcu(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); /** * atomic_notifier_call_chain - Call functions in an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an atomic context, so they must not block. * This routine uses RCU to synchronize with changes to the chain. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then atomic_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v) { int ret; rcu_read_lock(); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); NOKPROBE_SYMBOL(atomic_notifier_call_chain); /** * atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty * @nh: Pointer to head of the atomic notifier chain * * Checks whether notifier chain is empty. * * Returns true is notifier chain is empty, false otherwise. */ bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh) { return !rcu_access_pointer(nh->head); } /* * Blocking notifier chain routines. All access to the chain is * synchronized by an rwsem. */ static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n, bool unique_priority) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, unique_priority); down_write(&nh->rwsem); ret = notifier_chain_register(&nh->head, n, unique_priority); up_write(&nh->rwsem); return ret; } /** * blocking_notifier_chain_register - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to a blocking notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, false); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); /** * blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to an blocking notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, true); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio); /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a blocking notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); down_write(&nh->rwsem); ret = notifier_chain_unregister(&nh->head, n); up_write(&nh->rwsem); return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister); int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust); /** * blocking_notifier_call_chain - Call functions in a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then blocking_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); /* * Raw notifier chain routines. There is no protection; * the caller must provide it. Use at your own risk! */ /** * raw_notifier_chain_register - Add notifier to a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: New entry in notifier chain * * Adds a notifier to a raw notifier chain. * All locking must be provided by the caller. * * Returns 0 on success, %-EEXIST on error. */ int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_register(&nh->head, n, false); } EXPORT_SYMBOL_GPL(raw_notifier_chain_register); /** * raw_notifier_chain_unregister - Remove notifier from a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a raw notifier chain. * All locking must be provided by the caller. * * Returns zero on success or %-ENOENT on failure. */ int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_unregister(&nh->head, n); } EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister); int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { return notifier_call_chain_robust(&nh->head, val_up, val_down, v); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust); /** * raw_notifier_call_chain - Call functions in a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an undefined context. * All locking must be provided by the caller. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then raw_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v) { return notifier_call_chain(&nh->head, val, v, -1, NULL); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). */ /** * srcu_notifier_chain_register - Add notifier to an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: New entry in notifier chain * * Adds a notifier to an SRCU notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, false); mutex_lock(&nh->mutex); ret = notifier_chain_register(&nh->head, n, false); mutex_unlock(&nh->mutex); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_register); /** * srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an SRCU notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); mutex_lock(&nh->mutex); ret = notifier_chain_unregister(&nh->head, n); mutex_unlock(&nh->mutex); synchronize_srcu(&nh->srcu); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister); /** * srcu_notifier_call_chain - Call functions in an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then srcu_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v) { int ret; int idx; idx = srcu_read_lock(&nh->srcu); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); srcu_read_unlock(&nh->srcu, idx); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_call_chain); /** * srcu_init_notifier_head - Initialize an SRCU notifier head * @nh: Pointer to head of the srcu notifier chain * * Unlike other sorts of notifier heads, SRCU notifier heads require * dynamic initialization. Be sure to call this routine before * calling any of the other SRCU notifier routines for this head. * * If an SRCU notifier head is deallocated, it must first be cleaned * up by calling srcu_cleanup_notifier_head(). Otherwise the head's * per-cpu data (used by the SRCU mechanism) will leak. */ void srcu_init_notifier_head(struct srcu_notifier_head *nh) { mutex_init(&nh->mutex); if (init_srcu_struct(&nh->srcu) < 0) BUG(); nh->head = NULL; } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { .regs = regs, .str = str, .err = err, .trapnr = trap, .signr = sig, }; RCU_LOCKDEP_WARN(!rcu_is_watching(), "notify_die called but RCU thinks we're quiescent"); return atomic_notifier_call_chain(&die_chain, val, &args); } NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); int unregister_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&die_chain, nb); } EXPORT_SYMBOL_GPL(unregister_die_notifier); |
| 2 2 2 2 2 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> #include <net/flow.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/route.h> /* don't try to find route from mcast/bcast/zeronet */ static __be32 get_saddr(__be32 addr) { if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) || ipv4_is_zeronet(addr)) return 0; return addr; } void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); u32 *dst = ®s->data[priv->dreg]; const struct net_device *dev = NULL; struct iphdr *iph, _iph; __be32 addr; if (priv->flags & NFTA_FIB_F_IIF) dev = nft_in(pkt); else if (priv->flags & NFTA_FIB_F_OIF) dev = nft_out(pkt); iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { regs->verdict.code = NFT_BREAK; return; } if (priv->flags & NFTA_FIB_F_DADDR) addr = iph->daddr; else addr = iph->saddr; if (priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) { *dst = inet_dev_addr_type(nft_net(pkt), dev, addr); return; } *dst = inet_addr_type_dev_table(nft_net(pkt), pkt->skb->dev, addr); } EXPORT_SYMBOL_GPL(nft_fib4_eval_type); void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); u32 *dest = ®s->data[priv->dreg]; struct iphdr *iph, _iph; struct fib_result res; struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_proto = pkt->tprot, .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), }; const struct net_device *oif; const struct net_device *found; if (nft_fib_can_skip(pkt)) { nft_fib_store_result(dest, priv, nft_in(pkt)); return; } /* * Do not set flowi4_oif, it restricts results (for example, asking * for oif 3 will get RTN_UNICAST result even if the daddr exits * on another interface. * * Search results for the desired outinterface instead. */ if (priv->flags & NFTA_FIB_F_OIF) oif = nft_out(pkt); else if (priv->flags & NFTA_FIB_F_IIF) oif = nft_in(pkt); else oif = NULL; fl4.flowi4_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, oif); iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); if (!iph) { regs->verdict.code = NFT_BREAK; return; } if (ipv4_is_zeronet(iph->saddr)) { if (ipv4_is_lbcast(iph->daddr) || ipv4_is_local_multicast(iph->daddr)) { nft_fib_store_result(dest, priv, pkt->skb->dev); return; } } if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; fl4.flowi4_dscp = ip4h_dscp(iph); if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; fl4.saddr = get_saddr(iph->saddr); } else { if (nft_hook(pkt) == NF_INET_FORWARD && priv->flags & NFTA_FIB_F_IIF) fl4.flowi4_iif = nft_out(pkt)->ifindex; fl4.daddr = iph->saddr; fl4.saddr = get_saddr(iph->daddr); } nft_fib_store_result(dest, priv, NULL); if (fib_lookup(nft_net(pkt), &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) return; switch (res.type) { case RTN_UNICAST: break; case RTN_LOCAL: /* Should not see RTN_LOCAL here */ return; default: break; } if (!oif) { found = FIB_RES_DEV(res); } else { if (!fib_info_nh_uses_dev(res.fi, oif)) return; found = oif; } nft_fib_store_result(dest, priv, found); } EXPORT_SYMBOL_GPL(nft_fib4_eval); static struct nft_expr_type nft_fib4_type; static const struct nft_expr_ops nft_fib4_type_ops = { .type = &nft_fib4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib4_eval_type, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, }; static const struct nft_expr_ops nft_fib4_ops = { .type = &nft_fib4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib4_eval, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, }; static const struct nft_expr_ops * nft_fib4_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { enum nft_fib_result result; if (!tb[NFTA_FIB_RESULT]) return ERR_PTR(-EINVAL); result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); switch (result) { case NFT_FIB_RESULT_OIF: return &nft_fib4_ops; case NFT_FIB_RESULT_OIFNAME: return &nft_fib4_ops; case NFT_FIB_RESULT_ADDRTYPE: return &nft_fib4_type_ops; default: return ERR_PTR(-EOPNOTSUPP); } } static struct nft_expr_type nft_fib4_type __read_mostly = { .name = "fib", .select_ops = nft_fib4_select_ops, .policy = nft_fib_policy, .maxattr = NFTA_FIB_MAX, .family = NFPROTO_IPV4, .owner = THIS_MODULE, }; static int __init nft_fib4_module_init(void) { return nft_register_expr(&nft_fib4_type); } static void __exit nft_fib4_module_exit(void) { nft_unregister_expr(&nft_fib4_type); } module_init(nft_fib4_module_init); module_exit(nft_fib4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(2, "fib"); MODULE_DESCRIPTION("nftables fib / ip route lookup support"); |
| 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 | /* * Copyright (c) 2002 Red Hat, Inc. All rights reserved. * * This software may be freely redistributed under the terms of the * GNU General Public License. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Authors: David Woodhouse <dwmw2@infradead.org> * David Howells <dhowells@redhat.com> * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/sched.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/iversion.h> #include "internal.h" #include "afs_fs.h" static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode) { static unsigned long once_only; pr_warn("kAFS: AFS vnode with undefined type %u\n", vnode->status.type); pr_warn("kAFS: A=%d m=%o s=%llx v=%llx\n", vnode->status.abort_code, vnode->status.mode, vnode->status.size, vnode->status.data_version); pr_warn("kAFS: vnode %llx:%llx:%x\n", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); if (parent_vnode) pr_warn("kAFS: dir %llx:%llx:%x\n", parent_vnode->fid.vid, parent_vnode->fid.vnode, parent_vnode->fid.unique); if (!test_and_set_bit(0, &once_only)) dump_stack(); } /* * Set parameters for the netfs library */ static void afs_set_netfs_context(struct afs_vnode *vnode, bool is_file) { netfs_inode_init(&vnode->netfs, &afs_req_ops, is_file); } /* * Initialise an inode from the vnode status. */ static int afs_inode_init_from_status(struct afs_operation *op, struct afs_vnode_param *vp, struct afs_vnode *vnode) { struct afs_file_status *status = &vp->scb.status; struct inode *inode = AFS_VNODE_TO_I(vnode); struct timespec64 t; _enter("{%llx:%llu.%u} %s", vp->fid.vid, vp->fid.vnode, vp->fid.unique, op->type ? op->type->name : "???"); _debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu", status->type, status->nlink, (unsigned long long) status->size, status->data_version, status->mode); write_seqlock(&vnode->cb_lock); vnode->cb_v_check = op->cb_v_break; vnode->status = *status; t = status->mtime_client; inode_set_ctime_to_ts(inode, t); inode_set_mtime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); inode->i_flags |= S_NOATIME; inode->i_uid = make_kuid(&init_user_ns, status->owner); inode->i_gid = make_kgid(&init_user_ns, status->group); set_nlink(&vnode->netfs.inode, status->nlink); i_size_write(inode, status->size); inode_set_bytes(inode, status->size); afs_set_netfs_context(vnode, status->type == AFS_FTYPE_FILE); switch (status->type) { case AFS_FTYPE_FILE: inode->i_mode = S_IFREG | (status->mode & S_IALLUGO); inode->i_op = &afs_file_inode_operations; inode->i_fop = &afs_file_operations; inode->i_mapping->a_ops = &afs_file_aops; mapping_set_large_folios(inode->i_mapping); break; case AFS_FTYPE_DIR: inode->i_mode = S_IFDIR | (status->mode & S_IALLUGO); inode->i_op = &afs_dir_inode_operations; inode->i_fop = &afs_dir_file_operations; inode->i_mapping->a_ops = &afs_dir_aops; __set_bit(NETFS_ICTX_SINGLE_NO_UPLOAD, &vnode->netfs.flags); /* Assume locally cached directory data will be valid. */ __set_bit(AFS_VNODE_DIR_VALID, &vnode->flags); break; case AFS_FTYPE_SYMLINK: /* Symlinks with a mode of 0644 are actually mountpoints. */ if ((status->mode & 0777) == 0644) { inode->i_flags |= S_AUTOMOUNT; set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); inode->i_mode = S_IFDIR | 0555; inode->i_op = &afs_mntpt_inode_operations; inode->i_fop = &afs_mntpt_file_operations; } else { inode->i_mode = S_IFLNK | status->mode; inode->i_op = &afs_symlink_inode_operations; } inode->i_mapping->a_ops = &afs_symlink_aops; inode_nohighmem(inode); break; default: dump_vnode(vnode, op->file[0].vnode != vnode ? op->file[0].vnode : NULL); write_sequnlock(&vnode->cb_lock); return afs_protocol_error(NULL, afs_eproto_file_type); } vnode->invalid_before = status->data_version; trace_afs_set_dv(vnode, status->data_version); inode_set_iversion_raw(&vnode->netfs.inode, status->data_version); if (!vp->scb.have_cb) { /* it's a symlink we just created (the fileserver * didn't give us a callback) */ afs_clear_cb_promise(vnode, afs_cb_promise_set_new_symlink); } else { vnode->cb_server = op->server; afs_set_cb_promise(vnode, vp->scb.callback.expires_at, afs_cb_promise_set_new_inode); } write_sequnlock(&vnode->cb_lock); return 0; } /* * Update the core inode struct from a returned status record. */ static void afs_apply_status(struct afs_operation *op, struct afs_vnode_param *vp) { struct afs_file_status *status = &vp->scb.status; struct afs_vnode *vnode = vp->vnode; struct netfs_inode *ictx = &vnode->netfs; struct inode *inode = &ictx->inode; struct timespec64 t; umode_t mode; bool unexpected_jump = false; bool data_changed = false; bool change_size = vp->set_size; _enter("{%llx:%llu.%u} %s", vp->fid.vid, vp->fid.vnode, vp->fid.unique, op->type ? op->type->name : "???"); BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags)); if (status->type != vnode->status.type) { pr_warn("Vnode %llx:%llx:%x changed type %u to %u\n", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, status->type, vnode->status.type); afs_protocol_error(NULL, afs_eproto_bad_status); return; } if (status->nlink != vnode->status.nlink) set_nlink(inode, status->nlink); if (status->owner != vnode->status.owner) inode->i_uid = make_kuid(&init_user_ns, status->owner); if (status->group != vnode->status.group) inode->i_gid = make_kgid(&init_user_ns, status->group); if (status->mode != vnode->status.mode) { mode = inode->i_mode; mode &= ~S_IALLUGO; mode |= status->mode & S_IALLUGO; WRITE_ONCE(inode->i_mode, mode); } t = status->mtime_client; inode_set_mtime_to_ts(inode, t); if (vp->update_ctime) inode_set_ctime_to_ts(inode, op->ctime); if (vnode->status.data_version != status->data_version) { trace_afs_set_dv(vnode, status->data_version); data_changed = true; } vnode->status = *status; if (vp->dv_before + vp->dv_delta != status->data_version) { trace_afs_dv_mismatch(vnode, vp->dv_before, vp->dv_delta, status->data_version); if (vnode->cb_ro_snapshot == atomic_read(&vnode->volume->cb_ro_snapshot) && atomic64_read(&vnode->cb_expires_at) != AFS_NO_CB_PROMISE) pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n", vnode->fid.vid, vnode->fid.vnode, (unsigned long long)vp->dv_before + vp->dv_delta, (unsigned long long)status->data_version, op->type ? op->type->name : "???", op->debug_id); vnode->invalid_before = status->data_version; if (vnode->status.type == AFS_FTYPE_DIR) afs_invalidate_dir(vnode, afs_dir_invalid_dv_mismatch); else set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); change_size = true; data_changed = true; unexpected_jump = true; } else if (vnode->status.type == AFS_FTYPE_DIR) { /* Expected directory change is handled elsewhere so * that we can locally edit the directory and save on a * download. */ if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) data_changed = false; change_size = true; } if (data_changed) { unsigned long long zero_point, size = status->size; inode_set_iversion_raw(inode, status->data_version); /* Only update the size if the data version jumped. If the * file is being modified locally, then we might have our own * idea of what the size should be that's not the same as * what's on the server. */ spin_lock(&inode->i_lock); if (change_size || size > i_size_read(inode)) { /* We can read the sizes directly as we hold i_lock. */ zero_point = ictx->_zero_point; if (unexpected_jump) zero_point = size; netfs_write_sizes(inode, size, size, zero_point); inode_set_bytes(inode, size); inode_set_ctime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); } else { netfs_write_remote_i_size(inode, size); } spin_unlock(&inode->i_lock); if (op->ops == &afs_fetch_data_operation) op->fetch.subreq->rreq->i_size = size; } } /* * Apply a callback to a vnode. */ static void afs_apply_callback(struct afs_operation *op, struct afs_vnode_param *vp) { struct afs_callback *cb = &vp->scb.callback; struct afs_vnode *vnode = vp->vnode; if (!afs_cb_is_broken(vp->cb_break_before, vnode)) { if (op->volume->type == AFSVL_RWVOL) vnode->cb_server = op->server; afs_set_cb_promise(vnode, cb->expires_at, afs_cb_promise_set_apply_cb); } } /* * Apply the received status and callback to an inode all in the same critical * section to avoid races with afs_validate(). */ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *vp) { struct afs_vnode *vnode = vp->vnode; _enter(""); write_seqlock(&vnode->cb_lock); if (vp->scb.have_error) { /* A YFS server will return this from RemoveFile2 and AFS and * YFS will return this from InlineBulkStatus. */ if (vp->scb.status.abort_code == VNOVNODE) { set_bit(AFS_VNODE_DELETED, &vnode->flags); clear_nlink(&vnode->netfs.inode); __afs_break_callback(vnode, afs_cb_break_for_deleted); op->flags &= ~AFS_OPERATION_DIR_CONFLICT; } } else if (vp->scb.have_status) { if (vp->speculative && (test_bit(AFS_VNODE_MODIFYING, &vnode->flags) || vp->dv_before != vnode->status.data_version)) /* Ignore the result of a speculative bulk status fetch * if it splits around a modification op, thereby * appearing to regress the data version. */ goto out; afs_apply_status(op, vp); if (vp->scb.have_cb) afs_apply_callback(op, vp); } else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) { drop_nlink(&vnode->netfs.inode); if (vnode->netfs.inode.i_nlink == 0) { set_bit(AFS_VNODE_DELETED, &vnode->flags); __afs_break_callback(vnode, afs_cb_break_for_deleted); } } out: write_sequnlock(&vnode->cb_lock); if (vp->scb.have_status) afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb); } static void afs_fetch_status_success(struct afs_operation *op) { struct afs_vnode_param *vp = &op->file[op->fetch_status.which]; struct afs_vnode *vnode = vp->vnode; int ret; if (inode_state_read_once(&vnode->netfs.inode) & I_NEW) { ret = afs_inode_init_from_status(op, vp, vnode); afs_op_set_error(op, ret); if (ret == 0) afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb); } else { afs_vnode_commit_status(op, vp); } } const struct afs_operation_ops afs_fetch_status_operation = { .issue_afs_rpc = afs_fs_fetch_status, .issue_yfs_rpc = yfs_fs_fetch_status, .success = afs_fetch_status_success, .aborted = afs_check_for_remote_deletion, }; /* * Fetch file status from the volume. */ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool is_new, afs_access_t *_caller_access) { struct afs_operation *op; _enter("%s,{%llx:%llu.%u,S=%lx}", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, vnode->flags); op = afs_alloc_operation(key, vnode->volume); if (IS_ERR(op)) return PTR_ERR(op); afs_op_set_vnode(op, 0, vnode); op->nr_files = 1; op->ops = &afs_fetch_status_operation; afs_begin_vnode_operation(op); afs_wait_for_operation(op); if (_caller_access) *_caller_access = op->file[0].scb.status.caller_access; return afs_put_operation(op); } /* * ilookup() comparator */ int afs_ilookup5_test_by_fid(struct inode *inode, void *opaque) { struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_fid *fid = opaque; return (fid->vnode == vnode->fid.vnode && fid->vnode_hi == vnode->fid.vnode_hi && fid->unique == vnode->fid.unique); } /* * iget5() comparator */ static int afs_iget5_test(struct inode *inode, void *opaque) { struct afs_vnode_param *vp = opaque; //struct afs_vnode *vnode = AFS_FS_I(inode); return afs_ilookup5_test_by_fid(inode, &vp->fid); } /* * iget5() inode initialiser */ static int afs_iget5_set(struct inode *inode, void *opaque) { struct afs_vnode_param *vp = opaque; struct afs_super_info *as = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); vnode->volume = as->volume; vnode->fid = vp->fid; /* YFS supports 96-bit vnode IDs, but Linux only supports * 64-bit inode numbers. */ inode->i_ino = vnode->fid.vnode; inode->i_generation = vnode->fid.unique; return 0; } /* * Get a cache cookie for an inode. */ static void afs_get_inode_cache(struct afs_vnode *vnode) { #ifdef CONFIG_AFS_FSCACHE struct { __be32 vnode_id; __be32 unique; __be32 vnode_id_ext[2]; /* Allow for a 96-bit key */ } __packed key; struct afs_vnode_cache_aux aux; if (vnode->status.type != AFS_FTYPE_FILE && vnode->status.type != AFS_FTYPE_DIR && vnode->status.type != AFS_FTYPE_SYMLINK) { vnode->netfs.cache = NULL; return; } key.vnode_id = htonl(vnode->fid.vnode); key.unique = htonl(vnode->fid.unique); key.vnode_id_ext[0] = htonl(vnode->fid.vnode >> 32); key.vnode_id_ext[1] = htonl(vnode->fid.vnode_hi); afs_set_cache_aux(vnode, &aux); afs_vnode_set_cache(vnode, fscache_acquire_cookie( vnode->volume->cache, vnode->status.type == AFS_FTYPE_FILE ? 0 : FSCACHE_ADV_SINGLE_CHUNK, &key, sizeof(key), &aux, sizeof(aux), i_size_read(&vnode->netfs.inode))); #endif } /* * inode retrieval */ struct inode *afs_iget(struct afs_operation *op, struct afs_vnode_param *vp) { struct afs_vnode_param *dvp = &op->file[0]; struct super_block *sb = dvp->vnode->netfs.inode.i_sb; struct afs_vnode *vnode; struct inode *inode; int ret; _enter(",{%llx:%llu.%u},,", vp->fid.vid, vp->fid.vnode, vp->fid.unique); inode = iget5_locked(sb, vp->fid.vnode, afs_iget5_test, afs_iget5_set, vp); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } vnode = AFS_FS_I(inode); _debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }", inode, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); /* deal with an existing inode */ if (!(inode_state_read_once(inode) & I_NEW)) { _leave(" = %p", inode); return inode; } ret = afs_inode_init_from_status(op, vp, vnode); if (ret < 0) goto bad_inode; afs_get_inode_cache(vnode); /* success */ clear_bit(AFS_VNODE_UNSET, &vnode->flags); unlock_new_inode(inode); _leave(" = %p", inode); return inode; /* failure */ bad_inode: iget_failed(inode); _leave(" = %d [bad]", ret); return ERR_PTR(ret); } static int afs_iget5_set_root(struct inode *inode, void *opaque) { struct afs_super_info *as = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); vnode->volume = as->volume; vnode->fid.vid = as->volume->vid; vnode->fid.vnode = 1; vnode->fid.unique = 1; inode->i_ino = 1; inode->i_generation = 1; return 0; } /* * Set up the root inode for a volume. This is always vnode 1, unique 1 within * the volume. */ struct inode *afs_root_iget(struct super_block *sb, struct key *key) { struct afs_super_info *as = AFS_FS_S(sb); struct afs_operation *op; struct afs_vnode *vnode; struct inode *inode; int ret; _enter(",{%llx},,", as->volume->vid); inode = iget5_locked(sb, 1, NULL, afs_iget5_set_root, NULL); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } _debug("GOT ROOT INODE %p { vl=%llx }", inode, as->volume->vid); BUG_ON(!(inode_state_read_once(inode) & I_NEW)); vnode = AFS_FS_I(inode); vnode->cb_v_check = atomic_read(&as->volume->cb_v_break); op = afs_alloc_operation(key, as->volume); if (IS_ERR(op)) { ret = PTR_ERR(op); goto error; } afs_op_set_vnode(op, 0, vnode); op->nr_files = 1; op->ops = &afs_fetch_status_operation; ret = afs_do_sync_operation(op); if (ret < 0) goto error; afs_get_inode_cache(vnode); clear_bit(AFS_VNODE_UNSET, &vnode->flags); unlock_new_inode(inode); _leave(" = %p", inode); return inode; error: iget_failed(inode); _leave(" = %d [bad]", ret); return ERR_PTR(ret); } /* * read the attributes of an inode */ int afs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct afs_vnode *vnode = AFS_FS_I(inode); struct key *key; int ret, seq; _enter("{ ino=%llu v=%u }", inode->i_ino, inode->i_generation); if (vnode->volume && !(query_flags & AT_STATX_DONT_SYNC) && atomic64_read(&vnode->cb_expires_at) == AFS_NO_CB_PROMISE) { key = afs_request_key(vnode->volume->cell); if (IS_ERR(key)) return PTR_ERR(key); ret = afs_validate(vnode, key); key_put(key); if (ret < 0) return ret; } do { seq = read_seqbegin(&vnode->cb_lock); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) && stat->nlink > 0) stat->nlink -= 1; /* Lie about the size of directories. We maintain a locally * edited copy and may make different allocation decisions on * it, but we need to give userspace the server's size. */ if (S_ISDIR(inode->i_mode)) stat->size = netfs_read_remote_i_size(inode); } while (read_seqretry(&vnode->cb_lock, seq)); return 0; } /* * discard an AFS inode */ int afs_drop_inode(struct inode *inode) { _enter(""); if (test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(inode)->flags)) return inode_just_drop(inode); else return inode_generic_drop(inode); } /* * clear an AFS inode */ void afs_evict_inode(struct inode *inode) { struct afs_vnode_cache_aux aux; struct afs_super_info *sbi = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); _enter("{%llx:%llu.%d}", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); _debug("CLEAR INODE %p", inode); ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); if ((S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && (inode_state_read_once(inode) & I_DIRTY) && !sbi->dyn_root) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .for_sync = true, .range_end = LLONG_MAX, }; inode->i_mapping->a_ops->writepages(inode->i_mapping, &wbc); } flush_delayed_work(&vnode->lock_work); netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); netfs_free_folioq_buffer(vnode->directory); if (vnode->symlink) afs_evict_symlink(vnode); afs_set_cache_aux(vnode, &aux); netfs_clear_inode_writeback(inode, &aux); clear_inode(inode); while (!list_empty(&vnode->wb_keys)) { struct afs_wb_key *wbk = list_entry(vnode->wb_keys.next, struct afs_wb_key, vnode_link); list_del(&wbk->vnode_link); afs_put_wb_key(wbk); } fscache_relinquish_cookie(afs_vnode_cache(vnode), test_bit(AFS_VNODE_DELETED, &vnode->flags)); afs_prune_wb_keys(vnode); afs_put_permits(rcu_access_pointer(vnode->permit_cache)); key_put(vnode->silly_key); vnode->silly_key = NULL; key_put(vnode->lock_key); vnode->lock_key = NULL; _leave(""); } static void afs_setattr_success(struct afs_operation *op) { struct afs_vnode_param *vp = &op->file[0]; struct inode *inode = &vp->vnode->netfs.inode; loff_t old_i_size = i_size_read(inode); op->setattr.old_i_size = old_i_size; afs_vnode_commit_status(op, vp); /* inode->i_size has now been changed. */ if (op->setattr.attr->ia_valid & ATTR_SIZE) { loff_t size = op->setattr.attr->ia_size; if (size > old_i_size) pagecache_isize_extended(inode, old_i_size, size); } } static void afs_setattr_edit_file(struct afs_operation *op) { struct afs_vnode_param *vp = &op->file[0]; struct afs_vnode *vnode = vp->vnode; struct inode *inode = &vnode->netfs.inode; if (op->setattr.attr->ia_valid & ATTR_SIZE) { loff_t size = op->setattr.attr->ia_size; loff_t old = op->setattr.old_i_size; /* Note: inode->i_size was updated by afs_apply_status() inside * the I/O and callback locks. */ if (size != old) { truncate_pagecache(inode, size); netfs_resize_file(&vnode->netfs, size, true); fscache_resize_cookie(afs_vnode_cache(vnode), size); } } } static const struct afs_operation_ops afs_setattr_operation = { .issue_afs_rpc = afs_fs_setattr, .issue_yfs_rpc = yfs_fs_setattr, .success = afs_setattr_success, .edit_dir = afs_setattr_edit_file, }; /* * set the attributes of an inode */ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { const unsigned int supported = ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | ATTR_TOUCH; struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); struct inode *inode = &vnode->netfs.inode; loff_t i_size; int ret; _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, attr->ia_valid); if (!(attr->ia_valid & supported)) { _leave(" = 0 [unsupported]"); return 0; } i_size = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { if (!S_ISREG(inode->i_mode)) return -EISDIR; ret = inode_newsize_ok(inode, attr->ia_size); if (ret) return ret; if (attr->ia_size == i_size) attr->ia_valid &= ~ATTR_SIZE; } fscache_use_cookie(afs_vnode_cache(vnode), true); /* Prevent any new writebacks from starting whilst we do this. */ down_write(&vnode->validate_lock); if ((attr->ia_valid & ATTR_SIZE) && S_ISREG(inode->i_mode)) { loff_t size = attr->ia_size; /* Wait for any outstanding writes to the server to complete */ loff_t from = min(size, i_size); loff_t to = max(size, i_size); ret = filemap_fdatawait_range(inode->i_mapping, from, to); if (ret < 0) goto out_unlock; /* Don't talk to the server if we're just shortening in-memory * writes that haven't gone to the server yet. */ if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) && attr->ia_size < i_size && attr->ia_size > netfs_read_remote_i_size(inode)) { truncate_setsize(inode, attr->ia_size); netfs_resize_file(&vnode->netfs, size, false); fscache_resize_cookie(afs_vnode_cache(vnode), attr->ia_size); ret = 0; goto out_unlock; } } op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ? afs_file_key(attr->ia_file) : NULL), vnode->volume); if (IS_ERR(op)) { ret = PTR_ERR(op); goto out_unlock; } afs_op_set_vnode(op, 0, vnode); op->setattr.attr = attr; if (attr->ia_valid & ATTR_SIZE) { op->file[0].dv_delta = 1; op->file[0].set_size = true; } op->ctime = attr->ia_ctime; op->file[0].update_ctime = 1; op->file[0].modification = true; op->ops = &afs_setattr_operation; ret = afs_do_sync_operation(op); out_unlock: up_write(&vnode->validate_lock); fscache_unuse_cookie(afs_vnode_cache(vnode), NULL, NULL); _leave(" = %d", ret); return ret; } |
| 4 1 3 4 4 4 4 2 1 1 1 4 1 1 1 1 1 1 12 4 1 3 4 3 3 4 1 1 1 6 4 6 6 2 1 3 1 2 7 1 1 1 1 3 158 157 156 47 158 158 160 1 1 5 153 159 1 153 3 156 152 6 158 159 1 154 5 62 105 | 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 | /* * Created: Fri Jan 8 09:01:26 1999 by faith@valinux.com * * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas. * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California. * All Rights Reserved. * * Author Rickard E. (Rik) Faith <faith@valinux.com> * Author Gareth Hughes <gareth@valinux.com> * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. */ #include <linux/export.h> #include <linux/nospec.h> #include <linux/pci.h> #include <linux/uaccess.h> #include <drm/drm_auth.h> #include <drm/drm_crtc.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> #include <drm/drm_ioctl.h> #include <drm/drm_print.h> #include "drm_crtc_internal.h" #include "drm_internal.h" /** * DOC: getunique and setversion story * * BEWARE THE DRAGONS! MIND THE TRAPDOORS! * * In an attempt to warn anyone else who's trying to figure out what's going * on here, I'll try to summarize the story. First things first, let's clear up * the names, because the kernel internals, libdrm and the ioctls are all named * differently: * * - GET_UNIQUE ioctl, implemented by drm_getunique is wrapped up in libdrm * through the drmGetBusid function. * - The libdrm drmSetBusid function is backed by the SET_UNIQUE ioctl. All * that code is nerved in the kernel with drm_invalid_op(). * - The internal set_busid kernel functions and driver callbacks are * exclusively use by the SET_VERSION ioctl, because only drm 1.0 (which is * nerved) allowed userspace to set the busid through the above ioctl. * - Other ioctls and functions involved are named consistently. * * For anyone wondering what's the difference between drm 1.1 and 1.4: Correctly * handling pci domains in the busid on ppc. Doing this correctly was only * implemented in libdrm in 2010, hence can't be nerved yet. No one knows what's * special with drm 1.2 and 1.3. * * Now the actual horror story of how device lookup in drm works. At large, * there's 2 different ways, either by busid, or by device driver name. * * Opening by busid is fairly simple: * * 1. First call SET_VERSION to make sure pci domains are handled properly. As a * side-effect this fills out the unique name in the master structure. * 2. Call GET_UNIQUE to read out the unique name from the master structure, * which matches the busid thanks to step 1. If it doesn't, proceed to try * the next device node. * * Opening by name is slightly different: * * 1. Directly call VERSION to get the version and to match against the driver * name returned by that ioctl. Note that SET_VERSION is not called, which * means the unique name for the master node just opening is _not_ filled * out. This despite that with current drm device nodes are always bound to * one device, and can't be runtime assigned like with drm 1.0. * 2. Match driver name. If it mismatches, proceed to the next device node. * 3. Call GET_UNIQUE, and check whether the unique name has length zero (by * checking that the first byte in the string is 0). If that's not the case * libdrm skips and proceeds to the next device node. Probably this is just * copypasta from drm 1.0 times where a set unique name meant that the driver * was in use already, but that's just conjecture. * * Long story short: To keep the open by name logic working, GET_UNIQUE must * _not_ return a unique string when SET_VERSION hasn't been called yet, * otherwise libdrm breaks. Even when that unique string can't ever change, and * is totally irrelevant for actually opening the device because runtime * assignable device instances were only support in drm 1.0, which is long dead. * But the libdrm code in drmOpenByName somehow survived, hence this can't be * broken. */ /* * Get the bus id. * * \param inode device inode. * \param file_priv DRM file private. * \param cmd command. * \param arg user argument, pointing to a drm_unique structure. * \return zero on success or a negative number on failure. * * Copies the bus id from drm_device::unique into user space. */ int drm_getunique(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_unique *u = data; struct drm_master *master; mutex_lock(&dev->master_mutex); master = file_priv->master; if (u->unique_len >= master->unique_len) { if (copy_to_user(u->unique, master->unique, master->unique_len)) { mutex_unlock(&dev->master_mutex); return -EFAULT; } } u->unique_len = master->unique_len; mutex_unlock(&dev->master_mutex); return 0; } static void drm_unset_busid(struct drm_device *dev, struct drm_master *master) { kfree(master->unique); master->unique = NULL; master->unique_len = 0; } static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv) { struct drm_master *master = file_priv->master; int ret; if (master->unique != NULL) drm_unset_busid(dev, master); if (dev->dev && dev_is_pci(dev->dev)) { ret = drm_pci_set_busid(dev, master); if (ret) { drm_unset_busid(dev, master); return ret; } } else { WARN_ON(!dev->unique); master->unique = kstrdup(dev->unique, GFP_KERNEL); if (master->unique) master->unique_len = strlen(dev->unique); } return 0; } /* * Get client information. * * \param inode device inode. * \param file_priv DRM file private. * \param cmd command. * \param arg user argument, pointing to a drm_client structure. * * \return zero on success or a negative number on failure. * * Searches for the client with the specified index and copies its information * into userspace */ int drm_getclient(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_client *client = data; /* * Hollowed-out getclient ioctl to keep some dead old drm tests/tools * not breaking completely. Userspace tools stop enumerating one they * get -EINVAL, hence this is the return value we need to hand back for * no clients tracked. * * Unfortunately some clients (*cough* libva *cough*) use this in a fun * attempt to figure out whether they're authenticated or not. Since * that's the only thing they care about, give it to the directly * instead of walking one giant list. */ if (client->idx == 0) { client->auth = file_priv->authenticated; client->pid = task_pid_vnr(current); client->uid = overflowuid; client->magic = 0; client->iocs = 0; return 0; } else { return -EINVAL; } } /* * Get statistics information. * * \param inode device inode. * \param file_priv DRM file private. * \param cmd command. * \param arg user argument, pointing to a drm_stats structure. * * \return zero on success or a negative number on failure. */ static int drm_getstats(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_stats *stats = data; /* Clear stats to prevent userspace from eating its stack garbage. */ memset(stats, 0, sizeof(*stats)); return 0; } /* * Get device/driver capabilities */ static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_get_cap *req = data; struct drm_crtc *crtc; req->value = 0; /* Only some caps make sense with UMS/render-only drivers. */ switch (req->capability) { case DRM_CAP_TIMESTAMP_MONOTONIC: req->value = 1; return 0; case DRM_CAP_PRIME: req->value = DRM_PRIME_CAP_IMPORT | DRM_PRIME_CAP_EXPORT; return 0; case DRM_CAP_SYNCOBJ: req->value = drm_core_check_feature(dev, DRIVER_SYNCOBJ); return 0; case DRM_CAP_SYNCOBJ_TIMELINE: req->value = drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE); return 0; } /* Other caps only work with KMS drivers */ if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; switch (req->capability) { case DRM_CAP_DUMB_BUFFER: if (dev->driver->dumb_create) req->value = 1; break; case DRM_CAP_VBLANK_HIGH_CRTC: req->value = 1; break; case DRM_CAP_DUMB_PREFERRED_DEPTH: req->value = dev->mode_config.preferred_depth; break; case DRM_CAP_DUMB_PREFER_SHADOW: req->value = dev->mode_config.prefer_shadow; break; case DRM_CAP_ASYNC_PAGE_FLIP: req->value = dev->mode_config.async_page_flip; break; case DRM_CAP_PAGE_FLIP_TARGET: req->value = 1; drm_for_each_crtc(crtc, dev) { if (!crtc->funcs->page_flip_target) req->value = 0; } break; case DRM_CAP_CURSOR_WIDTH: if (dev->mode_config.cursor_width) req->value = dev->mode_config.cursor_width; else req->value = 64; break; case DRM_CAP_CURSOR_HEIGHT: if (dev->mode_config.cursor_height) req->value = dev->mode_config.cursor_height; else req->value = 64; break; case DRM_CAP_ADDFB2_MODIFIERS: req->value = !dev->mode_config.fb_modifiers_not_supported; break; case DRM_CAP_CRTC_IN_VBLANK_EVENT: req->value = 1; break; case DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP: req->value = drm_core_check_feature(dev, DRIVER_ATOMIC) && dev->mode_config.async_page_flip; break; default: return -EINVAL; } return 0; } /* * Set device/driver capabilities */ static int drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_set_client_cap *req = data; /* No render-only settable capabilities for now */ /* Below caps that only works with KMS drivers */ if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; switch (req->capability) { case DRM_CLIENT_CAP_STEREO_3D: if (req->value > 1) return -EINVAL; file_priv->stereo_allowed = req->value; break; case DRM_CLIENT_CAP_UNIVERSAL_PLANES: if (req->value > 1) return -EINVAL; file_priv->universal_planes = req->value; break; case DRM_CLIENT_CAP_ATOMIC: if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) return -EOPNOTSUPP; /* The modesetting DDX has a totally broken idea of atomic. */ if (current->comm[0] == 'X' && req->value == 1) { pr_info("broken atomic modeset userspace detected, disabling atomic\n"); return -EOPNOTSUPP; } if (req->value > 2) return -EINVAL; file_priv->atomic = req->value; file_priv->universal_planes = req->value; /* * No atomic user-space blows up on aspect ratio mode bits. */ file_priv->aspect_ratio_allowed = req->value; break; case DRM_CLIENT_CAP_ASPECT_RATIO: if (req->value > 1) return -EINVAL; file_priv->aspect_ratio_allowed = req->value; break; case DRM_CLIENT_CAP_WRITEBACK_CONNECTORS: if (!file_priv->atomic) return -EINVAL; if (req->value > 1) return -EINVAL; file_priv->writeback_connectors = req->value; break; case DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT: if (!drm_core_check_feature(dev, DRIVER_CURSOR_HOTSPOT)) return -EOPNOTSUPP; if (!file_priv->atomic) return -EINVAL; if (req->value > 1) return -EINVAL; file_priv->supports_virtualized_cursor_plane = req->value; break; case DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE: { struct drm_plane *plane; bool has_plane_with_color_pipeline = false; if (!file_priv->atomic) return -EINVAL; if (req->value > 1) return -EINVAL; drm_for_each_plane(plane, dev) { if (plane->color_pipeline_property) { has_plane_with_color_pipeline = true; break; } } if (!has_plane_with_color_pipeline) return -EOPNOTSUPP; file_priv->plane_color_pipeline = req->value; break; } default: return -EINVAL; } return 0; } /* * Setversion ioctl. * * \param inode device inode. * \param file_priv DRM file private. * \param cmd command. * \param arg user argument, pointing to a drm_lock structure. * \return zero on success or negative number on failure. * * Sets the requested interface version */ static int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_set_version *sv = data; int if_version, retcode = 0; mutex_lock(&dev->master_mutex); if (sv->drm_di_major != -1) { if (sv->drm_di_major != DRM_IF_MAJOR || sv->drm_di_minor < 0 || sv->drm_di_minor > DRM_IF_MINOR) { retcode = -EINVAL; goto done; } if_version = DRM_IF_VERSION(sv->drm_di_major, sv->drm_di_minor); dev->if_version = max(if_version, dev->if_version); if (sv->drm_di_minor >= 1) { /* * Version 1.1 includes tying of DRM to specific device * Version 1.4 has proper PCI domain support */ retcode = drm_set_busid(dev, file_priv); if (retcode) goto done; } } if (sv->drm_dd_major != -1) { if (sv->drm_dd_major != dev->driver->major || sv->drm_dd_minor < 0 || sv->drm_dd_minor > dev->driver->minor) { retcode = -EINVAL; goto done; } } done: sv->drm_di_major = DRM_IF_MAJOR; sv->drm_di_minor = DRM_IF_MINOR; sv->drm_dd_major = dev->driver->major; sv->drm_dd_minor = dev->driver->minor; mutex_unlock(&dev->master_mutex); return retcode; } /** * drm_noop - DRM no-op ioctl implementation * @dev: DRM device for the ioctl * @data: data pointer for the ioctl * @file_priv: DRM file for the ioctl call * * This no-op implementation for drm ioctls is useful for deprecated * functionality where we can't return a failure code because existing userspace * checks the result of the ioctl, but doesn't care about the action. * * Always returns successfully with 0. */ int drm_noop(struct drm_device *dev, void *data, struct drm_file *file_priv) { drm_dbg_core(dev, "\n"); return 0; } EXPORT_SYMBOL(drm_noop); /** * drm_invalid_op - DRM invalid ioctl implementation * @dev: DRM device for the ioctl * @data: data pointer for the ioctl * @file_priv: DRM file for the ioctl call * * This no-op implementation for drm ioctls is useful for deprecated * functionality where we really don't want to allow userspace to call the ioctl * any more. This is the case for old ums interfaces for drivers that * transitioned to kms gradually and so kept the old legacy tables around. This * only applies to radeon and i915 kms drivers, other drivers shouldn't need to * use this function. * * Always fails with a return value of -EINVAL. */ int drm_invalid_op(struct drm_device *dev, void *data, struct drm_file *file_priv) { return -EINVAL; } EXPORT_SYMBOL(drm_invalid_op); /* * Copy and IOCTL return string to user space */ static int drm_copy_field(char __user *buf, size_t *buf_len, const char *value) { size_t len; /* don't attempt to copy a NULL pointer */ if (WARN_ONCE(!value, "BUG: the value to copy was not set!")) { *buf_len = 0; return 0; } /* don't overflow userbuf */ len = strlen(value); if (len > *buf_len) len = *buf_len; /* let userspace know exact length of driver value (which could be * larger than the userspace-supplied buffer) */ *buf_len = strlen(value); /* finally, try filling in the userbuf */ if (len && buf) if (copy_to_user(buf, value, len)) return -EFAULT; return 0; } /* * Get version information * * \param inode device inode. * \param filp file pointer. * \param cmd command. * \param arg user argument, pointing to a drm_version structure. * \return zero on success or negative number on failure. * * Fills in the version information in \p arg. */ int drm_version(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_version *version = data; int err; version->version_major = dev->driver->major; version->version_minor = dev->driver->minor; version->version_patchlevel = dev->driver->patchlevel; err = drm_copy_field(version->name, &version->name_len, dev->driver->name); /* Driver date is deprecated. Userspace expects a non-empty string. */ if (!err) err = drm_copy_field(version->date, &version->date_len, "0"); if (!err) err = drm_copy_field(version->desc, &version->desc_len, dev->driver->desc); return err; } /* * Check if the passed string contains control char or spaces or * anything that would mess up a formatted output. */ static int drm_validate_value_string(const char *value, size_t len) { int i; for (i = 0; i < len; i++) { if (!isascii(value[i]) || !isgraph(value[i])) return -EINVAL; } return 0; } static int drm_set_client_name(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_set_client_name *name = data; size_t len = name->name_len; void __user *user_ptr; char *new_name; if (len > DRM_CLIENT_NAME_MAX_LEN) { return -EINVAL; } else if (len) { user_ptr = u64_to_user_ptr(name->name); new_name = memdup_user_nul(user_ptr, len); if (IS_ERR(new_name)) return PTR_ERR(new_name); if (strlen(new_name) != len || drm_validate_value_string(new_name, len) < 0) { kfree(new_name); return -EINVAL; } } else { new_name = NULL; } mutex_lock(&file_priv->client_name_lock); kfree(file_priv->client_name); file_priv->client_name = new_name; mutex_unlock(&file_priv->client_name_lock); return 0; } static int drm_ioctl_permit(u32 flags, struct drm_file *file_priv) { /* ROOT_ONLY is only for CAP_SYS_ADMIN */ if (unlikely((flags & DRM_ROOT_ONLY) && !capable(CAP_SYS_ADMIN))) return -EACCES; /* AUTH is only for authenticated or render client */ if (unlikely((flags & DRM_AUTH) && !drm_is_render_client(file_priv) && !file_priv->authenticated)) return -EACCES; /* MASTER is only for master or control clients */ if (unlikely((flags & DRM_MASTER) && !drm_is_current_master(file_priv))) return -EACCES; /* Render clients must be explicitly allowed */ if (unlikely(!(flags & DRM_RENDER_ALLOW) && drm_is_render_client(file_priv))) return -EACCES; return 0; } #define DRM_IOCTL_DEF(ioctl, _func, _flags) \ [DRM_IOCTL_NR(ioctl)] = { \ .cmd = ioctl, \ .func = _func, \ .flags = _flags, \ .name = #ioctl \ } /* Ioctl table */ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0), DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0), DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, 0), DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, 0), DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0), DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_invalid_op, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF(DRM_IOCTL_BLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_ADD_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF(DRM_IOCTL_RM_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH), DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH), DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH), /* see drm_gem.c:drm_gem_change_handle_ioctl for why this is invalid */ DRM_IOCTL_DEF(DRM_IOCTL_GEM_CHANGE_HANDLE, drm_invalid_op, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, 0), DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_NAME, drm_set_client_name, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETGAMMA, drm_mode_gamma_get_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETGAMMA, drm_mode_gamma_set_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_connector_property_set_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB2, drm_mode_getfb2_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CLOSEFB, drm_mode_closefb_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATOMIC, drm_mode_atomic_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATEPROPBLOB, drm_mode_createblob_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROYPROPBLOB, drm_mode_destroyblob_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_CREATE, drm_syncobj_create_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_DESTROY, drm_syncobj_destroy_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD, drm_syncobj_handle_to_fd_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE, drm_syncobj_fd_to_handle_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TRANSFER, drm_syncobj_transfer_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_WAIT, drm_syncobj_wait_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, drm_syncobj_timeline_wait_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_EVENTFD, drm_syncobj_eventfd_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_RESET, drm_syncobj_reset_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_SIGNAL, drm_syncobj_signal_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL, drm_syncobj_timeline_signal_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, 0), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_LIST_LESSEES, drm_mode_list_lessees_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_GET_LEASE, drm_mode_get_lease_ioctl, DRM_MASTER), DRM_IOCTL_DEF(DRM_IOCTL_MODE_REVOKE_LEASE, drm_mode_revoke_lease_ioctl, DRM_MASTER), }; #define DRM_CORE_IOCTL_COUNT ARRAY_SIZE(drm_ioctls) /** * DOC: driver specific ioctls * * First things first, driver private IOCTLs should only be needed for drivers * supporting rendering. Kernel modesetting is all standardized, and extended * through properties. There are a few exceptions in some existing drivers, * which define IOCTL for use by the display DRM master, but they all predate * properties. * * Now if you do have a render driver you always have to support it through * driver private properties. There's a few steps needed to wire all the things * up. * * First you need to define the structure for your IOCTL in your driver private * UAPI header in ``include/uapi/drm/my_driver_drm.h``:: * * struct my_driver_operation { * u32 some_thing; * u32 another_thing; * }; * * Please make sure that you follow all the best practices from * ``Documentation/process/botching-up-ioctls.rst``. Note that drm_ioctl() * automatically zero-extends structures, hence make sure you can add more stuff * at the end, i.e. don't put a variable sized array there. * * Then you need to define your IOCTL number, using one of DRM_IO(), DRM_IOR(), * DRM_IOW() or DRM_IOWR(). It must start with the DRM_IOCTL\_ prefix:: * * ##define DRM_IOCTL_MY_DRIVER_OPERATION \ * DRM_IOW(DRM_COMMAND_BASE, struct my_driver_operation) * * DRM driver private IOCTL must be in the range from DRM_COMMAND_BASE to * DRM_COMMAND_END. Finally you need an array of &struct drm_ioctl_desc to wire * up the handlers and set the access rights:: * * static const struct drm_ioctl_desc my_driver_ioctls[] = { * DRM_IOCTL_DEF_DRV(MY_DRIVER_OPERATION, my_driver_operation, * DRM_AUTH|DRM_RENDER_ALLOW), * }; * * And then assign this to the &drm_driver.ioctls field in your driver * structure. * * See the separate chapter on :ref:`file operations<drm_driver_fops>` for how * the driver-specific IOCTLs are wired up. */ long drm_ioctl_kernel(struct file *file, drm_ioctl_t *func, void *kdata, u32 flags) { struct drm_file *file_priv = file->private_data; struct drm_device *dev = file_priv->minor->dev; int ret; /* Update drm_file owner if fd was passed along. */ drm_file_update_pid(file_priv); if (drm_dev_is_unplugged(dev)) return -ENODEV; ret = drm_ioctl_permit(flags, file_priv); if (unlikely(ret)) return ret; return func(dev, kdata, file_priv); } EXPORT_SYMBOL(drm_ioctl_kernel); /** * drm_ioctl - ioctl callback implementation for DRM drivers * @filp: file this ioctl is called on * @cmd: ioctl cmd number * @arg: user argument * * Looks up the ioctl function in the DRM core and the driver dispatch table, * stored in &drm_driver.ioctls. It checks for necessary permission by calling * drm_ioctl_permit(), and dispatches to the respective function. * * Returns: * Zero on success, negative error code on failure. */ long drm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct drm_file *file_priv = filp->private_data; struct drm_device *dev; const struct drm_ioctl_desc *ioctl = NULL; drm_ioctl_t *func; unsigned int nr = DRM_IOCTL_NR(cmd); int retcode = -EINVAL; char stack_kdata[128]; char *kdata = NULL; unsigned int in_size, out_size, drv_size, ksize; bool is_driver_ioctl; dev = file_priv->minor->dev; if (drm_dev_is_unplugged(dev)) return -ENODEV; if (DRM_IOCTL_TYPE(cmd) != DRM_IOCTL_BASE) return -ENOTTY; is_driver_ioctl = nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END; if (is_driver_ioctl) { /* driver ioctl */ unsigned int index = nr - DRM_COMMAND_BASE; if (index >= dev->driver->num_ioctls) goto err_i1; index = array_index_nospec(index, dev->driver->num_ioctls); ioctl = &dev->driver->ioctls[index]; } else { /* core ioctl */ if (nr >= DRM_CORE_IOCTL_COUNT) goto err_i1; nr = array_index_nospec(nr, DRM_CORE_IOCTL_COUNT); ioctl = &drm_ioctls[nr]; } drv_size = _IOC_SIZE(ioctl->cmd); out_size = in_size = _IOC_SIZE(cmd); if ((cmd & ioctl->cmd & IOC_IN) == 0) in_size = 0; if ((cmd & ioctl->cmd & IOC_OUT) == 0) out_size = 0; ksize = max(max(in_size, out_size), drv_size); drm_dbg_core(dev, "comm=\"%s\" pid=%d, dev=0x%lx, auth=%d, %s\n", current->comm, task_pid_nr(current), (long)old_encode_dev(file_priv->minor->kdev->devt), file_priv->authenticated, ioctl->name); /* Do not trust userspace, use our own definition */ func = ioctl->func; if (unlikely(!func)) { drm_dbg_core(dev, "no function\n"); retcode = -EINVAL; goto err_i1; } if (ksize <= sizeof(stack_kdata)) { kdata = stack_kdata; } else { kdata = kmalloc(ksize, GFP_KERNEL); if (!kdata) { retcode = -ENOMEM; goto err_i1; } } if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { retcode = -EFAULT; goto err_i1; } if (ksize > in_size) memset(kdata + in_size, 0, ksize - in_size); retcode = drm_ioctl_kernel(filp, func, kdata, ioctl->flags); if (copy_to_user((void __user *)arg, kdata, out_size) != 0) retcode = -EFAULT; err_i1: if (!ioctl) drm_dbg_core(dev, "invalid ioctl: comm=\"%s\", pid=%d, dev=0x%lx, auth=%d, cmd=0x%02x, nr=0x%02x\n", current->comm, task_pid_nr(current), (long)old_encode_dev(file_priv->minor->kdev->devt), file_priv->authenticated, cmd, nr); if (kdata != stack_kdata) kfree(kdata); if (retcode) drm_dbg_core(dev, "comm=\"%s\", pid=%d, ret=%d\n", current->comm, task_pid_nr(current), retcode); return retcode; } EXPORT_SYMBOL(drm_ioctl); /** * drm_ioctl_flags - Check for core ioctl and return ioctl permission flags * @nr: ioctl number * @flags: where to return the ioctl permission flags * * This ioctl is only used by the vmwgfx driver to augment the access checks * done by the drm core and insofar a pretty decent layering violation. This * shouldn't be used by any drivers. * * Returns: * True if the @nr corresponds to a DRM core ioctl number, false otherwise. */ bool drm_ioctl_flags(unsigned int nr, unsigned int *flags) { if (nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END) return false; if (nr >= DRM_CORE_IOCTL_COUNT) return false; nr = array_index_nospec(nr, DRM_CORE_IOCTL_COUNT); *flags = drm_ioctls[nr].flags; return true; } EXPORT_SYMBOL(drm_ioctl_flags); |
| 153 143 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> */ #include <linux/xattr.h> #include <linux/evm.h> int posix_xattr_acl(const char *xattr) { int xattr_len = strlen(xattr); if ((strlen(XATTR_NAME_POSIX_ACL_ACCESS) == xattr_len) && (strncmp(XATTR_NAME_POSIX_ACL_ACCESS, xattr, xattr_len) == 0)) return 1; if ((strlen(XATTR_NAME_POSIX_ACL_DEFAULT) == xattr_len) && (strncmp(XATTR_NAME_POSIX_ACL_DEFAULT, xattr, xattr_len) == 0)) return 1; return 0; } |
| 30 27 8 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * VMware vSockets Driver * * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. */ #ifndef __AF_VSOCK_H__ #define __AF_VSOCK_H__ #include <linux/kernel.h> #include <linux/workqueue.h> #include <net/netns/vsock.h> #include <net/sock.h> #include <uapi/linux/vm_sockets.h> #include "vsock_addr.h" #define LAST_RESERVED_PORT 1023 #define VSOCK_HASH_SIZE 251 extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; extern spinlock_t vsock_table_lock; #define vsock_sk(__sk) ((struct vsock_sock *)__sk) #define sk_vsock(__vsk) (&(__vsk)->sk) struct vsock_sock { /* sk must be the first member. */ struct sock sk; const struct vsock_transport *transport; struct sockaddr_vm local_addr; struct sockaddr_vm remote_addr; /* Links for the global tables of bound and connected sockets. */ struct list_head bound_table; struct list_head connected_table; /* Accessed without the socket lock held. This means it can never be * modified outsided of socket create or destruct. */ bool trusted; bool cached_peer_allow_dgram; /* Dgram communication allowed to * cached peer? */ u32 cached_peer; /* Context ID of last dgram destination check. */ const struct cred *owner; /* Rest are SOCK_STREAM only. */ long connect_timeout; /* Listening socket that this came from. */ struct sock *listener; /* Used for pending list and accept queue during connection handshake. * The listening socket is the head for both lists. Sockets created * for connection requests are placed in the pending list until they * are connected, at which point they are put in the accept queue list * so they can be accepted in accept(). */ struct list_head pending_links; struct list_head accept_queue; struct delayed_work connect_work; struct delayed_work pending_work; struct delayed_work close_work; bool close_work_scheduled; u32 peer_shutdown; bool sent_request; bool ignore_connecting_rst; /* Protected by lock_sock(sk) */ u64 buffer_size; u64 buffer_min_size; u64 buffer_max_size; /* Private to transport. */ void *trans; }; s64 vsock_connectible_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); struct sock *vsock_create_connected(struct sock *parent); void vsock_data_ready(struct sock *sk); /**** TRANSPORT ****/ struct vsock_transport_recv_notify_data { u64 data1; /* Transport-defined. */ u64 data2; /* Transport-defined. */ bool notify_on_block; }; struct vsock_transport_send_notify_data { u64 data1; /* Transport-defined. */ u64 data2; /* Transport-defined. */ }; /* Transport features flags */ /* Transport provides host->guest communication */ #define VSOCK_TRANSPORT_F_H2G 0x00000001 /* Transport provides guest->host communication */ #define VSOCK_TRANSPORT_F_G2H 0x00000002 /* Transport provides DGRAM communication */ #define VSOCK_TRANSPORT_F_DGRAM 0x00000004 /* Transport provides local (loopback) communication */ #define VSOCK_TRANSPORT_F_LOCAL 0x00000008 struct vsock_transport { struct module *module; /* Initialize/tear-down socket. */ int (*init)(struct vsock_sock *, struct vsock_sock *); void (*destruct)(struct vsock_sock *); void (*release)(struct vsock_sock *); /* Cancel all pending packets sent on vsock. */ int (*cancel_pkt)(struct vsock_sock *vsk); /* Connections. */ int (*connect)(struct vsock_sock *); /* DGRAM. */ int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, struct msghdr *, size_t len); bool (*dgram_allow)(struct vsock_sock *vsk, u32 cid, u32 port); /* STREAM. */ /* TODO: stream_bind() */ ssize_t (*stream_dequeue)(struct vsock_sock *, struct msghdr *, size_t len, int flags); ssize_t (*stream_enqueue)(struct vsock_sock *, struct msghdr *, size_t len); s64 (*stream_has_data)(struct vsock_sock *); s64 (*stream_has_space)(struct vsock_sock *); u64 (*stream_rcvhiwat)(struct vsock_sock *); bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(struct vsock_sock *vsk, u32 cid, u32 port); /* SEQ_PACKET. */ ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, int flags); int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len); bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid); u32 (*seqpacket_has_data)(struct vsock_sock *vsk); /* Notification. */ int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); int (*notify_recv_init)(struct vsock_sock *, size_t, struct vsock_transport_recv_notify_data *); int (*notify_recv_pre_block)(struct vsock_sock *, size_t, struct vsock_transport_recv_notify_data *); int (*notify_recv_pre_dequeue)(struct vsock_sock *, size_t, struct vsock_transport_recv_notify_data *); int (*notify_recv_post_dequeue)(struct vsock_sock *, size_t, ssize_t, bool, struct vsock_transport_recv_notify_data *); int (*notify_send_init)(struct vsock_sock *, struct vsock_transport_send_notify_data *); int (*notify_send_pre_block)(struct vsock_sock *, struct vsock_transport_send_notify_data *); int (*notify_send_pre_enqueue)(struct vsock_sock *, struct vsock_transport_send_notify_data *); int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, struct vsock_transport_send_notify_data *); /* sk_lock held by the caller */ void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); /* SIOCOUTQ ioctl */ ssize_t (*unsent_bytes)(struct vsock_sock *vsk); /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); /* Addressing. */ u32 (*get_local_cid)(void); /* Check if this transport serves a specific remote CID. * For H2G transports: return true if the CID belongs to a registered * guest. If not implemented, all CIDs > VMADDR_CID_HOST go to H2G. * For G2H transports: return true if the transport can reach arbitrary * CIDs via the hypervisor (i.e. supports the fallback overlay). VMCI * does not implement this as it only serves CIDs 0 and 2. */ bool (*has_remote_cid)(struct vsock_sock *vsk, u32 remote_cid); /* Read a single skb */ int (*read_skb)(struct vsock_sock *, skb_read_actor_t); /* Zero-copy. */ bool (*msgzerocopy_allow)(void); }; /**** CORE ****/ int vsock_core_register(const struct vsock_transport *t, int features); void vsock_core_unregister(const struct vsock_transport *t); /* The transport may downcast this to access transport-specific functions */ const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk); /**** UTILS ****/ /* vsock_table_lock must be held */ static inline bool __vsock_in_bound_table(struct vsock_sock *vsk) { return !list_empty(&vsk->bound_table); } /* vsock_table_lock must be held */ static inline bool __vsock_in_connected_table(struct vsock_sock *vsk) { return !list_empty(&vsk->connected_table); } void vsock_add_pending(struct sock *listener, struct sock *pending); void vsock_remove_pending(struct sock *listener, struct sock *pending); void vsock_enqueue_accept(struct sock *listener, struct sock *connected); void vsock_pending_to_accept(struct sock *listener, struct sock *pending); void vsock_insert_connected(struct vsock_sock *vsk); void vsock_remove_bound(struct vsock_sock *vsk); void vsock_remove_connected(struct vsock_sock *vsk); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct net *net); struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, struct sockaddr_vm *dst, struct net *net); bool vsock_check_source(const struct vsock_sock *vsk, const struct vsock_transport *transport, const struct sockaddr_vm *src); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk); bool vsock_find_cid(unsigned int cid); void vsock_linger(struct sock *sk); /**** TAP ****/ struct vsock_tap { struct net_device *dev; struct module *module; struct list_head list; }; int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); extern struct proto vsock_proto; #ifdef CONFIG_BPF_SYSCALL int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void __init vsock_bpf_build_proto(void); #else static inline void __init vsock_bpf_build_proto(void) {} #endif static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t) { return t->msgzerocopy_allow && t->msgzerocopy_allow(); } static inline enum vsock_net_mode vsock_net_mode(struct net *net) { if (!net) return VSOCK_NET_MODE_GLOBAL; return READ_ONCE(net->vsock.mode); } static inline bool vsock_net_mode_global(struct vsock_sock *vsk) { return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL; } static inline bool vsock_net_set_child_mode(struct net *net, enum vsock_net_mode mode) { int new_locked = mode + 1; int old_locked = 0; /* unlocked */ if (try_cmpxchg(&net->vsock.child_ns_mode_locked, &old_locked, new_locked)) { WRITE_ONCE(net->vsock.child_ns_mode, mode); return true; } return old_locked == new_locked; } static inline enum vsock_net_mode vsock_net_child_mode(struct net *net) { return READ_ONCE(net->vsock.child_ns_mode); } /* Return true if two namespaces pass the mode rules. Otherwise, return false. * * A NULL namespace is treated as VSOCK_NET_MODE_GLOBAL. * * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c. */ static inline bool vsock_net_check_mode(struct net *ns0, struct net *ns1) { enum vsock_net_mode mode0, mode1; /* Any vsocks within the same network namespace are always reachable, * regardless of the mode. */ if (net_eq(ns0, ns1)) return true; mode0 = vsock_net_mode(ns0); mode1 = vsock_net_mode(ns1); /* Different namespaces are only reachable if they are both * global mode. */ return mode0 == VSOCK_NET_MODE_GLOBAL && mode0 == mode1; } #endif /* __AF_VSOCK_H__ */ |
| 1 1 2 4 4 9 9 9 3 8 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 4 4 4 4 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory_hotplug.c * * Copyright (C) */ #include <linux/stddef.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/swap.h> #include <linux/interrupt.h> #include <linux/pagemap.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/writeback.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/memory.h> #include <linux/memremap.h> #include <linux/memory_hotplug.h> #include <linux/vmalloc.h> #include <linux/ioport.h> #include <linux/delay.h> #include <linux/migrate.h> #include <linux/page-isolation.h> #include <linux/pfn.h> #include <linux/suspend.h> #include <linux/mm_inline.h> #include <linux/firmware-map.h> #include <linux/stop_machine.h> #include <linux/hugetlb.h> #include <linux/memblock.h> #include <linux/compaction.h> #include <linux/rmap.h> #include <linux/module.h> #include <linux/node.h> #include <asm/tlbflush.h> #include "internal.h" #include "mm_init.h" #include "page_alloc.h" #include "shuffle.h" enum { MEMMAP_ON_MEMORY_DISABLE = 0, MEMMAP_ON_MEMORY_ENABLE, MEMMAP_ON_MEMORY_FORCE, }; static int memmap_mode __read_mostly = MEMMAP_ON_MEMORY_DISABLE; static inline unsigned long memory_block_memmap_size(void) { return PHYS_PFN(memory_block_size_bytes()) * sizeof(struct page); } static inline unsigned long memory_block_memmap_on_memory_pages(void) { unsigned long nr_pages = PFN_UP(memory_block_memmap_size()); /* * In "forced" memmap_on_memory mode, we add extra pages to align the * vmemmap size to cover full pageblocks. That way, we can add memory * even if the vmemmap size is not properly aligned, however, we might waste * memory. */ if (memmap_mode == MEMMAP_ON_MEMORY_FORCE) return pageblock_align(nr_pages); return nr_pages; } #ifdef CONFIG_MHP_MEMMAP_ON_MEMORY /* * memory_hotplug.memmap_on_memory parameter */ static int set_memmap_mode(const char *val, const struct kernel_param *kp) { int ret, mode; bool enabled; if (sysfs_streq(val, "force") || sysfs_streq(val, "FORCE")) { mode = MEMMAP_ON_MEMORY_FORCE; } else { ret = kstrtobool(val, &enabled); if (ret < 0) return ret; if (enabled) mode = MEMMAP_ON_MEMORY_ENABLE; else mode = MEMMAP_ON_MEMORY_DISABLE; } *((int *)kp->arg) = mode; if (mode == MEMMAP_ON_MEMORY_FORCE) { unsigned long memmap_pages = memory_block_memmap_on_memory_pages(); pr_info_once("Memory hotplug will waste %ld pages in each memory block\n", memmap_pages - PFN_UP(memory_block_memmap_size())); } return 0; } static int get_memmap_mode(char *buffer, const struct kernel_param *kp) { int mode = *((int *)kp->arg); if (mode == MEMMAP_ON_MEMORY_FORCE) return sprintf(buffer, "force\n"); return sprintf(buffer, "%c\n", mode ? 'Y' : 'N'); } static const struct kernel_param_ops memmap_mode_ops = { .set = set_memmap_mode, .get = get_memmap_mode, }; module_param_cb(memmap_on_memory, &memmap_mode_ops, &memmap_mode, 0444); MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug\n" "With value \"force\" it could result in memory wastage due " "to memmap size limitations (Y/N/force)"); static inline bool mhp_memmap_on_memory(void) { return memmap_mode != MEMMAP_ON_MEMORY_DISABLE; } #else static inline bool mhp_memmap_on_memory(void) { return false; } #endif enum { ONLINE_POLICY_CONTIG_ZONES = 0, ONLINE_POLICY_AUTO_MOVABLE, }; static const char * const online_policy_to_str[] = { [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones", [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable", }; static int set_online_policy(const char *val, const struct kernel_param *kp) { int ret = sysfs_match_string(online_policy_to_str, val); if (ret < 0) return ret; *((int *)kp->arg) = ret; return 0; } static int get_online_policy(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%s\n", online_policy_to_str[*((int *)kp->arg)]); } /* * memory_hotplug.online_policy: configure online behavior when onlining without * specifying a zone (MMOP_ONLINE) * * "contig-zones": keep zone contiguous * "auto-movable": online memory to ZONE_MOVABLE if the configuration * (auto_movable_ratio, auto_movable_numa_aware) allows for it */ static int online_policy __read_mostly = ONLINE_POLICY_CONTIG_ZONES; static const struct kernel_param_ops online_policy_ops = { .set = set_online_policy, .get = get_online_policy, }; module_param_cb(online_policy, &online_policy_ops, &online_policy, 0644); MODULE_PARM_DESC(online_policy, "Set the online policy (\"contig-zones\", \"auto-movable\") " "Default: \"contig-zones\""); /* * memory_hotplug.auto_movable_ratio: specify maximum MOVABLE:KERNEL ratio * * The ratio represent an upper limit and the kernel might decide to not * online some memory to ZONE_MOVABLE -- e.g., because hotplugged KERNEL memory * doesn't allow for more MOVABLE memory. */ static unsigned int auto_movable_ratio __read_mostly = 301; module_param(auto_movable_ratio, uint, 0644); MODULE_PARM_DESC(auto_movable_ratio, "Set the maximum ratio of MOVABLE:KERNEL memory in the system " "in percent for \"auto-movable\" online policy. Default: 301"); /* * memory_hotplug.auto_movable_numa_aware: consider numa node stats */ #ifdef CONFIG_NUMA static bool auto_movable_numa_aware __read_mostly = true; module_param(auto_movable_numa_aware, bool, 0644); MODULE_PARM_DESC(auto_movable_numa_aware, "Consider numa node stats in addition to global stats in " "\"auto-movable\" online policy. Default: true"); #endif /* CONFIG_NUMA */ /* * online_page_callback contains pointer to current page onlining function. * Initially it is generic_online_page(). If it is required it could be * changed by calling set_online_page_callback() for callback registration * and restore_online_page_callback() for generic callback restore. */ static online_page_callback_t online_page_callback = generic_online_page; static DEFINE_MUTEX(online_page_callback_lock); DEFINE_STATIC_PERCPU_RWSEM(mem_hotplug_lock); void get_online_mems(void) { percpu_down_read(&mem_hotplug_lock); } void put_online_mems(void) { percpu_up_read(&mem_hotplug_lock); } bool movable_node_enabled = false; static int mhp_default_online_type = -1; enum mmop mhp_get_default_online_type(void) { if (mhp_default_online_type >= 0) return mhp_default_online_type; if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE)) mhp_default_online_type = MMOP_OFFLINE; else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO)) mhp_default_online_type = MMOP_ONLINE; else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL)) mhp_default_online_type = MMOP_ONLINE_KERNEL; else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE)) mhp_default_online_type = MMOP_ONLINE_MOVABLE; else mhp_default_online_type = MMOP_OFFLINE; return mhp_default_online_type; } EXPORT_SYMBOL_GPL(mhp_get_default_online_type); void mhp_set_default_online_type(enum mmop online_type) { mhp_default_online_type = online_type; } static int __init setup_memhp_default_state(char *str) { const int online_type = mhp_online_type_from_str(str); if (online_type >= 0) mhp_default_online_type = online_type; return 1; } __setup("memhp_default_state=", setup_memhp_default_state); void mem_hotplug_begin(void) { cpus_read_lock(); percpu_down_write(&mem_hotplug_lock); } void mem_hotplug_done(void) { percpu_up_write(&mem_hotplug_lock); cpus_read_unlock(); } u64 max_mem_size = U64_MAX; /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size, const char *resource_name) { struct resource *res; unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; if (strcmp(resource_name, "System RAM")) flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED; if (!mhp_range_allowed(start, size, true)) return ERR_PTR(-E2BIG); /* * Make sure value parsed from 'mem=' only restricts memory adding * while booting, so that memory hotplug won't be impacted. Please * refer to document of 'mem=' in kernel-parameters.txt for more * details. */ if (start + size > max_mem_size && system_state < SYSTEM_RUNNING) return ERR_PTR(-E2BIG); /* * Request ownership of the new memory range. This might be * a child of an existing resource that was present but * not marked as busy. */ res = __request_region(&iomem_resource, start, size, resource_name, flags); if (!res) { pr_debug("Unable to reserve System RAM region: %016llx->%016llx\n", start, start + size); return ERR_PTR(-EEXIST); } return res; } static void release_memory_resource(struct resource *res) { if (!res) return; release_resource(res); kfree(res); } static int check_pfn_span(unsigned long pfn, unsigned long nr_pages) { /* * Disallow all operations smaller than a sub-section. * Note that check_hotplug_memory_range() enforces a larger * memory_block_size_bytes() granularity for memory that will be marked * online, so this check should only fire for direct * arch_{add,remove}_memory() users outside of add_memory_resource(). */ if (!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SUBSECTION)) return -EINVAL; return 0; } /* * Return page for the valid pfn only if the page is online. All pfn * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ struct page *pfn_to_online_page(unsigned long pfn) { unsigned long nr = pfn_to_section_nr(pfn); struct dev_pagemap *pgmap; struct mem_section *ms; if (nr >= NR_MEM_SECTIONS) return NULL; ms = __nr_to_section(nr); if (!online_section(ms)) return NULL; /* * Save some code text when online_section() + * pfn_section_valid() are sufficient. */ if (IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) && !pfn_valid(pfn)) return NULL; if (!pfn_section_valid(ms, pfn)) return NULL; if (!online_device_section(ms)) return pfn_to_page(pfn); /* * Slowpath: when ZONE_DEVICE collides with * ZONE_{NORMAL,MOVABLE} within the same section some pfns in * the section may be 'offline' but 'valid'. Only * get_dev_pagemap() can determine sub-section online status. */ pgmap = get_dev_pagemap(pfn); put_dev_pagemap(pgmap); /* The presence of a pgmap indicates ZONE_DEVICE offline pfn */ if (pgmap) return NULL; return pfn_to_page(pfn); } EXPORT_SYMBOL_GPL(pfn_to_online_page); int __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, struct mhp_params *params) { const unsigned long end_pfn = pfn + nr_pages; unsigned long cur_nr_pages; int err; struct vmem_altmap *altmap = params->altmap; if (WARN_ON_ONCE(!pgprot_val(params->pgprot))) return -EINVAL; VM_BUG_ON(!mhp_range_allowed(PFN_PHYS(pfn), nr_pages * PAGE_SIZE, false)); if (altmap) { /* * Validate altmap is within bounds of the total request */ if (altmap->base_pfn != pfn || vmem_altmap_offset(altmap) > nr_pages) { pr_warn_once("memory add fail, invalid altmap\n"); return -EINVAL; } altmap->alloc = 0; } if (check_pfn_span(pfn, nr_pages)) { WARN(1, "Misaligned %s start: %#lx end: %#lx\n", __func__, pfn, pfn + nr_pages - 1); return -EINVAL; } for (; pfn < end_pfn; pfn += cur_nr_pages) { /* Select all remaining pages up to the next section boundary */ cur_nr_pages = min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); err = sparse_add_section(nid, pfn, cur_nr_pages, altmap, params->pgmap); if (err) break; cond_resched(); } vmemmap_populate_print_last(); return err; } /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) continue; if (zone != page_zone(pfn_to_page(start_pfn))) continue; return start_pfn; } return 0; } /* find the biggest valid pfn in the range [start_pfn, end_pfn). */ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) continue; if (zone != page_zone(pfn_to_page(pfn))) continue; return pfn; } return 0; } static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; int nid = zone_to_nid(zone); if (zone->zone_start_pfn == start_pfn) { /* * If the section is smallest section in the zone, it need * shrink zone->zone_start_pfn and zone->zone_spanned_pages. * In this case, we find second smallest valid mem_section * for shrinking zone. */ pfn = find_smallest_section_pfn(nid, zone, end_pfn, zone_end_pfn(zone)); if (pfn) { zone->spanned_pages = zone_end_pfn(zone) - pfn; zone->zone_start_pfn = pfn; } else { zone->zone_start_pfn = 0; zone->spanned_pages = 0; } } else if (zone_end_pfn(zone) == end_pfn) { /* * If the section is biggest section in the zone, it need * shrink zone->spanned_pages. * In this case, we find second biggest valid mem_section for * shrinking zone. */ pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn, start_pfn); if (pfn) zone->spanned_pages = pfn - zone->zone_start_pfn + 1; else { zone->zone_start_pfn = 0; zone->spanned_pages = 0; } } } static void update_pgdat_span(struct pglist_data *pgdat) { unsigned long node_start_pfn = 0, node_end_pfn = 0; struct zone *zone; for (zone = pgdat->node_zones; zone < pgdat->node_zones + MAX_NR_ZONES; zone++) { unsigned long end_pfn = zone_end_pfn(zone); /* No need to lock the zones, they can't change. */ if (!zone->spanned_pages) continue; if (!node_end_pfn) { node_start_pfn = zone->zone_start_pfn; node_end_pfn = end_pfn; continue; } if (end_pfn > node_end_pfn) node_end_pfn = end_pfn; if (zone->zone_start_pfn < node_start_pfn) node_start_pfn = zone->zone_start_pfn; } pgdat->node_start_pfn = node_start_pfn; pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } void remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { const unsigned long end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; unsigned long pfn, cur_nr_pages; /* Poison struct pages because they are now uninitialized again. */ for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { cond_resched(); /* Select all remaining pages up to the next section boundary */ cur_nr_pages = min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); page_init_poison(pfn_to_page(pfn), sizeof(struct page) * cur_nr_pages); } /* * Zone shrinking code cannot properly deal with ZONE_DEVICE. So * we will not try to shrink the zones - which is okay as * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. */ if (zone_is_zone_device(zone)) return; clear_zone_contiguous(zone); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); set_zone_contiguous(zone); } /** * __remove_pages() - remove sections of pages * @pfn: starting pageframe (must be aligned to start of a section) * @nr_pages: number of pages to remove (must be multiple of section size) * @altmap: alternative device page map or %NULL if default memmap is used * @pgmap: device page map or %NULL if not ZONE_DEVICE * * Generic helper function to remove section mappings and sysfs entries * for the section of the memory we are removing. Caller needs to make * sure that pages are marked reserved and zones are adjust properly by * calling offline_pages(). */ void __remove_pages(unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { const unsigned long end_pfn = pfn + nr_pages; unsigned long cur_nr_pages; if (check_pfn_span(pfn, nr_pages)) { WARN(1, "Misaligned %s start: %#lx end: %#lx\n", __func__, pfn, pfn + nr_pages - 1); return; } for (; pfn < end_pfn; pfn += cur_nr_pages) { cond_resched(); /* Select all remaining pages up to the next section boundary */ cur_nr_pages = min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); sparse_remove_section(pfn, cur_nr_pages, altmap, pgmap); } } int set_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; get_online_mems(); mutex_lock(&online_page_callback_lock); if (online_page_callback == generic_online_page) { online_page_callback = callback; rc = 0; } mutex_unlock(&online_page_callback_lock); put_online_mems(); return rc; } EXPORT_SYMBOL_GPL(set_online_page_callback); int restore_online_page_callback(online_page_callback_t callback) { int rc = -EINVAL; get_online_mems(); mutex_lock(&online_page_callback_lock); if (online_page_callback == callback) { online_page_callback = generic_online_page; rc = 0; } mutex_unlock(&online_page_callback_lock); put_online_mems(); return rc; } EXPORT_SYMBOL_GPL(restore_online_page_callback); /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ void generic_online_page(struct page *page, unsigned int order) { __free_pages_core(page, order, MEMINIT_HOTPLUG); } EXPORT_SYMBOL_GPL(generic_online_page); static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) { const unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn; /* * Online the pages in MAX_PAGE_ORDER aligned chunks. The callback might * decide to not expose all pages to the buddy (e.g., expose them * later). We account all pages as being online and belonging to this * zone ("present"). * When using memmap_on_memory, the range might not be aligned to * MAX_ORDER_NR_PAGES - 1, but pageblock aligned. __ffs() will detect * this and the first chunk to online will be pageblock_nr_pages. */ for (pfn = start_pfn; pfn < end_pfn;) { struct page *page = pfn_to_page(pfn); int order; /* * Free to online pages in the largest chunks alignment allows. * * __ffs() behaviour is undefined for 0. start == 0 is * MAX_PAGE_ORDER-aligned, Set order to MAX_PAGE_ORDER for * the case. */ if (pfn) order = min_t(int, MAX_PAGE_ORDER, __ffs(pfn)); else order = MAX_PAGE_ORDER; /* * Exposing the page to the buddy by freeing can cause * issues with debug_pagealloc enabled: some archs don't * like double-unmappings. So treat them like any pages that * were allocated from the buddy. */ debug_pagealloc_map_pages(page, 1 << order); (*online_page_callback)(page, order); pfn += (1UL << order); } /* mark all involved sections as online */ online_mem_sections(start_pfn, end_pfn); } static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { unsigned long old_end_pfn = zone_end_pfn(zone); if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn) zone->zone_start_pfn = start_pfn; zone->spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - zone->zone_start_pfn; } static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned long start_pfn, unsigned long nr_pages) { unsigned long old_end_pfn = pgdat_end_pfn(pgdat); if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn) pgdat->node_start_pfn = start_pfn; pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn; } #ifdef CONFIG_ZONE_DEVICE static void section_taint_zone_device(unsigned long pfn) { struct mem_section *ms = __pfn_to_section(pfn); ms->section_mem_map |= SECTION_TAINT_ZONE_DEVICE; } #else static inline void section_taint_zone_device(unsigned long pfn) { } #endif /* * Associate the pfn range with the given zone, initializing the memmaps * and resizing the pgdat/zone data to span the added pages. After this * call, all affected pages are PageOffline(). * * All aligned pageblocks are initialized to the specified migratetype * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related * zone stats (e.g., nr_isolate_pageblock) are touched. */ void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap, int migratetype, bool isolate_pageblock) { struct pglist_data *pgdat = zone->zone_pgdat; int nid = pgdat->node_id; clear_zone_contiguous(zone); if (zone_is_empty(zone)) init_currently_empty_zone(zone, start_pfn, nr_pages); resize_zone_range(zone, start_pfn, nr_pages); resize_pgdat_range(pgdat, start_pfn, nr_pages); /* * Subsection population requires care in pfn_to_online_page(). * Set the taint to enable the slow path detection of * ZONE_DEVICE pages in an otherwise ZONE_{NORMAL,MOVABLE} * section. */ if (zone_is_zone_device(zone)) { if (!IS_ALIGNED(start_pfn, PAGES_PER_SECTION)) section_taint_zone_device(start_pfn); if (!IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)) section_taint_zone_device(start_pfn + nr_pages); } /* * TODO now we have a visible range of pages which are not associated * with their zone properly. Not nice but set_pfnblock_migratetype() * expects the zone spans the pfn range. All the pages in the range * are reserved so nobody should be touching them so we should be safe */ memmap_init_range(nr_pages, nid, zone_idx(zone), start_pfn, 0, MEMINIT_HOTPLUG, altmap, migratetype, isolate_pageblock); set_zone_contiguous(zone); } struct auto_movable_stats { unsigned long kernel_early_pages; unsigned long movable_pages; }; static void auto_movable_stats_account_zone(struct auto_movable_stats *stats, struct zone *zone) { if (zone_idx(zone) == ZONE_MOVABLE) { stats->movable_pages += zone->present_pages; } else { stats->kernel_early_pages += zone->present_early_pages; #ifdef CONFIG_CMA /* * CMA pages (never on hotplugged memory) behave like * ZONE_MOVABLE. */ stats->movable_pages += zone->cma_pages; stats->kernel_early_pages -= zone->cma_pages; #endif /* CONFIG_CMA */ } } struct auto_movable_group_stats { unsigned long movable_pages; unsigned long req_kernel_early_pages; }; static int auto_movable_stats_account_group(struct memory_group *group, void *arg) { const int ratio = READ_ONCE(auto_movable_ratio); struct auto_movable_group_stats *stats = arg; long pages; /* * We don't support modifying the config while the auto-movable online * policy is already enabled. Just avoid the division by zero below. */ if (!ratio) return 0; /* * Calculate how many early kernel pages this group requires to * satisfy the configured zone ratio. */ pages = group->present_movable_pages * 100 / ratio; pages -= group->present_kernel_pages; if (pages > 0) stats->req_kernel_early_pages += pages; stats->movable_pages += group->present_movable_pages; return 0; } static bool auto_movable_can_online_movable(int nid, struct memory_group *group, unsigned long nr_pages) { unsigned long kernel_early_pages, movable_pages; struct auto_movable_group_stats group_stats = {}; struct auto_movable_stats stats = {}; struct zone *zone; int i; /* Walk all relevant zones and collect MOVABLE vs. KERNEL stats. */ if (nid == NUMA_NO_NODE) { /* TODO: cache values */ for_each_populated_zone(zone) auto_movable_stats_account_zone(&stats, zone); } else { for (i = 0; i < MAX_NR_ZONES; i++) { pg_data_t *pgdat = NODE_DATA(nid); zone = pgdat->node_zones + i; if (populated_zone(zone)) auto_movable_stats_account_zone(&stats, zone); } } kernel_early_pages = stats.kernel_early_pages; movable_pages = stats.movable_pages; /* * Kernel memory inside dynamic memory group allows for more MOVABLE * memory within the same group. Remove the effect of all but the * current group from the stats. */ walk_dynamic_memory_groups(nid, auto_movable_stats_account_group, group, &group_stats); if (kernel_early_pages <= group_stats.req_kernel_early_pages) return false; kernel_early_pages -= group_stats.req_kernel_early_pages; movable_pages -= group_stats.movable_pages; if (group && group->is_dynamic) kernel_early_pages += group->present_kernel_pages; /* * Test if we could online the given number of pages to ZONE_MOVABLE * and still stay in the configured ratio. */ movable_pages += nr_pages; return movable_pages <= (auto_movable_ratio * kernel_early_pages) / 100; } /* * Returns a default kernel memory zone for the given pfn range. * If no kernel zone covers this pfn range it will automatically go * to the ZONE_NORMAL. */ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn, unsigned long nr_pages) { struct pglist_data *pgdat = NODE_DATA(nid); int zid; for (zid = 0; zid < ZONE_NORMAL; zid++) { struct zone *zone = &pgdat->node_zones[zid]; if (zone_intersects(zone, start_pfn, nr_pages)) return zone; } return &pgdat->node_zones[ZONE_NORMAL]; } /* * Determine to which zone to online memory dynamically based on user * configuration and system stats. We care about the following ratio: * * MOVABLE : KERNEL * * Whereby MOVABLE is memory in ZONE_MOVABLE and KERNEL is memory in * one of the kernel zones. CMA pages inside one of the kernel zones really * behaves like ZONE_MOVABLE, so we treat them accordingly. * * We don't allow for hotplugged memory in a KERNEL zone to increase the * amount of MOVABLE memory we can have, so we end up with: * * MOVABLE : KERNEL_EARLY * * Whereby KERNEL_EARLY is memory in one of the kernel zones, available since * boot. We base our calculation on KERNEL_EARLY internally, because: * * a) Hotplugged memory in one of the kernel zones can sometimes still get * hotunplugged, especially when hot(un)plugging individual memory blocks. * There is no coordination across memory devices, therefore "automatic" * hotunplugging, as implemented in hypervisors, could result in zone * imbalances. * b) Early/boot memory in one of the kernel zones can usually not get * hotunplugged again (e.g., no firmware interface to unplug, fragmented * with unmovable allocations). While there are corner cases where it might * still work, it is barely relevant in practice. * * Exceptions are dynamic memory groups, which allow for more MOVABLE * memory within the same memory group -- because in that case, there is * coordination within the single memory device managed by a single driver. * * We rely on "present pages" instead of "managed pages", as the latter is * highly unreliable and dynamic in virtualized environments, and does not * consider boot time allocations. For example, memory ballooning adjusts the * managed pages when inflating/deflating the balloon, and balloon page * migration can even migrate inflated pages between zones. * * Using "present pages" is better but some things to keep in mind are: * * a) Some memblock allocations, such as for the crashkernel area, are * effectively unused by the kernel, yet they account to "present pages". * Fortunately, these allocations are comparatively small in relevant setups * (e.g., fraction of system memory). * b) Some hotplugged memory blocks in virtualized environments, especially * hotplugged by virtio-mem, look like they are completely present, however, * only parts of the memory block are actually currently usable. * "present pages" is an upper limit that can get reached at runtime. As * we base our calculations on KERNEL_EARLY, this is not an issue. */ static struct zone *auto_movable_zone_for_pfn(int nid, struct memory_group *group, unsigned long pfn, unsigned long nr_pages) { unsigned long online_pages = 0, max_pages, end_pfn; struct page *page; if (!auto_movable_ratio) goto kernel_zone; if (group && !group->is_dynamic) { max_pages = group->s.max_pages; online_pages = group->present_movable_pages; /* If anything is !MOVABLE online the rest !MOVABLE. */ if (group->present_kernel_pages) goto kernel_zone; } else if (!group || group->d.unit_pages == nr_pages) { max_pages = nr_pages; } else { max_pages = group->d.unit_pages; /* * Take a look at all online sections in the current unit. * We can safely assume that all pages within a section belong * to the same zone, because dynamic memory groups only deal * with hotplugged memory. */ pfn = ALIGN_DOWN(pfn, group->d.unit_pages); end_pfn = pfn + group->d.unit_pages; for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { page = pfn_to_online_page(pfn); if (!page) continue; /* If anything is !MOVABLE online the rest !MOVABLE. */ if (!is_zone_movable_page(page)) goto kernel_zone; online_pages += PAGES_PER_SECTION; } } /* * Online MOVABLE if we could *currently* online all remaining parts * MOVABLE. We expect to (add+) online them immediately next, so if * nobody interferes, all will be MOVABLE if possible. */ nr_pages = max_pages - online_pages; if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages)) goto kernel_zone; #ifdef CONFIG_NUMA if (auto_movable_numa_aware && !auto_movable_can_online_movable(nid, group, nr_pages)) goto kernel_zone; #endif /* CONFIG_NUMA */ return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; kernel_zone: return default_kernel_zone_for_pfn(nid, pfn, nr_pages); } static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, unsigned long nr_pages) { struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages); bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages); /* * We inherit the existing zone in a simple case where zones do not * overlap in the given range */ if (in_kernel ^ in_movable) return (in_kernel) ? kernel_zone : movable_zone; /* * If the range doesn't belong to any zone or two zones overlap in the * given range then we use movable zone only if movable_node is * enabled because we always online to a kernel zone by default. */ return movable_node_enabled ? movable_zone : kernel_zone; } struct zone *zone_for_pfn_range(enum mmop online_type, int nid, struct memory_group *group, unsigned long start_pfn, unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); if (online_type == MMOP_ONLINE_MOVABLE) return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; if (online_policy == ONLINE_POLICY_AUTO_MOVABLE) return auto_movable_zone_for_pfn(nid, group, start_pfn, nr_pages); return default_zone_for_pfn(nid, start_pfn, nr_pages); } /* * This function should only be called by memory_block_{online,offline}, * and {online,offline}_pages. */ void adjust_present_page_count(struct page *page, struct memory_group *group, long nr_pages) { struct zone *zone = page_zone(page); const bool movable = zone_idx(zone) == ZONE_MOVABLE; /* * We only support onlining/offlining/adding/removing of complete * memory blocks; therefore, either all is either early or hotplugged. */ if (early_section(__pfn_to_section(page_to_pfn(page)))) zone->present_early_pages += nr_pages; zone->present_pages += nr_pages; zone->zone_pgdat->node_present_pages += nr_pages; if (group && movable) group->present_movable_pages += nr_pages; else if (group && !movable) group->present_kernel_pages += nr_pages; } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, struct zone *zone) { unsigned long end_pfn = pfn + nr_pages; int ret, i; ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); if (ret) return ret; move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE, false); for (i = 0; i < nr_pages; i++) { struct page *page = pfn_to_page(pfn + i); __ClearPageOffline(page); SetPageVmemmapSelfHosted(page); } /* * It might be that the vmemmap_pages fully span sections. If that is * the case, mark those sections online here as otherwise they will be * left offline. */ if (nr_pages >= PAGES_PER_SECTION) online_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION)); return ret; } void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) { unsigned long end_pfn = pfn + nr_pages; /* * It might be that the vmemmap_pages fully span sections. If that is * the case, mark those sections offline here as otherwise they will be * left online. */ if (nr_pages >= PAGES_PER_SECTION) offline_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION)); /* * The pages associated with this vmemmap have been offlined, so * we can reset its state here. */ remove_pfn_range_from_zone(page_zone(pfn_to_page(pfn)), pfn, nr_pages); kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } /* * Must be called with mem_hotplug_lock in write mode. */ int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { struct memory_notify mem_arg = { .start_pfn = pfn, .nr_pages = nr_pages, }; struct node_notify node_arg = { .nid = NUMA_NO_NODE, }; const int nid = zone_to_nid(zone); int need_zonelists_rebuild = 0; unsigned long flags; int ret; /* * {on,off}lining is constrained to full memory sections (or more * precisely to memory blocks from the user space POV). * memmap_on_memory is an exception because it reserves initial part * of the physical memory space for vmemmaps. That space is pageblock * aligned. */ if (WARN_ON_ONCE(!nr_pages || !pageblock_aligned(pfn) || !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE, true); if (!node_state(nid, N_MEMORY)) { /* Adding memory to the node for the first time */ node_arg.nid = nid; ret = node_notify(NODE_ADDING_FIRST_MEMORY, &node_arg); ret = notifier_to_errno(ret); if (ret) goto failed_addition; } ret = memory_notify(MEM_GOING_ONLINE, &mem_arg); ret = notifier_to_errno(ret); if (ret) goto failed_addition; /* * Fixup the number of isolated pageblocks before marking the sections * onlining, such that undo_isolate_page_range() works correctly. */ spin_lock_irqsave(&zone->lock, flags); zone->nr_isolate_pageblock += nr_pages / pageblock_nr_pages; spin_unlock_irqrestore(&zone->lock, flags); /* * If this zone is not populated, then it is not in zonelist. * This means the page allocator ignores this zone. * So, zonelist must be updated after online. */ if (!populated_zone(zone)) { need_zonelists_rebuild = 1; setup_zone_pageset(zone); } online_pages_range(pfn, nr_pages); adjust_present_page_count(pfn_to_page(pfn), group, nr_pages); if (node_arg.nid >= 0) node_set_state(nid, N_MEMORY); /* * Check whether we are adding normal memory to the node for the first * time. */ if (!node_state(nid, N_NORMAL_MEMORY) && zone_idx(zone) <= ZONE_NORMAL) node_set_state(nid, N_NORMAL_MEMORY); if (need_zonelists_rebuild) build_all_zonelists(NULL); /* Basic onlining is complete, allow allocation of onlined pages. */ undo_isolate_page_range(pfn, pfn + nr_pages); /* * Freshly onlined pages aren't shuffled (e.g., all pages are placed to * the tail of the freelist when undoing isolation). Shuffle the whole * zone to make sure the just onlined pages are properly distributed * across the whole freelist - to create an initial shuffle. */ shuffle_zone(zone); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); kswapd_run(nid); kcompactd_run(nid); if (node_arg.nid >= 0) /* First memory added successfully. Notify consumers. */ node_notify(NODE_ADDED_FIRST_MEMORY, &node_arg); writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &mem_arg); return 0; failed_addition: pr_debug("online_pages [mem %#010llx-%#010llx] failed\n", (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &mem_arg); if (node_arg.nid != NUMA_NO_NODE) node_notify(NODE_CANCEL_ADDING_FIRST_MEMORY, &node_arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); return ret; } /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ static pg_data_t *hotadd_init_pgdat(int nid) { struct pglist_data *pgdat; /* * NODE_DATA is preallocated (free_area_init) but its internal * state is not allocated completely. Add missing pieces. * Completely offline nodes stay around and they just need * reinitialization. */ pgdat = NODE_DATA(nid); /* init node's zones as empty zones, we don't have any present pages.*/ if (free_area_init_core_hotplug(pgdat)) return NULL; /* * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ build_all_zonelists(pgdat); return pgdat; } /* * __try_online_node - online a node if offlined * @nid: the node ID * @set_node_online: Whether we want to online the node * called by cpu_up() to online a node without onlined memory. * * Returns: * 1 -> a new node has been allocated * 0 -> the node is already online * -ENOMEM -> the node could not be allocated */ static int __try_online_node(int nid, bool set_node_online) { pg_data_t *pgdat; int ret = 1; if (node_online(nid)) return 0; pgdat = hotadd_init_pgdat(nid); if (!pgdat) { pr_err("Cannot online node %d due to NULL pgdat\n", nid); ret = -ENOMEM; goto out; } if (set_node_online) { node_set_online(nid); ret = register_node(nid); BUG_ON(ret); } out: return ret; } /* * Users of this function always want to online/register the node */ int try_online_node(int nid) { int ret; mem_hotplug_begin(); ret = __try_online_node(nid, true); mem_hotplug_done(); return ret; } static int check_hotplug_memory_range(u64 start, u64 size) { /* memory range must be block size aligned */ if (!size || !IS_ALIGNED(start, memory_block_size_bytes()) || !IS_ALIGNED(size, memory_block_size_bytes())) { pr_err("Block size [%#lx] unaligned hotplug range: start %#llx, size %#llx", memory_block_size_bytes(), start, size); return -EINVAL; } return 0; } static int online_memory_block(struct memory_block *mem, void *arg) { enum mmop *online_type = arg; mem->online_type = *online_type; return device_online(&mem->dev); } #ifndef arch_supports_memmap_on_memory static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size) { /* * As default, we want the vmemmap to span a complete PMD such that we * can map the vmemmap using a single PMD if supported by the * architecture. */ return IS_ALIGNED(vmemmap_size, PMD_SIZE); } #endif bool mhp_supports_memmap_on_memory(void) { unsigned long vmemmap_size = memory_block_memmap_size(); unsigned long memmap_pages = memory_block_memmap_on_memory_pages(); /* * Besides having arch support and the feature enabled at runtime, we * need a few more assumptions to hold true: * * a) The vmemmap pages span complete PMDs: We don't want vmemmap code * to populate memory from the altmap for unrelated parts (i.e., * other memory blocks) * * b) The vmemmap pages (and thereby the pages that will be exposed to * the buddy) have to cover full pageblocks: memory onlining/offlining * code requires applicable ranges to be page-aligned, for example, to * set the migratetypes properly. * * TODO: Although we have a check here to make sure that vmemmap pages * fully populate a PMD, it is not the right place to check for * this. A much better solution involves improving vmemmap code * to fallback to base pages when trying to populate vmemmap using * altmap as an alternative source of memory, and we do not exactly * populate a single PMD. */ if (!mhp_memmap_on_memory()) return false; /* * Make sure the vmemmap allocation is fully contained * so that we always allocate vmemmap memory from altmap area. */ if (!IS_ALIGNED(vmemmap_size, PAGE_SIZE)) return false; /* * start pfn should be pageblock_nr_pages aligned for correctly * setting migrate types */ if (!pageblock_aligned(memmap_pages)) return false; if (memmap_pages == PHYS_PFN(memory_block_size_bytes())) /* No effective hotplugged memory doesn't make sense. */ return false; return arch_supports_memmap_on_memory(vmemmap_size); } EXPORT_SYMBOL_GPL(mhp_supports_memmap_on_memory); static void altmap_free(struct vmem_altmap *altmap) { WARN_ONCE(altmap->alloc, "Altmap not fully unmapped"); kfree(altmap); } static void remove_memory_blocks_and_altmaps(u64 start, u64 size) { unsigned long memblock_size = memory_block_size_bytes(); u64 cur_start; /* * For memmap_on_memory, the altmaps were added on a per-memblock * basis; we have to process each individual memory block. */ for (cur_start = start; cur_start < start + size; cur_start += memblock_size) { struct vmem_altmap *altmap = NULL; struct memory_block *mem; mem = memory_block_get(phys_to_block_id(cur_start)); if (WARN_ON_ONCE(!mem)) continue; altmap = mem->altmap; mem->altmap = NULL; memory_block_put(mem); remove_memory_block_devices(cur_start, memblock_size); arch_remove_memory(cur_start, memblock_size, altmap, NULL); altmap_free(altmap); } } static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, u64 start, u64 size) { unsigned long memblock_size = memory_block_size_bytes(); u64 cur_start; int ret; for (cur_start = start; cur_start < start + size; cur_start += memblock_size) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; struct vmem_altmap mhp_altmap = { .base_pfn = PHYS_PFN(cur_start), .end_pfn = PHYS_PFN(cur_start + memblock_size - 1), }; mhp_altmap.free = memory_block_memmap_on_memory_pages(); params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap), GFP_KERNEL); if (!params.altmap) { ret = -ENOMEM; goto out; } /* call arch's memory hotadd */ ret = arch_add_memory(nid, cur_start, memblock_size, ¶ms); if (ret < 0) { altmap_free(params.altmap); goto out; } /* create memory block devices after memory was added */ ret = create_memory_block_devices(cur_start, memblock_size, nid, params.altmap, group); if (ret) { arch_remove_memory(cur_start, memblock_size, params.altmap, NULL); altmap_free(params.altmap); goto out; } } return 0; out: if (ret && cur_start != start) remove_memory_blocks_and_altmaps(start, cur_start - start); return ret; } /* * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations (triggered e.g. by sysfs). * * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ static int __add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags, enum mmop online_type) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; enum memblock_flags memblock_flags = MEMBLOCK_NONE; struct memory_group *group = NULL; u64 start, size; bool new_node = false; int ret; start = res->start; size = resource_size(res); ret = check_hotplug_memory_range(start, size); if (ret) return ret; if (mhp_flags & MHP_NID_IS_MGID) { group = memory_group_find_by_id(nid); if (!group) return -EINVAL; nid = group->nid; } if (!node_possible(nid)) { WARN(1, "node %d was absent from the node_possible_map\n", nid); return -EINVAL; } mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED) memblock_flags = MEMBLOCK_DRIVER_MANAGED; ret = memblock_add_node(start, size, nid, memblock_flags); if (ret) goto error_mem_hotplug_end; } ret = __try_online_node(nid, false); if (ret < 0) goto error_memblock_remove; if (ret) { node_set_online(nid); ret = register_node(nid); if (WARN_ON(ret)) { node_set_offline(nid); goto error_memblock_remove; } new_node = true; } /* * Self hosted memmap array */ if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) && mhp_supports_memmap_on_memory()) { ret = create_altmaps_and_memory_blocks(nid, group, start, size); if (ret) goto error; } else { ret = arch_add_memory(nid, start, size, ¶ms); if (ret < 0) goto error; /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, nid, NULL, group); if (ret) { arch_remove_memory(start, size, params.altmap, NULL); goto error; } } register_memory_blocks_under_node_hotplug(nid, PFN_DOWN(start), PFN_UP(start + size - 1)); /* create new memmap entry */ if (!strcmp(res->name, "System RAM")) firmware_map_add_hotplug(start, start + size, "System RAM"); /* device_online() will take the lock when calling online_pages() */ mem_hotplug_done(); /* * In case we're allowed to merge the resource, flag it and trigger * merging now that adding succeeded. */ if (mhp_flags & MHP_MERGE_RESOURCE) merge_system_ram_resource(res); /* online pages if requested */ if (online_type != MMOP_OFFLINE) walk_memory_blocks(start, size, &online_type, online_memory_block); return ret; error: if (new_node) { node_set_offline(nid); unregister_node(nid); } error_memblock_remove: if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); error_mem_hotplug_end: mem_hotplug_done(); return ret; } int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { return __add_memory_resource(nid, res, mhp_flags, mhp_get_default_online_type()); } /* requires device_hotplug_lock, see __add_memory_resource() */ int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags) { struct resource *res; int ret; res = register_memory_resource(start, size, "System RAM"); if (IS_ERR(res)) return PTR_ERR(res); ret = add_memory_resource(nid, res, mhp_flags); if (ret < 0) release_memory_resource(res); return ret; } int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags) { int rc; lock_device_hotplug(); rc = __add_memory(nid, start, size, mhp_flags); unlock_device_hotplug(); return rc; } EXPORT_SYMBOL_GPL(add_memory); /** * __add_memory_driver_managed - add driver-managed memory with explicit online_type * @nid: NUMA node ID where the memory will be added * @start: Start physical address of the memory range * @size: Size of the memory range in bytes * @resource_name: Resource name in format "System RAM ($DRIVER)" * @mhp_flags: Memory hotplug flags * @online_type: Auto-Online behavior (offline, online, kernel, movable) * * Add special, driver-managed memory to the system as system RAM. Such * memory is not exposed via the raw firmware-provided memmap as system * RAM, instead, it is detected and added by a driver - during cold boot, * after a reboot, and after kexec. * * Reasons why this memory should not be used for the initial memmap of a * kexec kernel or for placing kexec images: * * - The booting kernel is in charge of determining how this memory will be * used (e.g., use persistent memory as system RAM) * - Coordination with a hypervisor is required before this memory * can be used (e.g., inaccessible parts). * * For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided * memory map") are created. Also, the created memory resource is flagged * with IORESOURCE_SYSRAM_DRIVER_MANAGED, so in-kernel users can special-case * this memory as well (esp., not place kexec images onto it). * * The resource_name (visible via /proc/iomem) has to have the format * "System RAM ($DRIVER)". * * Return: 0 on success, negative error code on failure. */ int __add_memory_driver_managed(int nid, u64 start, u64 size, const char *resource_name, mhp_t mhp_flags, enum mmop online_type) { struct resource *res; int rc; if (!resource_name || strstr(resource_name, "System RAM (") != resource_name || resource_name[strlen(resource_name) - 1] != ')') return -EINVAL; if (online_type < MMOP_OFFLINE || online_type > MMOP_ONLINE_MOVABLE) return -EINVAL; lock_device_hotplug(); res = register_memory_resource(start, size, resource_name); if (IS_ERR(res)) { rc = PTR_ERR(res); goto out_unlock; } rc = __add_memory_resource(nid, res, mhp_flags, online_type); if (rc < 0) release_memory_resource(res); out_unlock: unlock_device_hotplug(); return rc; } EXPORT_SYMBOL_FOR_MODULES(__add_memory_driver_managed, "kmem"); /** * add_memory_driver_managed - add driver-managed memory * @nid: NUMA node ID where the memory will be added * @start: Start physical address of the memory range * @size: Size of the memory range in bytes * @resource_name: Resource name in format "System RAM ($DRIVER)" * @mhp_flags: Memory hotplug flags * * Add driver-managed memory with the system default online type set by * build config or kernel boot parameter. * * See __add_memory_driver_managed for more details. * * Return: 0 on success, negative error code on failure. */ int add_memory_driver_managed(int nid, u64 start, u64 size, const char *resource_name, mhp_t mhp_flags) { return __add_memory_driver_managed(nid, start, size, resource_name, mhp_flags, mhp_get_default_online_type()); } EXPORT_SYMBOL_GPL(add_memory_driver_managed); /* * Platforms should define arch_get_mappable_range() that provides * maximum possible addressable physical memory range for which the * linear mapping could be created. The platform returned address * range must adhere to these following semantics. * * - range.start <= range.end * - Range includes both end points [range.start..range.end] * * There is also a fallback definition provided here, allowing the * entire possible physical address range in case any platform does * not define arch_get_mappable_range(). */ struct range __weak arch_get_mappable_range(void) { struct range mhp_range = { .start = 0UL, .end = -1ULL, }; return mhp_range; } struct range mhp_get_pluggable_range(bool need_mapping) { const u64 max_phys = DIRECT_MAP_PHYSMEM_END; struct range mhp_range; if (need_mapping) { mhp_range = arch_get_mappable_range(); if (mhp_range.start > max_phys) { mhp_range.start = 0; mhp_range.end = 0; } mhp_range.end = min_t(u64, mhp_range.end, max_phys); } else { mhp_range.start = 0; mhp_range.end = max_phys; } return mhp_range; } EXPORT_SYMBOL_GPL(mhp_get_pluggable_range); bool mhp_range_allowed(u64 start, u64 size, bool need_mapping) { struct range mhp_range = mhp_get_pluggable_range(need_mapping); u64 end = start + size; if (start < end && start >= mhp_range.start && (end - 1) <= mhp_range.end) return true; pr_warn("Hotplug memory [%#llx-%#llx] exceeds maximum addressable range [%#llx-%#llx]\n", start, end, mhp_range.start, mhp_range.end); return false; } #ifdef CONFIG_MEMORY_HOTREMOVE /* * Scan pfn range [start,end) to find movable/migratable pages (LRU and * hugetlb folio, movable_ops pages). Will skip over most unmovable * pages (esp., pages that can be skipped when offlining), but bail out on * definitely unmovable pages. * * Returns: * 0 in case a movable page is found and movable_pfn was updated. * -ENOENT in case no movable page was found. * -EBUSY in case a definitely unmovable page was found. */ static int scan_movable_pages(unsigned long start, unsigned long end, unsigned long *movable_pfn) { unsigned long pfn; for (pfn = start; pfn < end; pfn++) { unsigned long nr_pages; struct page *page; struct folio *folio; page = pfn_to_page(pfn); if (PageLRU(page) || page_has_movable_ops(page)) goto found; /* * PageOffline() pages that do not have movable_ops and * have a reference count > 0 (after MEM_GOING_OFFLINE) are * definitely unmovable. If their reference count would be 0, * they could at least be skipped when offlining memory. */ if (PageOffline(page) && page_count(page)) return -EBUSY; folio = page_folio(page); if (!folio_test_hugetlb(folio)) continue; /* * This test is racy as we hold no reference or lock. The * hugetlb page could have been free'ed and head is no longer * a hugetlb page before the following check. In such unlikely * cases false positives and negatives are possible. Calling * code must deal with these scenarios. */ if (folio_test_hugetlb_migratable(folio)) goto found; nr_pages = folio_nr_pages(folio); if (unlikely(nr_pages < 1 || nr_pages > MAX_FOLIO_NR_PAGES || !is_power_of_2(nr_pages))) continue; pfn |= nr_pages - 1; } return -ENOENT; found: *movable_pfn = pfn; return 0; } static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { struct folio *folio; unsigned long pfn; LIST_HEAD(source); static DEFINE_RATELIMIT_STATE(migrate_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); for (pfn = start_pfn; pfn < end_pfn; pfn++) { struct page *page; page = pfn_to_page(pfn); folio = page_folio(page); if (!folio_try_get(folio)) continue; if (unlikely(page_folio(page) != folio)) goto put_folio; if (folio_test_large(folio)) pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1; if (folio_contain_hwpoisoned_page(folio)) { /* * unmap_poisoned_folio() cannot handle large folios * in all cases yet. */ if (folio_test_large(folio) && !folio_test_hugetlb(folio)) goto put_folio; if (folio_test_lru(folio) && !folio_isolate_lru(folio)) goto put_folio; if (folio_mapped(folio)) { folio_lock(folio); unmap_poisoned_folio(folio, pfn, false); folio_unlock(folio); } goto put_folio; } if (!isolate_folio_to_list(folio, &source)) { if (__ratelimit(&migrate_rs)) { pr_warn("failed to isolate pfn %lx\n", page_to_pfn(page)); dump_page(page, "isolation failed"); } } put_folio: folio_put(folio); } if (!list_empty(&source)) { nodemask_t nmask = node_states[N_MEMORY]; struct migration_target_control mtc = { .nmask = &nmask, .gfp_mask = GFP_KERNEL | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, .reason = MR_MEMORY_HOTPLUG, }; int ret; /* * We have checked that migration range is on a single zone so * we can use the nid of the first page to all the others. */ mtc.nid = folio_nid(list_first_entry(&source, struct folio, lru)); /* * try to allocate from a different node but reuse this node * if there are no other online nodes to be used (e.g. we are * offlining a part of the only existing node) */ node_clear(mtc.nid, nmask); if (nodes_empty(nmask)) node_set(mtc.nid, nmask); ret = migrate_pages(&source, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG, NULL); if (ret) { list_for_each_entry(folio, &source, lru) { if (__ratelimit(&migrate_rs)) { pr_warn("migrating pfn %lx failed ret:%d\n", folio_pfn(folio), ret); dump_page(&folio->page, "migration failure"); } } putback_movable_pages(&source); } } } static int __init cmdline_parse_movable_node(char *p) { movable_node_enabled = true; return 0; } early_param("movable_node", cmdline_parse_movable_node); static int count_system_ram_pages_cb(unsigned long start_pfn, unsigned long nr_pages, void *data) { unsigned long *nr_system_ram_pages = data; *nr_system_ram_pages += nr_pages; return 0; } /* * Must be called with mem_hotplug_lock in write mode. */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { unsigned long pfn, managed_pages, system_ram_pages = 0; const unsigned long end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; const int node = zone_to_nid(zone); struct memory_notify mem_arg = { .start_pfn = start_pfn, .nr_pages = nr_pages, }; struct node_notify node_arg = { .nid = NUMA_NO_NODE, }; unsigned long flags; char *reason; int ret; unsigned long normal_pages = 0; enum zone_type zt; /* * {on,off}lining is constrained to full memory sections (or more * precisely to memory blocks from the user space POV). * memmap_on_memory is an exception because it reserves initial part * of the physical memory space for vmemmaps. That space is pageblock * aligned. */ if (WARN_ON_ONCE(!nr_pages || !pageblock_aligned(start_pfn) || !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined * via the hotplug path - online_pages() - as hotplugged memory has * no holes. This way, we don't have to worry about memory holes, * don't need pfn_valid() checks, and can avoid using * walk_system_ram_range() later. */ walk_system_ram_range(start_pfn, nr_pages, &system_ram_pages, count_system_ram_pages_cb); if (system_ram_pages != nr_pages) { ret = -EINVAL; reason = "memory holes"; goto failed_removal; } /* * We only support offlining of memory blocks managed by a single zone, * checked by calling code. This is just a sanity check that we might * want to remove in the future. */ if (WARN_ON_ONCE(page_zone(pfn_to_page(start_pfn)) != zone || page_zone(pfn_to_page(end_pfn - 1)) != zone)) { ret = -EINVAL; reason = "multizone range"; goto failed_removal; } /* * Disable pcplists so that page isolation cannot race with freeing * in a way that pages from isolated pageblock are left on pcplists. */ zone_pcp_disable(zone); lru_cache_disable(); /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, PB_ISOLATE_MODE_MEM_OFFLINE); if (ret) { reason = "failure to isolate range"; goto failed_removal_pcplists_disabled; } /* * Check whether the node will have no present pages after we offline * 'nr_pages' more. If so, we know that the node will become empty, and * so we will clear N_MEMORY for it. */ if (nr_pages >= pgdat->node_present_pages) { node_arg.nid = node; ret = node_notify(NODE_REMOVING_LAST_MEMORY, &node_arg); ret = notifier_to_errno(ret); if (ret) { reason = "node notifier failure"; goto failed_removal_isolated; } } ret = memory_notify(MEM_GOING_OFFLINE, &mem_arg); ret = notifier_to_errno(ret); if (ret) { reason = "notifier failure"; goto failed_removal_isolated; } do { pfn = start_pfn; do { /* * Historically we always checked for any signal and * can't limit it to fatal signals without eventually * breaking user space. */ if (signal_pending(current)) { ret = -EINTR; reason = "signal backoff"; goto failed_removal_isolated; } cond_resched(); ret = scan_movable_pages(pfn, end_pfn, &pfn); if (!ret) { /* * TODO: fatal migration failures should bail * out */ do_migrate_range(pfn, end_pfn); } } while (!ret); if (ret != -ENOENT) { reason = "unmovable page"; goto failed_removal_isolated; } /* * Dissolve free hugetlb folios in the memory block before doing * offlining actually in order to make hugetlbfs's object * counting consistent. */ ret = dissolve_free_hugetlb_folios(start_pfn, end_pfn); if (ret) { reason = "failure to dissolve huge pages"; goto failed_removal_isolated; } ret = test_pages_isolated(start_pfn, end_pfn, PB_ISOLATE_MODE_MEM_OFFLINE); } while (ret); /* Mark all sections offline and remove free pages from the buddy. */ managed_pages = __offline_isolated_pages(start_pfn, end_pfn); pr_debug("Offlined Pages %ld\n", nr_pages); /* * The memory sections are marked offline, and the pageblock flags * effectively stale; nobody should be touching them. Fixup the number * of isolated pageblocks, memory onlining will properly revert this. */ spin_lock_irqsave(&zone->lock, flags); zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages; spin_unlock_irqrestore(&zone->lock, flags); lru_cache_enable(); zone_pcp_enable(zone); /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -managed_pages); adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); /* * Check whether this operation removes the last normal memory from * the node. We do this before clearing N_MEMORY to avoid the possible * transient "!N_MEMORY && N_NORMAL_MEMORY" state. */ if (zone_idx(zone) <= ZONE_NORMAL) { for (zt = 0; zt <= ZONE_NORMAL; zt++) normal_pages += pgdat->node_zones[zt].present_pages; if (!normal_pages) node_clear_state(node, N_NORMAL_MEMORY); } /* * Make sure to mark the node as memory-less before rebuilding the zone * list. Otherwise this node would still appear in the fallback lists. */ if (node_arg.nid >= 0) node_clear_state(node, N_MEMORY); if (!populated_zone(zone)) { zone_pcp_reset(zone); build_all_zonelists(NULL); } if (node_arg.nid >= 0) { kcompactd_stop(node); kswapd_stop(node); /* Node went memoryless. Notify consumers */ node_notify(NODE_REMOVED_LAST_MEMORY, &node_arg); } writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &mem_arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); return 0; failed_removal_isolated: /* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn); memory_notify(MEM_CANCEL_OFFLINE, &mem_arg); if (node_arg.nid != NUMA_NO_NODE) node_notify(NODE_CANCEL_REMOVING_LAST_MEMORY, &node_arg); failed_removal_pcplists_disabled: lru_cache_enable(); zone_pcp_enable(zone); failed_removal: pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n", (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); return ret; } static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { int *nid = arg; *nid = mem->nid; if (unlikely(mem->state != MEM_OFFLINE)) { phys_addr_t beginpa, endpa; beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)); endpa = beginpa + memory_block_size_bytes() - 1; pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n", &beginpa, &endpa); return -EBUSY; } return 0; } static int count_memory_range_altmaps_cb(struct memory_block *mem, void *arg) { u64 *num_altmaps = (u64 *)arg; if (mem->altmap) *num_altmaps += 1; return 0; } static int check_cpu_on_node(int nid) { int cpu; for_each_present_cpu(cpu) { if (cpu_to_node(cpu) == nid) /* * the cpu on this node isn't removed, and we can't * offline this node. */ return -EBUSY; } return 0; } static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg) { int nid = *(int *)arg; /* * If a memory block belongs to multiple nodes, the stored nid is not * reliable. However, such blocks are always online (e.g., cannot get * offlined) and, therefore, are still spanned by the node. */ return mem->nid == nid ? -EEXIST : 0; } /** * try_offline_node * @nid: the node ID * * Offline a node if all memory sections and cpus of the node are removed. * * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call. */ void try_offline_node(int nid) { int rc; /* * If the node still spans pages (especially ZONE_DEVICE), don't * offline it. A node spans memory after move_pfn_range_to_zone(), * e.g., after the memory block was onlined. */ if (node_spanned_pages(nid)) return; /* * Especially offline memory blocks might not be spanned by the * node. They will get spanned by the node once they get onlined. * However, they link to the node in sysfs and can get onlined later. */ rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb); if (rc) return; if (check_cpu_on_node(nid)) return; /* * all memory/cpu of this node are removed, we can offline this * node now. */ node_set_offline(nid); unregister_node(nid); } EXPORT_SYMBOL(try_offline_node); static int memory_blocks_have_altmaps(u64 start, u64 size) { u64 num_memblocks = size / memory_block_size_bytes(); u64 num_altmaps = 0; if (!mhp_memmap_on_memory()) return 0; walk_memory_blocks(start, size, &num_altmaps, count_memory_range_altmaps_cb); if (num_altmaps == 0) return 0; if (WARN_ON_ONCE(num_memblocks != num_altmaps)) return -EINVAL; return 1; } static int try_remove_memory(u64 start, u64 size) { int rc, nid = NUMA_NO_NODE; BUG_ON(check_hotplug_memory_range(start, size)); /* * All memory blocks must be offlined before removing memory. Check * whether all memory blocks in question are offline and return error * if this is not the case. * * While at it, determine the nid. Note that if we'd have mixed nodes, * we'd only try to offline the last determined one -- which is good * enough for the cases we care about. */ rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb); if (rc) return rc; /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); mem_hotplug_begin(); rc = memory_blocks_have_altmaps(start, size); if (rc < 0) { mem_hotplug_done(); return rc; } else if (!rc) { /* * Memory block device removal under the device_hotplug_lock is * a barrier against racing online attempts. * No altmaps present, do the removal directly */ remove_memory_block_devices(start, size); arch_remove_memory(start, size, NULL, NULL); } else { /* all memblocks in the range have altmaps */ remove_memory_blocks_and_altmaps(start, size); } if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); release_mem_region_adjustable(start, size); if (nid != NUMA_NO_NODE) try_offline_node(nid); mem_hotplug_done(); return 0; } /** * __remove_memory - Remove memory if every memory block is offline * @start: physical address of the region to remove * @size: size of the region to remove * * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call, as required by * try_offline_node(). */ void __remove_memory(u64 start, u64 size) { /* * trigger BUG() if some memory is not offlined prior to calling this * function */ if (try_remove_memory(start, size)) BUG(); } /* * Remove memory if every memory block is offline, otherwise return -EBUSY is * some memory is not offline */ int remove_memory(u64 start, u64 size) { int rc; lock_device_hotplug(); rc = try_remove_memory(start, size); unlock_device_hotplug(); return rc; } EXPORT_SYMBOL_GPL(remove_memory); static int try_offline_memory_block(struct memory_block *mem, void *arg) { enum mmop online_type = MMOP_ONLINE_KERNEL; uint8_t **online_types = arg; struct page *page; int rc; /* * Sense the online_type via the zone of the memory block. Offlining * with multiple zones within one memory block will be rejected * by offlining code ... so we don't care about that. */ page = pfn_to_online_page(section_nr_to_pfn(mem->start_section_nr)); if (page && page_zonenum(page) == ZONE_MOVABLE) online_type = MMOP_ONLINE_MOVABLE; rc = device_offline(&mem->dev); /* * Default is MMOP_OFFLINE - change it only if offlining succeeded, * so try_reonline_memory_block() can do the right thing. */ if (!rc) **online_types = online_type; (*online_types)++; /* Ignore if already offline. */ return rc < 0 ? rc : 0; } static int try_reonline_memory_block(struct memory_block *mem, void *arg) { uint8_t **online_types = arg; int rc; if (**online_types != MMOP_OFFLINE) { mem->online_type = (enum mmop)**online_types; rc = device_online(&mem->dev); if (rc < 0) pr_warn("%s: Failed to re-online memory: %d", __func__, rc); } /* Continue processing all remaining memory blocks. */ (*online_types)++; return 0; } /* * Try to offline and remove memory. Might take a long time to finish in case * memory is still in use. Primarily useful for memory devices that logically * unplugged all memory (so it's no longer in use) and want to offline + remove * that memory. */ int offline_and_remove_memory(u64 start, u64 size) { struct range range = { .start = start, .end = start + size - 1, }; return offline_and_remove_memory_ranges(&range, 1); } EXPORT_SYMBOL_GPL(offline_and_remove_memory); /** * offline_and_remove_memory_ranges - offline and remove multiple memory ranges * @ranges: array of physical address ranges to offline and remove * @nr_ranges: number of entries in @ranges * * Offline and remove several memory ranges as one operation, serialized * against other hotplug operations by a single lock_device_hotplug(). * * This offlines all ranges before removing any of them. If offlining any * range fails, the entire process is reverted and nothing is removed. * This provides a fully atomic semantic for unplugging an entire device. * * Each range must be memory-block aligned in start and size. * * Return: 0 on success, negative errno on failure (never positive). On * failure no range has been removed. */ int offline_and_remove_memory_ranges(const struct range *ranges, unsigned int nr_ranges) { unsigned long mb_count = 0; uint8_t *online_types, *tmp; unsigned int i; int rc = 0; if (!ranges || !nr_ranges) return -EINVAL; for (i = 0; i < nr_ranges; i++) { const u64 start = ranges[i].start; const u64 size = range_len(&ranges[i]); if (!IS_ALIGNED(start, memory_block_size_bytes()) || !IS_ALIGNED(size, memory_block_size_bytes()) || !size) return -EINVAL; mb_count += size / memory_block_size_bytes(); } /* * Remember the old online type of every memory block across all ranges, * so we can revert if offlining a later block fails. All entries start * as MMOP_OFFLINE so blocks we never touched are skipped on rollback. */ online_types = kmalloc_array(mb_count, sizeof(*online_types), GFP_KERNEL); if (!online_types) return -ENOMEM; memset(online_types, MMOP_OFFLINE, mb_count); lock_device_hotplug(); /* * Phase 1: offline every block in every range. An already-offline * block folds to success, so out-of-band offlining never blocks unplug. */ tmp = online_types; for (i = 0; i < nr_ranges; i++) { rc = walk_memory_blocks(ranges[i].start, range_len(&ranges[i]), &tmp, try_offline_memory_block); if (rc) break; } /* If any failure occurred at all, rollback any changes and bail */ if (rc) { tmp = online_types; for (i = 0; i < nr_ranges; i++) walk_memory_blocks(ranges[i].start, range_len(&ranges[i]), &tmp, try_reonline_memory_block); goto out_unlock; } /* Phase 2: Remove. This should never fail holding the hotplug lock */ for (i = 0; i < nr_ranges; i++) WARN_ON_ONCE(try_remove_memory(ranges[i].start, range_len(&ranges[i]))); out_unlock: unlock_device_hotplug(); kfree(online_types); return rc; } EXPORT_SYMBOL_GPL(offline_and_remove_memory_ranges); #endif /* CONFIG_MEMORY_HOTREMOVE */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* handling of writes to regular files and writing back to the server * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/netfs.h> #include <trace/events/netfs.h> #include "internal.h" /* * completion of write to server */ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len) { _enter("{%llx:%llu},{%x @%llx}", vnode->fid.vid, vnode->fid.vnode, len, start); afs_prune_wb_keys(vnode); _leave(""); } /* * Find a key to use for the writeback. We cached the keys used to author the * writes on the vnode. wreq->netfs_priv2 will contain the last writeback key * record used or NULL and we need to start from there if it's set. * wreq->netfs_priv will be set to the key itself or NULL. */ static void afs_get_writeback_key(struct netfs_io_request *wreq) { struct afs_wb_key *wbk, *old = wreq->netfs_priv2; struct afs_vnode *vnode = AFS_FS_I(wreq->inode); key_put(wreq->netfs_priv); wreq->netfs_priv = NULL; wreq->netfs_priv2 = NULL; spin_lock(&vnode->wb_lock); if (old) wbk = list_next_entry(old, vnode_link); else wbk = list_first_entry(&vnode->wb_keys, struct afs_wb_key, vnode_link); list_for_each_entry_from(wbk, &vnode->wb_keys, vnode_link) { _debug("wbk %u", key_serial(wbk->key)); if (key_validate(wbk->key) == 0) { refcount_inc(&wbk->usage); wreq->netfs_priv = key_get(wbk->key); wreq->netfs_priv2 = wbk; _debug("USE WB KEY %u", key_serial(wbk->key)); break; } } spin_unlock(&vnode->wb_lock); afs_put_wb_key(old); } static void afs_store_data_success(struct afs_operation *op) { struct afs_vnode *vnode = op->file[0].vnode; op->ctime = op->file[0].scb.status.mtime_client; afs_vnode_commit_status(op, &op->file[0]); if (!afs_op_error(op)) { afs_pages_written_back(vnode, op->store.pos, op->store.size); afs_stat_v(vnode, n_stores); atomic_long_add(op->store.size, &afs_v2net(vnode)->n_store_bytes); } } static const struct afs_operation_ops afs_store_data_operation = { .issue_afs_rpc = afs_fs_store_data, .issue_yfs_rpc = yfs_fs_store_data, .success = afs_store_data_success, }; /* * Prepare a subrequest to write to the server. This sets the max_len * parameter. */ void afs_prepare_write(struct netfs_io_subrequest *subreq) { struct netfs_io_stream *stream = &subreq->rreq->io_streams[subreq->stream_nr]; //if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) // subreq->max_len = 512 * 1024; //else stream->sreq_max_len = 256 * 1024 * 1024; } /* * Issue a subrequest to write to the server. */ static void afs_issue_write_worker(struct work_struct *work) { struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work); struct netfs_io_request *wreq = subreq->rreq; struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(wreq->inode); unsigned long long pos = subreq->start + subreq->transferred; size_t len = subreq->len - subreq->transferred; int ret = -ENOKEY; _enter("R=%x[%x],%s{%llx:%llu.%u},%llx,%zx", wreq->debug_id, subreq->debug_index, vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, pos, len); #if 0 // Error injection if (subreq->debug_index == 3) return netfs_write_subrequest_terminated(subreq, -ENOANO); if (!subreq->retry_count) { set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); return netfs_write_subrequest_terminated(subreq, -EAGAIN); } #endif op = afs_alloc_operation(wreq->netfs_priv, vnode->volume); if (IS_ERR(op)) return netfs_write_subrequest_terminated(subreq, -EAGAIN); afs_op_set_vnode(op, 0, vnode); op->file[0].dv_delta = 1; op->file[0].modification = true; op->store.pos = pos; op->store.size = len; op->flags |= AFS_OPERATION_UNINTR; op->ops = &afs_store_data_operation; afs_begin_vnode_operation(op); op->store.write_iter = &subreq->io_iter; op->store.i_size = umax(pos + len, netfs_read_remote_i_size(&vnode->netfs.inode)); op->mtime = inode_get_mtime(&vnode->netfs.inode); afs_wait_for_operation(op); ret = afs_put_operation(op); switch (ret) { case 0: __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); break; case -EACCES: case -EPERM: case -ENOKEY: case -EKEYEXPIRED: case -EKEYREJECTED: case -EKEYREVOKED: /* If there are more keys we can try, use the retry algorithm * to rotate the keys. */ if (wreq->netfs_priv2) set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); break; } netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len); } void afs_issue_write(struct netfs_io_subrequest *subreq) { subreq->work.func = afs_issue_write_worker; if (!queue_work(system_dfl_wq, &subreq->work)) WARN_ON_ONCE(1); } /* * Writeback calls this when it finds a folio that needs uploading. This isn't * called if writeback only has copy-to-cache to deal with. */ void afs_begin_writeback(struct netfs_io_request *wreq) { if (S_ISREG(wreq->inode->i_mode)) afs_get_writeback_key(wreq); } /* * Prepare to retry the writes in request. Use this to try rotating the * available writeback keys. */ void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *stream) { struct netfs_io_subrequest *subreq = list_first_entry(&stream->subrequests, struct netfs_io_subrequest, rreq_link); switch (wreq->origin) { case NETFS_READAHEAD: case NETFS_READPAGE: case NETFS_READ_GAPS: case NETFS_READ_SINGLE: case NETFS_READ_FOR_WRITE: case NETFS_UNBUFFERED_READ: case NETFS_DIO_READ: return; default: break; } switch (subreq->error) { case -EACCES: case -EPERM: case -ENOKEY: case -EKEYEXPIRED: case -EKEYREJECTED: case -EKEYREVOKED: afs_get_writeback_key(wreq); if (!wreq->netfs_priv) stream->failed = true; break; } } /* * write some of the pending data back to the server */ int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); int ret; /* We have to be careful as we can end up racing with setattr() * truncating the pagecache since the caller doesn't take a lock here * to prevent it. */ if (wbc->sync_mode == WB_SYNC_ALL) down_read(&vnode->validate_lock); else if (!down_read_trylock(&vnode->validate_lock)) return 0; ret = netfs_writepages(mapping, wbc); up_read(&vnode->validate_lock); return ret; } /* * flush any dirty pages for this process, and check for write errors. * - the return status from this call provides a reliable indication of * whether any write errors occurred for this process. */ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); struct afs_file *af = file->private_data; int ret; _enter("{%llx:%llu},{n=%pD},%d", vnode->fid.vid, vnode->fid.vnode, file, datasync); ret = afs_validate(vnode, af->key); if (ret < 0) return ret; return file_write_and_wait_range(file, start, end); } /* * notification that a previously read-only page is about to become writable * - if it returns an error, the caller will deliver a bus error signal */ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0) return VM_FAULT_SIGBUS; return netfs_page_mkwrite(vmf, NULL); } /* * Prune the keys cached for writeback. The caller must hold vnode->wb_lock. */ void afs_prune_wb_keys(struct afs_vnode *vnode) { LIST_HEAD(graveyard); struct afs_wb_key *wbk, *tmp; /* Discard unused keys */ spin_lock(&vnode->wb_lock); if (!mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_WRITEBACK) && !mapping_tagged(&vnode->netfs.inode.i_data, PAGECACHE_TAG_DIRTY)) { list_for_each_entry_safe(wbk, tmp, &vnode->wb_keys, vnode_link) { if (refcount_read(&wbk->usage) == 1) list_move(&wbk->vnode_link, &graveyard); } } spin_unlock(&vnode->wb_lock); while (!list_empty(&graveyard)) { wbk = list_entry(graveyard.next, struct afs_wb_key, vnode_link); list_del(&wbk->vnode_link); afs_put_wb_key(wbk); } } |
| 2285 1251 1150 1150 1150 1203 58 1271 42 1238 1238 1236 3223 3231 3239 3228 28 6 81 3240 3240 3274 3106 3271 980 3227 1430 1429 3279 3274 131 3270 978 3228 6399 2 6412 6413 6401 2009 2 6414 15 15 15 15 2 2 961 956 142 950 950 950 946 1721 1658 880 795 1 794 1437 1444 1443 900 1415 1077 686 1444 2735 2213 40 507 795 1439 1791 2734 6114 6124 6125 4613 91 4535 17 17 1 17 12 9 9 9 10 10 9 2 2 2 2 2 25 25 25 25 25 25 1718 1720 1352 1644 1722 14 14 1722 17 1721 1 1723 20 1726 16 5 15 8 1 7 2 26 2 14 24 23 1715 1723 1724 141 1 2 43 10 199 201 201 201 201 39 6 6 4 2 1 1 161 3874 3279 3873 3871 1425 3663 37 2 1151 219 3760 1120 3650 1237 122 122 121 121 121 1 121 376 164 376 172 135 173 10 169 173 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/folio.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * Folio LRU helpers: add/remove folios from LRU lists, batching, * activation/deactivation, and page cache release paths. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/folio_batch.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #include "page_alloc.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) lruvec_unlock_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; struct folio_batch free_fbatch; bool is_lru_add = (move_fn == lru_add); /* * If we're adding to the LRU, preemptively filter dead folios. Use * this dedicated folio batch for temp storage and deferred cleanup. */ if (is_lru_add) folio_batch_init(&free_fbatch); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; /* block memcg migration while the folio moves between lru */ if (!is_lru_add && !folio_test_clear_lru(folio)) continue; /* * Filter dead folios by moving them from the add batch to the temp * batch for freeing after this loop. * * We're bypassing normal cleanup. Clear flags that are not * applicable to dead folios. * * Since the folio may be part of a huge page, unqueue from * deferred split list to avoid a dangling list entry. */ if (is_lru_add && folio_ref_freeze(folio, 1)) { __folio_clear_active(folio); __folio_clear_unevictable(folio); folio_unqueue_deferred_split(folio); fbatch->folios[i] = NULL; folio_batch_add(&free_fbatch, folio); continue; } folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) lruvec_unlock_irqrestore(lruvec, flags); /* Cleanup filtered dead folios. */ if (is_lru_add) { mem_cgroup_uncharge_folios(&free_fbatch); free_unref_folios(&free_fbatch); } folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ offsetof(struct cpu_fbatches, op) >= \ offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_move_tail); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_activate); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); lruvec_unlock_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); if (folio_test_unevictable(folio)) return; /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); return; } do { if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio); return; } new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); } static bool lru_gen_clear_refs(struct folio *folio) { int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); unsigned long seq; if (gen < 0) return true; set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS | BIT(PG_workingset), 0); rcu_read_lock(); seq = READ_ONCE(folio_lruvec(folio)->lrugen.min_seq[type]); rcu_read_unlock(); /* whether can do without shuffling under the LRU lock */ return gen == lru_gen_from_seq(seq); } #else /* !CONFIG_LRU_GEN */ static void lru_gen_inc_refs(struct folio *folio) { } static bool lru_gen_clear_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (folio_test_dropbehind(folio)) return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * For refaulted workingset folios, set PG_active so they * can be added to active generations. * For prefaulted file folios, folio_mark_accessed() sets * PG_referenced so lru_gen_folio_seq() places them into * the second oldest generation. */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) { if (folio_test_workingset(folio)) folio_set_active(folio); else if (!folio_test_referenced(folio)) folio_mark_accessed(folio); } folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropriate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); if (lru_gen_enabled()) lru_gen_clear_refs(folio); else folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; unsigned int nr_folios = folio_batch_count(fbatch); if (nr_folios) { folio_batch_move_lru(fbatch, lru_add); trace_mm_lru_add_drain_tp(cpu, nr_folios); } fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return data_race(folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu)) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; trace_mm_lru_add_drain_all_tp(force_all_cpus); /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); /* It helps everyone if we do our own local drain immediately. */ lru_add_drain(); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ /** * lru_cache_drain_for_folio() - drain LRU caches if the caches might hold * folio references * @folio: The folio. * @extra_refs: Extra folio references held by the caller. * @drained: Drain status for batch folio processing. * * Drain LRU caches if the caches might hold folio references. Start * with a local LRU cache drain, to then drain LRU caches on all CPUs if * local draining was insufficient. * * This function detects LRU cache references by comparing the folio refcount * with the sum of the expected folio refcount + extra references held by the * caller. Note that we cannot rely on PG_lru to reliably detect all LRU * cache references, and there are rare scenarios (concurrent folio (un)mapping) * where this function might miss detecting LRU cache references. * * If @drained is not NULL, the function will avoid re-draining LRU caches * when processing multiple folios in a row. In that case, the variable * @drained points at must be initialized to LRU_CACHE_NOT_DRAINED before * the first invocation by the caller. */ void lru_cache_drain_for_folio(const struct folio *folio, unsigned int extra_refs, enum lru_cache_drained *drained) { if (!folio_may_be_lru_cached(folio)) return; if (!drained || *drained == LRU_CACHE_NOT_DRAINED) { if (folio_ref_count(folio) == folio_expected_ref_count(folio) + extra_refs) return; lru_add_drain(); if (drained) *drained = LRU_CACHE_DRAINED; } if (!drained || *drained == LRU_CACHE_DRAINED) { if (folio_ref_count(folio) == folio_expected_ref_count(folio) + extra_refs) return; lru_add_drain_all(); if (drained) *drained = LRU_CACHE_DRAINED_ALL; } } atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; /* Folio batch entry may have been preemptively removed during drain. */ if (!folio) continue; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { lruvec_unlock_irqrestore(lruvec, flags); lruvec = NULL; } if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { lruvec_unlock_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) lruvec_unlock_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[FOLIO_BATCH_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } #ifdef CONFIG_MEMCG static void lruvec_reparent_lru(struct lruvec *child_lruvec, struct lruvec *parent_lruvec, enum lru_list lru, int nid) { int zid; struct zone *zone; if (lru != LRU_UNEVICTABLE) list_splice_tail_init(&child_lruvec->lists[lru], &parent_lruvec->lists[lru]); for_each_managed_zone_pgdat(zone, NODE_DATA(nid), zid, MAX_NR_ZONES - 1) { unsigned long size = mem_cgroup_get_zone_lru_size(child_lruvec, lru, zid); if (!size) continue; /* * The folios are accounted to the parent from now on, so the * size has to be moved, not just copied. Leaving it behind * makes the dying child describe folios it no longer owns. */ mem_cgroup_update_lru_size(parent_lruvec, lru, zid, size); mem_cgroup_update_lru_size(child_lruvec, lru, zid, -(long)size); } } void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid) { enum lru_list lru; struct lruvec *child_lruvec, *parent_lruvec; child_lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); parent_lruvec = mem_cgroup_lruvec(parent, NODE_DATA(nid)); for_each_lru(lru) lruvec_reparent_lru(child_lruvec, parent_lruvec, lru, nid); } #endif |
| 14 14 13 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 | // SPDX-License-Identifier: GPL-2.0 /* * fault injection support for nvme. * * Copyright (c) 2018, Oracle and/or its affiliates */ #include <linux/moduleparam.h> #include <linux/debugfs.h> #include "nvme.h" static DECLARE_FAULT_ATTR(fail_default_attr); /* optional fault injection attributes boot time option: * nvme_core.fail_request=<interval>,<probability>,<space>,<times> */ static char *fail_request; module_param(fail_request, charp, 0000); void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, const char *dev_name) { struct dentry *dir, *parent; struct fault_attr *attr = &fault_inj->attr; /* set default fault injection attribute */ if (fail_request) setup_fault_attr(&fail_default_attr, fail_request); /* create debugfs directory and attribute */ parent = debugfs_create_dir(dev_name, NULL); if (IS_ERR(parent)) { pr_warn("%s: failed to create debugfs directory\n", dev_name); return; } *attr = fail_default_attr; dir = fault_create_debugfs_attr("fault_inject", parent, attr); if (IS_ERR(dir)) { pr_warn("%s: failed to create debugfs attr\n", dev_name); debugfs_remove_recursive(parent); return; } fault_inj->parent = parent; /* create debugfs for status code and dont_retry */ fault_inj->status = NVME_SC_INVALID_OPCODE; fault_inj->dont_retry = true; debugfs_create_x16("status", 0600, dir, &fault_inj->status); debugfs_create_bool("dont_retry", 0600, dir, &fault_inj->dont_retry); } void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject) { /* remove debugfs directories */ debugfs_remove_recursive(fault_inject->parent); } void nvme_should_fail(struct request *req) { struct gendisk *disk = req->q->disk; struct nvme_fault_inject *fault_inject = NULL; u16 status; if (disk) { struct nvme_ns *ns = disk->private_data; if (ns) fault_inject = &ns->fault_inject; else WARN_ONCE(1, "No namespace found for request\n"); } else { fault_inject = &nvme_req(req)->ctrl->fault_inject; } if (fault_inject && should_fail(&fault_inject->attr, 1)) { /* inject status code and DNR bit */ status = fault_inject->status; if (fault_inject->dont_retry) status |= NVME_STATUS_DNR; nvme_req(req)->status = status; } } EXPORT_SYMBOL_GPL(nvme_should_fail); |
| 3620 2534 1098 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __LICENSE_H #define __LICENSE_H static inline int license_is_gpl_compatible(const char *license) { return (strcmp(license, "GPL") == 0 || strcmp(license, "GPL v2") == 0 || strcmp(license, "GPL and additional rights") == 0 || strcmp(license, "Dual BSD/GPL") == 0 || strcmp(license, "Dual MIT/GPL") == 0 || strcmp(license, "Dual MPL/GPL") == 0); } #endif |
| 1 1 3 2 1 1 3 1 2 25 25 25 23 23 4 4 1 1 2 1 1 1 1 1 3 1 1 1 6 1 3 4 3 1 1 1 9 9 3 2 4 4 3 2 5 1 2 5 4 1 1 1 1 4 1 2 1 2 1 1 5 5 2 1 2 1 1 1 3 1 1 1 2 4 1 1 2 2 8 3 2 3 2 4 4 1 1 2 2 2 2 3 1 2 1 1 4 2 1 1 4 2 1 1 4 2 1 1 1 1 1 1 1 1 5 1 2 1 1 4 1 2 1 405 106 299 299 28 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> * * Vendor commands implementation based on net/wireless/nl80211.c * which is: * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ #include <net/genetlink.h> #include <linux/nfc.h> #include <linux/slab.h> #include "nfc.h" #include "llcp.h" static const struct genl_multicast_group nfc_genl_mcgrps[] = { { .name = NFC_GENL_MCAST_EVENT_NAME, }, }; static struct genl_family nfc_genl_family; static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_DEVICE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING, .len = NFC_DEVICE_NAME_MAXSIZE }, [NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 }, [NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, [NFC_ATTR_IM_PROTOCOLS] = { .type = NLA_U32 }, [NFC_ATTR_TM_PROTOCOLS] = { .type = NLA_U32 }, [NFC_ATTR_LLC_PARAM_LTO] = { .type = NLA_U8 }, [NFC_ATTR_LLC_PARAM_RW] = { .type = NLA_U8 }, [NFC_ATTR_LLC_PARAM_MIUX] = { .type = NLA_U16 }, [NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED }, [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, }; static const struct nla_policy nfc_sdp_genl_policy[NFC_SDP_ATTR_MAX + 1] = { [NFC_SDP_ATTR_URI] = { .type = NLA_STRING, .len = U8_MAX - 4 }, [NFC_SDP_ATTR_SAP] = { .type = NLA_U8 }, }; static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, struct netlink_callback *cb, int flags) { void *hdr; hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &nfc_genl_family, flags, NFC_CMD_GET_TARGET); if (!hdr) return -EMSGSIZE; genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, target->supported_protocols) || nla_put_u16(msg, NFC_ATTR_TARGET_SENS_RES, target->sens_res) || nla_put_u8(msg, NFC_ATTR_TARGET_SEL_RES, target->sel_res)) goto nla_put_failure; if (target->nfcid1_len > 0 && nla_put(msg, NFC_ATTR_TARGET_NFCID1, target->nfcid1_len, target->nfcid1)) goto nla_put_failure; if (target->sensb_res_len > 0 && nla_put(msg, NFC_ATTR_TARGET_SENSB_RES, target->sensb_res_len, target->sensb_res)) goto nla_put_failure; if (target->sensf_res_len > 0 && nla_put(msg, NFC_ATTR_TARGET_SENSF_RES, target->sensf_res_len, target->sensf_res)) goto nla_put_failure; if (target->is_iso15693) { if (nla_put_u8(msg, NFC_ATTR_TARGET_ISO15693_DSFID, target->iso15693_dsfid) || nla_put(msg, NFC_ATTR_TARGET_ISO15693_UID, sizeof(target->iso15693_uid), target->iso15693_uid)) goto nla_put_failure; } if (target->ats_len > 0 && nla_put(msg, NFC_ATTR_TARGET_ATS, target->ats_len, target->ats)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct nfc_dev *dev; u32 idx; if (!info->info.attrs[NFC_ATTR_DEVICE_INDEX]) return ERR_PTR(-EINVAL); idx = nla_get_u32(info->info.attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return ERR_PTR(-ENODEV); return dev; } static int nfc_genl_dump_targets(struct sk_buff *skb, struct netlink_callback *cb) { int i = cb->args[0]; struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; int rc; if (!dev) { dev = __get_device_from_cb(cb); if (IS_ERR(dev)) return PTR_ERR(dev); cb->args[1] = (long) dev; } device_lock(&dev->dev); cb->seq = dev->targets_generation; while (i < dev->n_targets) { rc = nfc_genl_send_target(skb, &dev->targets[i], cb, NLM_F_MULTI); if (rc < 0) break; i++; } device_unlock(&dev->dev); cb->args[0] = i; return skb->len; } static int nfc_genl_dump_targets_done(struct netlink_callback *cb) { struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; if (dev) nfc_put_device(dev); return 0; } int nfc_genl_targets_found(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; dev->genl_data.poll_req_portid = 0; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TARGETS_FOUND); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TARGET_LOST); if (!hdr) goto free_msg; if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target_idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TM_ACTIVATED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; if (nla_put_u32(msg, NFC_ATTR_TM_PROTOCOLS, protocol)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_tm_deactivated(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_TM_DEACTIVATED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_setup_device_added(struct nfc_dev *dev, struct sk_buff *msg) { if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) || nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up) || nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode)) return -1; return 0; } int nfc_genl_device_added(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_DEVICE_ADDED); if (!hdr) goto free_msg; if (nfc_genl_setup_device_added(dev, msg)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_device_removed(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_DEVICE_REMOVED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list) { struct sk_buff *msg; struct nlattr *sdp_attr, *uri_attr; struct nfc_llcp_sdp_tlv *sdres; struct hlist_node *n; void *hdr; int rc = -EMSGSIZE; int i; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_LLC_SDRES); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; sdp_attr = nla_nest_start_noflag(msg, NFC_ATTR_LLC_SDP); if (sdp_attr == NULL) { rc = -ENOMEM; goto nla_put_failure; } i = 1; hlist_for_each_entry_safe(sdres, n, sdres_list, node) { pr_debug("uri: %s, sap: %d\n", sdres->uri, sdres->sap); uri_attr = nla_nest_start_noflag(msg, i++); if (uri_attr == NULL) { rc = -ENOMEM; goto nla_put_failure; } if (nla_put_u8(msg, NFC_SDP_ATTR_SAP, sdres->sap)) goto nla_put_failure; if (nla_put_string(msg, NFC_SDP_ATTR_URI, sdres->uri)) goto nla_put_failure; nla_nest_end(msg, uri_attr); hlist_del(&sdres->node); nfc_llcp_free_sdp_tlv(sdres); } nla_nest_end(msg, sdp_attr); genlmsg_end(msg, hdr); return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); nla_put_failure: free_msg: nlmsg_free(msg); nfc_llcp_free_sdp_tlv_list(sdres_list); return rc; } int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_ADDED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, type)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_REMOVED); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction) { struct nfc_se *se; struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_TRANSACTION); if (!hdr) goto free_msg; se = nfc_find_se(dev, se_idx); if (!se) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type) || nla_put(msg, NFC_ATTR_SE_AID, evt_transaction->aid_len, evt_transaction->aid) || nla_put(msg, NFC_ATTR_SE_PARAMS, evt_transaction->params_len, evt_transaction->params)) goto nla_put_failure; /* evt_transaction is no more used */ devm_kfree(&dev->dev, evt_transaction); genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: /* evt_transaction is no more used */ devm_kfree(&dev->dev, evt_transaction); nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_se_connectivity(struct nfc_dev *dev, u8 se_idx) { const struct nfc_se *se; struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_EVENT_SE_CONNECTIVITY); if (!hdr) goto free_msg; se = nfc_find_se(dev, se_idx); if (!se) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, flags, NFC_CMD_GET_DEVICE); if (!hdr) return -EMSGSIZE; if (cb) genl_dump_check_consistent(cb, hdr); if (nfc_genl_setup_device_added(dev, msg)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nfc_genl_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; bool first_call = false; if (!iter) { first_call = true; iter = kmalloc_obj(struct class_dev_iter); if (!iter) return -ENOMEM; cb->args[0] = (long) iter; } mutex_lock(&nfc_devlist_mutex); cb->seq = nfc_devlist_generation; if (first_call) { nfc_device_iter_init(iter); dev = nfc_device_iter_next(iter); } while (dev) { int rc; rc = nfc_genl_send_device(skb, dev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (rc < 0) break; dev = nfc_device_iter_next(iter); } mutex_unlock(&nfc_devlist_mutex); cb->args[1] = (long) dev; return skb->len; } static int nfc_genl_dump_devices_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; if (iter) { nfc_device_iter_exit(iter); kfree(iter); } return 0; } int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode) { struct sk_buff *msg; void *hdr; pr_debug("DEP link is up\n"); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_DEP_LINK_UP); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; if (rf_mode == NFC_RF_INITIATOR && nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target_idx)) goto nla_put_failure; if (nla_put_u8(msg, NFC_ATTR_COMM_MODE, comm_mode) || nla_put_u8(msg, NFC_ATTR_RF_MODE, rf_mode)) goto nla_put_failure; genlmsg_end(msg, hdr); dev->dep_link_up = true; genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } int nfc_genl_dep_link_down_event(struct nfc_dev *dev) { struct sk_buff *msg; void *hdr; pr_debug("DEP link is down\n"); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_DEP_LINK_DOWN); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_get_device(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct nfc_dev *dev; u32 idx; int rc = -ENOBUFS; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; goto out_putdev; } rc = nfc_genl_send_device(msg, dev, info->snd_portid, info->snd_seq, NULL, 0); if (rc < 0) goto out_free; nfc_put_device(dev); return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); out_putdev: nfc_put_device(dev); return rc; } static int nfc_genl_dev_up(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dev_up(dev); nfc_put_device(dev); return rc; } static int nfc_genl_dev_down(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dev_down(dev); nfc_put_device(dev); return rc; } static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; u32 im_protocols = 0, tm_protocols = 0; pr_debug("Poll start\n"); if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || ((!info->attrs[NFC_ATTR_IM_PROTOCOLS] && !info->attrs[NFC_ATTR_PROTOCOLS]) && !info->attrs[NFC_ATTR_TM_PROTOCOLS])) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); if (info->attrs[NFC_ATTR_TM_PROTOCOLS]) tm_protocols = nla_get_u32(info->attrs[NFC_ATTR_TM_PROTOCOLS]); if (info->attrs[NFC_ATTR_IM_PROTOCOLS]) im_protocols = nla_get_u32(info->attrs[NFC_ATTR_IM_PROTOCOLS]); else if (info->attrs[NFC_ATTR_PROTOCOLS]) im_protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; mutex_lock(&dev->genl_data.genl_data_mutex); rc = nfc_start_poll(dev, im_protocols, tm_protocols); if (!rc) dev->genl_data.poll_req_portid = info->snd_portid; mutex_unlock(&dev->genl_data.genl_data_mutex); nfc_put_device(dev); return rc; } static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); if (!dev->polling) { device_unlock(&dev->dev); nfc_put_device(dev); return -EINVAL; } device_unlock(&dev->dev); mutex_lock(&dev->genl_data.genl_data_mutex); if (dev->genl_data.poll_req_portid != info->snd_portid) { rc = -EBUSY; goto out; } rc = nfc_stop_poll(dev); dev->genl_data.poll_req_portid = 0; out: mutex_unlock(&dev->genl_data.genl_data_mutex); nfc_put_device(dev); return rc; } static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; u32 device_idx, target_idx, protocol; int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_TARGET_INDEX] || !info->attrs[NFC_ATTR_PROTOCOLS]) return -EINVAL; device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(device_idx); if (!dev) return -ENODEV; target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); protocol = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); nfc_deactivate_target(dev, target_idx, NFC_TARGET_MODE_SLEEP); rc = nfc_activate_target(dev, target_idx, protocol); nfc_put_device(dev); return rc; } static int nfc_genl_deactivate_target(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; u32 device_idx, target_idx; int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_TARGET_INDEX]) return -EINVAL; device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(device_idx); if (!dev) return -ENODEV; target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); rc = nfc_deactivate_target(dev, target_idx, NFC_TARGET_MODE_SLEEP); nfc_put_device(dev); return rc; } static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc, tgt_idx; u32 idx; u8 comm; pr_debug("DEP link up\n"); if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_COMM_MODE]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); if (!info->attrs[NFC_ATTR_TARGET_INDEX]) tgt_idx = NFC_TARGET_IDX_ANY; else tgt_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); comm = nla_get_u8(info->attrs[NFC_ATTR_COMM_MODE]); if (comm != NFC_COMM_ACTIVE && comm != NFC_COMM_PASSIVE) return -EINVAL; dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dep_link_up(dev, tgt_idx, comm); nfc_put_device(dev); return rc; } static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_dep_link_down(dev); nfc_put_device(dev); return rc; } static int nfc_genl_send_params(struct sk_buff *msg, struct nfc_llcp_local *local, u32 portid, u32 seq) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, 0, NFC_CMD_LLC_GET_PARAMS); if (!hdr) return -EMSGSIZE; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, local->dev->idx) || nla_put_u8(msg, NFC_ATTR_LLC_PARAM_LTO, local->lto) || nla_put_u8(msg, NFC_ATTR_LLC_PARAM_RW, local->rw) || nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct nfc_llcp_local *local; int rc = 0; struct sk_buff *msg = NULL; u32 idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); local = nfc_llcp_find_local(dev); if (!local) { rc = -ENODEV; goto exit; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; goto put_local; } rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); put_local: nfc_llcp_local_put(local); exit: device_unlock(&dev->dev); nfc_put_device(dev); if (rc < 0) { if (msg) nlmsg_free(msg); return rc; } return genlmsg_reply(msg, info); } static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct nfc_llcp_local *local; u8 rw = 0; u16 miux = 0; u32 idx; int rc = 0; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || (!info->attrs[NFC_ATTR_LLC_PARAM_LTO] && !info->attrs[NFC_ATTR_LLC_PARAM_RW] && !info->attrs[NFC_ATTR_LLC_PARAM_MIUX])) return -EINVAL; if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) { rw = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_RW]); if (rw > LLCP_MAX_RW) return -EINVAL; } if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) { miux = nla_get_u16(info->attrs[NFC_ATTR_LLC_PARAM_MIUX]); if (miux > LLCP_MAX_MIUX) return -EINVAL; } idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); local = nfc_llcp_find_local(dev); if (!local) { rc = -ENODEV; goto exit; } if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { if (dev->dep_link_up) { rc = -EINPROGRESS; goto put_local; } local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); } if (info->attrs[NFC_ATTR_LLC_PARAM_RW]) local->rw = rw; if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) local->miux = cpu_to_be16(miux); put_local: nfc_llcp_local_put(local); exit: device_unlock(&dev->dev); nfc_put_device(dev); return rc; } static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct nfc_llcp_local *local; struct nlattr *attr, *sdp_attrs[NFC_SDP_ATTR_MAX+1]; u32 idx; u8 tid; char *uri; int rc = 0, rem; size_t uri_len, tlvs_len; struct hlist_head sdreq_list; struct nfc_llcp_sdp_tlv *sdreq; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_LLC_SDP]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; device_lock(&dev->dev); if (dev->dep_link_up == false) { rc = -ENOLINK; goto exit; } local = nfc_llcp_find_local(dev); if (!local) { rc = -ENODEV; goto exit; } INIT_HLIST_HEAD(&sdreq_list); tlvs_len = 0; nla_for_each_nested(attr, info->attrs[NFC_ATTR_LLC_SDP], rem) { rc = nla_parse_nested_deprecated(sdp_attrs, NFC_SDP_ATTR_MAX, attr, nfc_sdp_genl_policy, info->extack); if (rc != 0) { rc = -EINVAL; goto put_local; } if (!sdp_attrs[NFC_SDP_ATTR_URI]) continue; uri_len = nla_len(sdp_attrs[NFC_SDP_ATTR_URI]); if (uri_len == 0) continue; uri = nla_data(sdp_attrs[NFC_SDP_ATTR_URI]); if (*uri == 0) continue; tid = local->sdreq_next_tid++; sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len); if (sdreq == NULL) { rc = -ENOMEM; goto put_local; } tlvs_len += sdreq->tlv_len; hlist_add_head(&sdreq->node, &sdreq_list); } if (hlist_empty(&sdreq_list)) { rc = -EINVAL; goto put_local; } rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len); put_local: nfc_llcp_local_put(local); exit: device_unlock(&dev->dev); nfc_put_device(dev); return rc; } static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx; char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1]; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; nla_strscpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME], sizeof(firmware_name)); rc = nfc_fw_download(dev, firmware_name); nfc_put_device(dev); return rc; } int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result) { struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_FW_DOWNLOAD); if (!hdr) goto free_msg; if (nla_put_string(msg, NFC_ATTR_FIRMWARE_NAME, firmware_name) || nla_put_u32(msg, NFC_ATTR_FIRMWARE_DOWNLOAD_STATUS, result) || nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; nla_put_failure: free_msg: nlmsg_free(msg); return -EMSGSIZE; } static int nfc_genl_enable_se(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx, se_idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); se_idx = nla_get_u32(info->attrs[NFC_ATTR_SE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_enable_se(dev, se_idx); nfc_put_device(dev); return rc; } static int nfc_genl_disable_se(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; int rc; u32 idx, se_idx; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); se_idx = nla_get_u32(info->attrs[NFC_ATTR_SE_INDEX]); dev = nfc_get_device(idx); if (!dev) return -ENODEV; rc = nfc_disable_se(dev, se_idx); nfc_put_device(dev); return rc; } static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev, u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; struct nfc_se *se, *n; list_for_each_entry_safe(se, n, &dev->secure_elements, list) { hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, flags, NFC_CMD_GET_SE); if (!hdr) goto nla_put_failure; if (cb) genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se->idx) || nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) goto nla_put_failure; genlmsg_end(msg, hdr); } return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int nfc_genl_dump_ses(struct sk_buff *skb, struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; bool first_call = false; if (!iter) { first_call = true; iter = kmalloc_obj(struct class_dev_iter); if (!iter) return -ENOMEM; cb->args[0] = (long) iter; } mutex_lock(&nfc_devlist_mutex); cb->seq = nfc_devlist_generation; if (first_call) { nfc_device_iter_init(iter); dev = nfc_device_iter_next(iter); } while (dev) { int rc; rc = nfc_genl_send_se(skb, dev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (rc < 0) break; dev = nfc_device_iter_next(iter); } mutex_unlock(&nfc_devlist_mutex); cb->args[1] = (long) dev; return skb->len; } static int nfc_genl_dump_ses_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; if (iter) { nfc_device_iter_exit(iter); kfree(iter); } return 0; } static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context) { struct nfc_se *se; int rc; pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx); device_lock(&dev->dev); if (!device_is_registered(&dev->dev)) { rc = -ENODEV; goto error; } if (!dev->dev_up) { rc = -ENODEV; goto error; } if (!dev->ops->se_io) { rc = -EOPNOTSUPP; goto error; } se = nfc_find_se(dev, se_idx); if (!se) { rc = -EINVAL; goto error; } if (se->state != NFC_SE_ENABLED) { rc = -ENODEV; goto error; } rc = dev->ops->se_io(dev, se_idx, apdu, apdu_length, cb, cb_context); device_unlock(&dev->dev); return rc; error: device_unlock(&dev->dev); kfree(cb_context); return rc; } struct se_io_ctx { u32 dev_idx; u32 se_idx; }; static void se_io_cb(void *context, u8 *apdu, size_t apdu_len, int err) { struct se_io_ctx *ctx = context; struct sk_buff *msg; void *hdr; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { kfree(ctx); return; } hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, NFC_CMD_SE_IO); if (!hdr) goto free_msg; if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, ctx->dev_idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, ctx->se_idx) || nla_put(msg, NFC_ATTR_SE_APDU, apdu_len, apdu)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); kfree(ctx); return; nla_put_failure: free_msg: nlmsg_free(msg); kfree(ctx); return; } static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; struct se_io_ctx *ctx; u32 dev_idx, se_idx; u8 *apdu; size_t apdu_len; int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX] || !info->attrs[NFC_ATTR_SE_APDU]) return -EINVAL; dev_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); se_idx = nla_get_u32(info->attrs[NFC_ATTR_SE_INDEX]); dev = nfc_get_device(dev_idx); if (!dev) return -ENODEV; if (!dev->ops || !dev->ops->se_io) { rc = -EOPNOTSUPP; goto put_dev; } apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]); if (apdu_len == 0) { rc = -EINVAL; goto put_dev; } apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]); ctx = kzalloc_obj(struct se_io_ctx); if (!ctx) { rc = -ENOMEM; goto put_dev; } ctx->dev_idx = dev_idx; ctx->se_idx = se_idx; rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx); put_dev: nfc_put_device(dev); return rc; } static int nfc_genl_vendor_cmd(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; const struct nfc_vendor_cmd *cmd; u32 dev_idx, vid, subcmd; u8 *data; size_t data_len; int i, err; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_VENDOR_ID] || !info->attrs[NFC_ATTR_VENDOR_SUBCMD]) return -EINVAL; dev_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); vid = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_ID]); subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]); dev = nfc_get_device(dev_idx); if (!dev) return -ENODEV; if (!dev->vendor_cmds || !dev->n_vendor_cmds) { err = -ENODEV; goto put_dev; } if (info->attrs[NFC_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]); data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]); if (data_len == 0) { err = -EINVAL; goto put_dev; } } else { data = NULL; data_len = 0; } for (i = 0; i < dev->n_vendor_cmds; i++) { cmd = &dev->vendor_cmds[i]; if (cmd->vendor_id != vid || cmd->subcmd != subcmd) continue; dev->cur_cmd_info = info; err = cmd->doit(dev, data, data_len); dev->cur_cmd_info = NULL; goto put_dev; } err = -EOPNOTSUPP; put_dev: nfc_put_device(dev); return err; } /* message building helper */ static inline void *nfc_hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd) { /* since there is no private header just add the generic one */ return genlmsg_put(skb, portid, seq, &nfc_genl_family, flags, cmd); } static struct sk_buff * __nfc_alloc_vendor_cmd_skb(struct nfc_dev *dev, int approxlen, u32 portid, u32 seq, enum nfc_attrs attr, u32 oui, u32 subcmd, gfp_t gfp) { struct sk_buff *skb; void *hdr; skb = nlmsg_new(approxlen + 100, gfp); if (!skb) return NULL; hdr = nfc_hdr_put(skb, portid, seq, 0, NFC_CMD_VENDOR); if (!hdr) { kfree_skb(skb); return NULL; } if (nla_put_u32(skb, NFC_ATTR_DEVICE_INDEX, dev->idx)) goto nla_put_failure; if (nla_put_u32(skb, NFC_ATTR_VENDOR_ID, oui)) goto nla_put_failure; if (nla_put_u32(skb, NFC_ATTR_VENDOR_SUBCMD, subcmd)) goto nla_put_failure; ((void **)skb->cb)[0] = dev; ((void **)skb->cb)[1] = hdr; return skb; nla_put_failure: kfree_skb(skb); return NULL; } struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, enum nfc_attrs attr, u32 oui, u32 subcmd, int approxlen) { if (WARN_ON(!dev->cur_cmd_info)) return NULL; return __nfc_alloc_vendor_cmd_skb(dev, approxlen, dev->cur_cmd_info->snd_portid, dev->cur_cmd_info->snd_seq, attr, oui, subcmd, GFP_KERNEL); } EXPORT_SYMBOL(__nfc_alloc_vendor_cmd_reply_skb); int nfc_vendor_cmd_reply(struct sk_buff *skb) { struct nfc_dev *dev = ((void **)skb->cb)[0]; void *hdr = ((void **)skb->cb)[1]; /* clear CB data for netlink core to own from now on */ memset(skb->cb, 0, sizeof(skb->cb)); if (WARN_ON(!dev->cur_cmd_info)) { kfree_skb(skb); return -EINVAL; } genlmsg_end(skb, hdr); return genlmsg_reply(skb, dev->cur_cmd_info); } EXPORT_SYMBOL(nfc_vendor_cmd_reply); static const struct genl_ops nfc_genl_ops[] = { { .cmd = NFC_CMD_GET_DEVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_get_device, .dumpit = nfc_genl_dump_devices, .done = nfc_genl_dump_devices_done, }, { .cmd = NFC_CMD_DEV_UP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dev_up, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEV_DOWN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dev_down, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_START_POLL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_start_poll, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_STOP_POLL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_stop_poll, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEP_LINK_UP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dep_link_up, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEP_LINK_DOWN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_dep_link_down, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_GET_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = nfc_genl_dump_targets, .done = nfc_genl_dump_targets_done, }, { .cmd = NFC_CMD_LLC_GET_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_get_params, }, { .cmd = NFC_CMD_LLC_SET_PARAMS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_set_params, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_LLC_SDREQ, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_llc_sdreq, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_FW_DOWNLOAD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_fw_download, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_ENABLE_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_enable_se, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DISABLE_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_disable_se, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_GET_SE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = nfc_genl_dump_ses, .done = nfc_genl_dump_ses_done, }, { .cmd = NFC_CMD_SE_IO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_se_io, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_ACTIVATE_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_activate_target, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_VENDOR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_vendor_cmd, .flags = GENL_ADMIN_PERM, }, { .cmd = NFC_CMD_DEACTIVATE_TARGET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nfc_genl_deactivate_target, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family nfc_genl_family __ro_after_init = { .hdrsize = 0, .name = NFC_GENL_NAME, .version = NFC_GENL_VERSION, .maxattr = NFC_ATTR_MAX, .policy = nfc_genl_policy, .module = THIS_MODULE, .ops = nfc_genl_ops, .n_ops = ARRAY_SIZE(nfc_genl_ops), .resv_start_op = NFC_CMD_DEACTIVATE_TARGET + 1, .mcgrps = nfc_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(nfc_genl_mcgrps), }; struct urelease_work { struct work_struct w; u32 portid; }; static void nfc_urelease_event_work(struct work_struct *work) { struct urelease_work *w = container_of(work, struct urelease_work, w); struct class_dev_iter iter; struct nfc_dev *dev; pr_debug("portid %d\n", w->portid); mutex_lock(&nfc_devlist_mutex); nfc_device_iter_init(&iter); dev = nfc_device_iter_next(&iter); while (dev) { mutex_lock(&dev->genl_data.genl_data_mutex); if (dev->genl_data.poll_req_portid == w->portid) { nfc_stop_poll(dev); dev->genl_data.poll_req_portid = 0; } mutex_unlock(&dev->genl_data.genl_data_mutex); dev = nfc_device_iter_next(&iter); } nfc_device_iter_exit(&iter); mutex_unlock(&nfc_devlist_mutex); kfree(w); } static int nfc_genl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct urelease_work *w; if (event != NETLINK_URELEASE || n->protocol != NETLINK_GENERIC) goto out; pr_debug("NETLINK_URELEASE event from id %d\n", n->portid); w = kmalloc_obj(*w, GFP_ATOMIC); if (w) { INIT_WORK(&w->w, nfc_urelease_event_work); w->portid = n->portid; schedule_work(&w->w); } out: return NOTIFY_DONE; } void nfc_genl_data_init(struct nfc_genl_data *genl_data) { genl_data->poll_req_portid = 0; mutex_init(&genl_data->genl_data_mutex); } void nfc_genl_data_exit(struct nfc_genl_data *genl_data) { mutex_destroy(&genl_data->genl_data_mutex); } static struct notifier_block nl_notifier = { .notifier_call = nfc_genl_rcv_nl_event, }; /** * nfc_genl_init() - Initialize netlink interface * * This initialization function registers the nfc netlink family. */ int __init nfc_genl_init(void) { int rc; rc = genl_register_family(&nfc_genl_family); if (rc) return rc; netlink_register_notifier(&nl_notifier); return 0; } /** * nfc_genl_exit() - Deinitialize netlink interface * * This exit function unregisters the nfc netlink family. */ void nfc_genl_exit(void) { netlink_unregister_notifier(&nl_notifier); genl_unregister_family(&nfc_genl_family); } |
| 96 95 4 4 6 8 14 88 9 9 94 3 2 9 7 12 103 207 207 203 4 204 4 207 207 205 109 121 121 116 4 115 7 7 119 27 92 119 112 99 13 14 97 5 5 95 14 14 27 80 107 107 107 107 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | // SPDX-License-Identifier: GPL-2.0 /* * Waiting for completion events */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/io_uring.h> #include <linux/time_namespace.h> #include <trace/events/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "napi.h" #include "wait.h" static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, int wake_flags, void *key) { struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); /* * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ if (io_should_wake(iowq) || io_has_work(iowq->ctx)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } int io_run_task_work_sig(struct io_ring_ctx *ctx) { if (io_local_work_pending(ctx)) { __set_current_state(TASK_RUNNING); if (io_run_local_work(ctx, INT_MAX, IO_LOCAL_TW_DEFAULT_MAX) > 0) return 0; } if (io_run_task_work() > 0) return 0; if (task_sigpending(current)) return -EINTR; return 0; } static bool current_pending_io(void) { struct io_uring_task *tctx = current->io_uring; if (!tctx) return false; return percpu_counter_read_positive(&tctx->inflight); } static enum hrtimer_restart io_cqring_timer_wakeup(struct hrtimer *timer) { struct io_wait_queue *iowq = container_of(timer, struct io_wait_queue, t); WRITE_ONCE(iowq->hit_timeout, 1); iowq->min_timeout = 0; wake_up_process(iowq->wq.private); return HRTIMER_NORESTART; } /* * Doing min_timeout portion. If we saw any timeouts, events, or have work, * wake up. If not, and we have a normal timeout, switch to that and keep * sleeping. */ static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer) { struct io_wait_queue *iowq = container_of(timer, struct io_wait_queue, t); struct io_ring_ctx *ctx = iowq->ctx; /* no general timeout, or shorter (or equal), we are done */ if (iowq->timeout == KTIME_MAX || ktime_compare(iowq->min_timeout, iowq->timeout) >= 0) goto out_wake; /* work we may need to run, wake function will see if we need to wake */ if (io_has_work(ctx)) goto out_wake; /* got events since we started waiting, min timeout is done */ scoped_guard(rcu) { struct io_rings *rings = io_get_rings(ctx); if (iowq->cq_min_tail != READ_ONCE(rings->cq.tail)) goto out_wake; /* if we have any events and min timeout expired, we're done */ if (io_cqring_events(ctx)) goto out_wake; } /* * If using deferred task_work running and application is waiting on * more than one request, ensure we reset it now where we are switching * to normal sleeps. Any request completion post min_wait should wake * the task and return. */ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { atomic_set(&ctx->cq_wait_nr, 1); smp_mb(); if (io_local_work_pending(ctx)) goto out_wake; } /* any generated CQE posted past this time should wake us up */ iowq->cq_tail = iowq->cq_min_tail + 1; hrtimer_update_function(&iowq->t, io_cqring_timer_wakeup); hrtimer_set_expires(timer, iowq->timeout); return HRTIMER_RESTART; out_wake: return io_cqring_timer_wakeup(timer); } static int io_cqring_schedule_timeout(struct io_wait_queue *iowq, clockid_t clock_id, ktime_t start_time) { ktime_t timeout; if (iowq->min_timeout) { timeout = ktime_add_ns(iowq->min_timeout, start_time); hrtimer_setup_on_stack(&iowq->t, io_cqring_min_timer_wakeup, clock_id, HRTIMER_MODE_ABS); } else { timeout = iowq->timeout; hrtimer_setup_on_stack(&iowq->t, io_cqring_timer_wakeup, clock_id, HRTIMER_MODE_ABS); } hrtimer_set_expires_range_ns(&iowq->t, timeout, 0); hrtimer_start_expires(&iowq->t, HRTIMER_MODE_ABS); if (!READ_ONCE(iowq->hit_timeout)) schedule(); hrtimer_cancel(&iowq->t); destroy_hrtimer_on_stack(&iowq->t); __set_current_state(TASK_RUNNING); return READ_ONCE(iowq->hit_timeout) ? -ETIME : 0; } static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct ext_arg *ext_arg, ktime_t start_time) { int ret = 0; /* * Mark us as being in io_wait if we have pending requests, so cpufreq * can take into account that the task is waiting for IO - turns out * to be important for low QD IO. */ if (ext_arg->iowait && current_pending_io()) current->in_iowait = 1; if (iowq->timeout != KTIME_MAX || iowq->min_timeout) ret = io_cqring_schedule_timeout(iowq, ctx->clockid, start_time); else schedule(); current->in_iowait = 0; return ret; } /* If this returns > 0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct ext_arg *ext_arg, ktime_t start_time) { if (unlikely(READ_ONCE(ctx->check_cq))) return 1; if (unlikely(io_local_work_pending(ctx))) return 1; if (unlikely(task_work_pending(current))) return 1; if (unlikely(task_sigpending(current))) return -EINTR; if (unlikely(io_should_wake(iowq))) return 0; return __io_cqring_wait_schedule(ctx, iowq, ext_arg, start_time); } /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. */ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, struct ext_arg *ext_arg) { struct io_wait_queue iowq; struct io_rings *rings; ktime_t start_time; int ret, nr_wait; min_events = min_t(int, min_events, ctx->cq_entries); if (!io_allowed_run_tw(ctx)) return -EEXIST; if (io_local_work_pending(ctx)) io_run_local_work(ctx, min_events, max(IO_LOCAL_TW_DEFAULT_MAX, min_events)); io_run_task_work(); if (unlikely(test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))) io_cqring_do_overflow_flush(ctx); rcu_read_lock(); rings = io_get_rings(ctx); if (__io_cqring_events_user(ctx) >= min_events) { rcu_read_unlock(); return 0; } init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); iowq.ctx = ctx; iowq.cq_tail = READ_ONCE(rings->cq.head) + min_events; iowq.cq_min_tail = READ_ONCE(rings->cq.tail); nr_wait = (int) iowq.cq_tail - READ_ONCE(rings->cq.tail); rcu_read_unlock(); rings = NULL; iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); iowq.hit_timeout = 0; iowq.min_timeout = ext_arg->min_time; iowq.timeout = KTIME_MAX; start_time = io_get_time(ctx); if (ext_arg->ts_set) { iowq.timeout = timespec64_to_ktime(ext_arg->ts); if (flags & IORING_ENTER_ABS_TIMER) iowq.timeout = timens_ktime_to_host(ctx->clockid, iowq.timeout); else iowq.timeout = ktime_add(iowq.timeout, start_time); } if (ext_arg->sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) ret = set_compat_user_sigmask((const compat_sigset_t __user *)ext_arg->sig, ext_arg->argsz); else #endif ret = set_user_sigmask(ext_arg->sig, ext_arg->argsz); if (ret) return ret; } io_napi_busy_loop(ctx, &iowq); trace_io_uring_cqring_wait(ctx, min_events); do { unsigned long check_cq; if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { atomic_set(&ctx->cq_wait_nr, nr_wait); set_current_state(TASK_INTERRUPTIBLE); } else { prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); } ret = io_cqring_wait_schedule(ctx, &iowq, ext_arg, start_time); __set_current_state(TASK_RUNNING); atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT); /* * Run task_work after scheduling and before io_should_wake(). * If we got woken because of task_work being processed, run it * now rather than let the caller do another wait loop. */ if (io_local_work_pending(ctx)) io_run_local_work(ctx, nr_wait, nr_wait); io_run_task_work(); /* * Non-local task_work will be run on exit to userspace, but * if we're using DEFER_TASKRUN, then we could have waited * with a timeout for a number of requests. If the timeout * hits, we could have some requests ready to process. Ensure * this break is _after_ we have run task_work, to avoid * deferring running potentially pending requests until the * next time we wait for events. */ if (ret < 0) break; check_cq = READ_ONCE(ctx->check_cq); if (unlikely(check_cq)) { /* let the caller flush overflows, retry */ if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) io_cqring_do_overflow_flush(ctx); if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) { ret = -EBADR; break; } } if (io_should_wake(&iowq)) { ret = 0; break; } cond_resched(); /* if min timeout has been hit, don't reset wait count */ if (!iowq.hit_timeout) scoped_guard(rcu) nr_wait = (int) iowq.cq_tail - READ_ONCE(io_get_rings(ctx)->cq.tail); else nr_wait = 1; } while (1); if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) finish_wait(&ctx->cq_wait, &iowq.wq); restore_saved_sigmask_unless(ret == -EINTR); guard(rcu)(); return READ_ONCE(io_get_rings(ctx)->cq.head) == READ_ONCE(io_get_rings(ctx)->cq.tail) ? ret : 0; } |
| 3 3 5 2 3 2 1 1 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 | /* Copyright (c) 2013 Coraid, Inc. See COPYING for GPL terms. */ /* * aoenet.c * Ethernet portion of AoE driver */ #include <linux/gfp.h> #include <linux/hdreg.h> #include <linux/blkdev.h> #include <linux/netdevice.h> #include <linux/moduleparam.h> #include <net/net_namespace.h> #include <linux/unaligned.h> #include "aoe.h" #define NECODES 5 static char *aoe_errlist[] = { "no such error", "unrecognized command code", "bad argument parameter", "device unavailable", "config string present", "unsupported version" }; enum { IFLISTSZ = 1024, }; static char aoe_iflist[IFLISTSZ]; module_param_string(aoe_iflist, aoe_iflist, IFLISTSZ, 0600); MODULE_PARM_DESC(aoe_iflist, "aoe_iflist=dev1[,dev2...]"); static wait_queue_head_t txwq; static struct ktstate kts; #ifndef MODULE static int __init aoe_iflist_setup(char *str) { strscpy(aoe_iflist, str, IFLISTSZ); return 1; } __setup("aoe_iflist=", aoe_iflist_setup); #endif static spinlock_t txlock; static struct sk_buff_head skbtxq; /* enters with txlock held */ static int tx(int id) __must_hold(&txlock) { struct sk_buff *skb; struct net_device *ifp; while ((skb = skb_dequeue(&skbtxq))) { spin_unlock_irq(&txlock); ifp = skb->dev; if (dev_queue_xmit(skb) == NET_XMIT_DROP && net_ratelimit()) pr_warn("aoe: packet could not be sent on %s. %s\n", ifp ? ifp->name : "netif", "consider increasing tx_queue_len"); dev_put(ifp); spin_lock_irq(&txlock); } return 0; } int is_aoe_netif(struct net_device *ifp) { register char *p, *q; register int len; if (aoe_iflist[0] == '\0') return 1; p = aoe_iflist + strspn(aoe_iflist, WHITESPACE); for (; *p; p = q + strspn(q, WHITESPACE)) { q = p + strcspn(p, WHITESPACE); if (q != p) len = q - p; else len = strlen(p); /* last token in aoe_iflist */ if (strlen(ifp->name) == len && !strncmp(ifp->name, p, len)) return 1; if (q == p) break; } return 0; } int set_aoe_iflist(const char __user *user_str, size_t size) { if (size >= IFLISTSZ) return -EINVAL; if (copy_from_user(aoe_iflist, user_str, size)) { printk(KERN_INFO "aoe: copy from user failed\n"); return -EFAULT; } aoe_iflist[size] = 0x00; return 0; } void aoenet_xmit(struct sk_buff_head *queue) { struct sk_buff *skb, *tmp; ulong flags; skb_queue_walk_safe(queue, skb, tmp) { __skb_unlink(skb, queue); spin_lock_irqsave(&txlock, flags); skb_queue_tail(&skbtxq, skb); spin_unlock_irqrestore(&txlock, flags); wake_up(&txwq); } } /* * (1) len doesn't include the header by default. I want this. */ static int aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt, struct net_device *orig_dev) { struct aoe_hdr *h; struct aoe_atahdr *ah; u32 n; int sn; if (dev_net(ifp) != &init_net) goto exit; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) return 0; if (!is_aoe_netif(ifp)) goto exit; skb_push(skb, ETH_HLEN); /* (1) */ sn = sizeof(*h) + sizeof(*ah); if (skb->len >= sn) { sn -= skb_headlen(skb); if (sn > 0 && !__pskb_pull_tail(skb, sn)) goto exit; } h = (struct aoe_hdr *) skb->data; n = get_unaligned_be32(&h->tag); if ((h->verfl & AOEFL_RSP) == 0 || (n & 1<<31)) goto exit; if (h->verfl & AOEFL_ERR) { n = h->err; if (n > NECODES) n = 0; if (net_ratelimit()) printk(KERN_ERR "%s%d.%d@%s; ecode=%d '%s'\n", "aoe: error packet from ", get_unaligned_be16(&h->major), h->minor, skb->dev->name, h->err, aoe_errlist[n]); goto exit; } switch (h->cmd) { case AOECMD_ATA: /* ata_rsp may keep skb for later processing or give it back */ skb = aoecmd_ata_rsp(skb); break; case AOECMD_CFG: aoecmd_cfg_rsp(skb); break; default: if (h->cmd >= AOECMD_VEND_MIN) break; /* don't complain about vendor commands */ pr_info("aoe: unknown AoE command type 0x%02x\n", h->cmd); break; } if (!skb) return 0; exit: dev_kfree_skb(skb); return 0; } static struct packet_type aoe_pt __read_mostly = { .type = __constant_htons(ETH_P_AOE), .func = aoenet_rcv, }; int __init aoenet_init(void) { skb_queue_head_init(&skbtxq); init_waitqueue_head(&txwq); spin_lock_init(&txlock); kts.lock = &txlock; kts.fn = tx; kts.waitq = &txwq; kts.id = 0; snprintf(kts.name, sizeof(kts.name), "aoe_tx%d", kts.id); if (aoe_ktstart(&kts)) return -EAGAIN; dev_add_pack(&aoe_pt); return 0; } void aoenet_exit(void) { aoe_ktstop(&kts); skb_queue_purge(&skbtxq); dev_remove_pack(&aoe_pt); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file contains common definitions for working with Enlightened VMCS which * are used both by Hyper-V on KVM and KVM on Hyper-V. */ #ifndef __KVM_X86_VMX_HYPERV_EVMCS_H #define __KVM_X86_VMX_HYPERV_EVMCS_H #include <hyperv/hvhdk.h> #include "capabilities.h" #include "vmcs12.h" #define KVM_EVMCS_VERSION 1 /* * Enlightened VMCSv1 doesn't support these: * * POSTED_INTR_NV = 0x00000002, * GUEST_INTR_STATUS = 0x00000810, * APIC_ACCESS_ADDR = 0x00002014, * POSTED_INTR_DESC_ADDR = 0x00002016, * EOI_EXIT_BITMAP0 = 0x0000201c, * EOI_EXIT_BITMAP1 = 0x0000201e, * EOI_EXIT_BITMAP2 = 0x00002020, * EOI_EXIT_BITMAP3 = 0x00002022, * GUEST_PML_INDEX = 0x00000812, * PML_ADDRESS = 0x0000200e, * VM_FUNCTION_CONTROL = 0x00002018, * EPTP_LIST_ADDRESS = 0x00002024, * VMREAD_BITMAP = 0x00002026, * VMWRITE_BITMAP = 0x00002028, * * TSC_MULTIPLIER = 0x00002032, * PLE_GAP = 0x00004020, * PLE_WINDOW = 0x00004022, * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, * * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, */ #define EVMCS1_SUPPORTED_PINCTRL \ (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ PIN_BASED_EXT_INTR_MASK | \ PIN_BASED_NMI_EXITING | \ PIN_BASED_VIRTUAL_NMIS) #define EVMCS1_SUPPORTED_EXEC_CTRL \ (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ CPU_BASED_HLT_EXITING | \ CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING | \ CPU_BASED_UNCOND_IO_EXITING | \ CPU_BASED_MOV_DR_EXITING | \ CPU_BASED_USE_TSC_OFFSETTING | \ CPU_BASED_MWAIT_EXITING | \ CPU_BASED_MONITOR_EXITING | \ CPU_BASED_INVLPG_EXITING | \ CPU_BASED_RDPMC_EXITING | \ CPU_BASED_INTR_WINDOW_EXITING | \ CPU_BASED_CR8_LOAD_EXITING | \ CPU_BASED_CR8_STORE_EXITING | \ CPU_BASED_RDTSC_EXITING | \ CPU_BASED_TPR_SHADOW | \ CPU_BASED_USE_IO_BITMAPS | \ CPU_BASED_MONITOR_TRAP_FLAG | \ CPU_BASED_USE_MSR_BITMAPS | \ CPU_BASED_NMI_WINDOW_EXITING | \ CPU_BASED_PAUSE_EXITING | \ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) #define EVMCS1_SUPPORTED_2NDEXEC \ (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ SECONDARY_EXEC_WBINVD_EXITING | \ SECONDARY_EXEC_ENABLE_VPID | \ SECONDARY_EXEC_ENABLE_EPT | \ SECONDARY_EXEC_UNRESTRICTED_GUEST | \ SECONDARY_EXEC_DESC | \ SECONDARY_EXEC_ENABLE_RDTSCP | \ SECONDARY_EXEC_ENABLE_INVPCID | \ SECONDARY_EXEC_ENABLE_XSAVES | \ SECONDARY_EXEC_RDSEED_EXITING | \ SECONDARY_EXEC_RDRAND_EXITING | \ SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ SECONDARY_EXEC_PT_USE_GPA | \ SECONDARY_EXEC_PT_CONCEAL_VMX | \ SECONDARY_EXEC_BUS_LOCK_DETECTION | \ SECONDARY_EXEC_NOTIFY_VM_EXITING | \ SECONDARY_EXEC_MODE_BASED_EPT_EXEC | \ SECONDARY_EXEC_ENCLS_EXITING) #define EVMCS1_SUPPORTED_3RDEXEC (0ULL) #define EVMCS1_SUPPORTED_VMEXIT_CTRL \ (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ VM_EXIT_SAVE_DEBUG_CONTROLS | \ VM_EXIT_ACK_INTR_ON_EXIT | \ VM_EXIT_HOST_ADDR_SPACE_SIZE | \ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ VM_EXIT_SAVE_IA32_PAT | \ VM_EXIT_LOAD_IA32_PAT | \ VM_EXIT_SAVE_IA32_EFER | \ VM_EXIT_LOAD_IA32_EFER | \ VM_EXIT_CLEAR_BNDCFGS | \ VM_EXIT_PT_CONCEAL_PIP | \ VM_EXIT_CLEAR_IA32_RTIT_CTL) #define EVMCS1_SUPPORTED_VMENTRY_CTRL \ (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ VM_ENTRY_LOAD_DEBUG_CONTROLS | \ VM_ENTRY_IA32E_MODE | \ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ VM_ENTRY_LOAD_IA32_PAT | \ VM_ENTRY_LOAD_IA32_EFER | \ VM_ENTRY_LOAD_BNDCFGS | \ VM_ENTRY_PT_CONCEAL_PIP | \ VM_ENTRY_LOAD_IA32_RTIT_CTL) #define EVMCS1_SUPPORTED_VMFUNC (0) struct evmcs_field { u16 offset; u16 clean_field; }; extern const struct evmcs_field vmcs_field_to_evmcs_1[]; extern const unsigned int nr_evmcs_1_fields; static __always_inline int evmcs_field_offset(unsigned long field, u16 *clean_field) { const struct evmcs_field *evmcs_field; unsigned int index = ENC_TO_VMCS12_IDX(field); if (unlikely(index >= nr_evmcs_1_fields)) return -ENOENT; evmcs_field = &vmcs_field_to_evmcs_1[index]; /* * Use offset=0 to detect holes in eVMCS. This offset belongs to * 'revision_id' but this field has no encoding and is supposed to * be accessed directly. */ if (unlikely(!evmcs_field->offset)) return -ENOENT; if (clean_field) *clean_field = evmcs_field->clean_field; return evmcs_field->offset; } static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, unsigned long field, u16 offset) { /* * vmcs12_read_any() doesn't care whether the supplied structure * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes * the exact offset of the required field, use it for convenience * here. */ return vmcs12_read_any((void *)evmcs, field, offset); } #endif /* __KVM_X86_VMX_HYPERV_H */ |
| 53 53 13 1 32 1 19 1 1 3 13 5 2 2 1 12 1 1 1 1 1 1 1 1 1 1 3 1 1 1 1 1 1 1 3 2 1 24 2 1 21 5 7 1 1 1 1 1 1 1 5 5 1 1 27 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org> * (C) 2012 by Vyatta Inc. <http://www.vyatta.com> */ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/rculist.h> #include <linux/rculist_nulls.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/security.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netlink.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/netfilter.h> #include <net/netlink.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static unsigned int nfct_timeout_id __read_mostly; struct ctnl_timeout { struct list_head head; struct list_head free_head; struct rcu_head rcu_head; char name[CTNL_TIMEOUT_NAME_MAX]; struct nf_ct_timeout *timeout; }; struct nfct_timeout_pernet { struct list_head nfct_timeout_list; struct list_head nfct_timeout_freelist; }; MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("cttimeout: Extended Netfilter Connection Tracking timeout tuning"); static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { [CTA_TIMEOUT_NAME] = { .type = NLA_NUL_STRING, .len = CTNL_TIMEOUT_NAME_MAX - 1}, [CTA_TIMEOUT_L3PROTO] = { .type = NLA_U16 }, [CTA_TIMEOUT_L4PROTO] = { .type = NLA_U8 }, [CTA_TIMEOUT_DATA] = { .type = NLA_NESTED }, }; static struct nfct_timeout_pernet *nfct_timeout_pernet(struct net *net) { return net_generic(net, nfct_timeout_id); } static int ctnl_timeout_parse_policy(void *timeout, const struct nf_conntrack_l4proto *l4proto, struct net *net, const struct nlattr *attr) { struct nlattr **tb; int ret = 0; tb = kzalloc_objs(*tb, l4proto->ctnl_timeout.nlattr_max + 1); if (!tb) return -ENOMEM; ret = nla_parse_nested_deprecated(tb, l4proto->ctnl_timeout.nlattr_max, attr, l4proto->ctnl_timeout.nla_policy, NULL); if (ret < 0) goto err; ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeout); err: kfree(tb); return ret; } static int cttimeout_new_timeout(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(info->net); __u16 l3num; __u8 l4num; const struct nf_conntrack_l4proto *l4proto; struct ctnl_timeout *timeout, *matching = NULL; char *name; int ret; if (!cda[CTA_TIMEOUT_NAME] || !cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO] || !cda[CTA_TIMEOUT_DATA]) return -EINVAL; name = nla_data(cda[CTA_TIMEOUT_NAME]); l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); list_for_each_entry(timeout, &pernet->nfct_timeout_list, head) { if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; if (info->nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; matching = timeout; break; } if (matching) { if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { /* You cannot replace one timeout policy by another of * different kind, sorry. */ if (matching->timeout->l3num != l3num || matching->timeout->l4proto->l4proto != l4num) return -EINVAL; return ctnl_timeout_parse_policy(&matching->timeout->data, matching->timeout->l4proto, info->net, cda[CTA_TIMEOUT_DATA]); } return -EBUSY; } l4proto = nf_ct_l4proto_find(l4num); /* This protocol is not supportted, skip. */ if (l4proto->l4proto != l4num) { ret = -EOPNOTSUPP; goto err_proto_put; } timeout = kzalloc(sizeof(*timeout), GFP_KERNEL); if (timeout == NULL) { ret = -ENOMEM; goto err_proto_put; } timeout->timeout = kzalloc(sizeof(*timeout->timeout) + l4proto->ctnl_timeout.obj_size, GFP_KERNEL); if (!timeout->timeout) { ret = -ENOMEM; goto err; } ret = ctnl_timeout_parse_policy(&timeout->timeout->data, l4proto, info->net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err_free_timeout_policy; nla_strscpy(timeout->name, cda[CTA_TIMEOUT_NAME], sizeof(timeout->name)); timeout->timeout->l3num = l3num; timeout->timeout->l4proto = l4proto; refcount_set(&timeout->timeout->refcnt, 1); __module_get(THIS_MODULE); list_add_tail_rcu(&timeout->head, &pernet->nfct_timeout_list); return 0; err_free_timeout_policy: kfree(timeout->timeout); err: kfree(timeout); err_proto_put: return ret; } static int ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct ctnl_timeout *timeout) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; const struct nf_conntrack_l4proto *l4proto = timeout->timeout->l4proto; struct nlattr *nest_parms; int ret; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) || nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->timeout->l3num)) || nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto) || nla_put_be32(skb, CTA_TIMEOUT_USE, htonl(refcount_read(&timeout->timeout->refcnt)))) goto nla_put_failure; nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA); if (!nest_parms) goto nla_put_failure; ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->timeout->data); if (ret < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nfct_timeout_pernet *pernet; struct net *net = sock_net(skb->sk); struct ctnl_timeout *cur, *last; if (cb->args[2]) return 0; last = (struct ctnl_timeout *)cb->args[1]; if (cb->args[1]) cb->args[1] = 0; rcu_read_lock(); pernet = nfct_timeout_pernet(net); list_for_each_entry_rcu(cur, &pernet->nfct_timeout_list, head) { if (last) { if (cur != last) continue; last = NULL; } if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur) < 0) { cb->args[1] = (unsigned long)cur; break; } } if (!cb->args[1]) cb->args[2] = 1; rcu_read_unlock(); return skb->len; } static int cttimeout_get_timeout(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(info->net); int ret = -ENOENT; char *name; struct ctnl_timeout *cur; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnl_timeout_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } if (!cda[CTA_TIMEOUT_NAME]) return -EINVAL; name = nla_data(cda[CTA_TIMEOUT_NAME]); list_for_each_entry(cur, &pernet->nfct_timeout_list, head) { struct sk_buff *skb2; if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { ret = -ENOMEM; break; } ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur); if (ret <= 0) { kfree_skb(skb2); break; } ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); break; } return ret; } static void ctnl_timeout_del(struct net *net, struct ctnl_timeout *timeout) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_untimeout(net, timeout->timeout); if (refcount_dec_and_test(&timeout->timeout->refcnt)) kfree_rcu(timeout->timeout, rcu); kfree_rcu(timeout, rcu_head); module_put(THIS_MODULE); } static int cttimeout_del_timeout(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(info->net); struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; char *name; if (!cda[CTA_TIMEOUT_NAME]) { list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_list, head) ctnl_timeout_del(info->net, cur); return 0; } name = nla_data(cda[CTA_TIMEOUT_NAME]); list_for_each_entry(cur, &pernet->nfct_timeout_list, head) { if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; ctnl_timeout_del(info->net, cur); ret = 0; break; } return ret; } static int cttimeout_default_set(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { const struct nf_conntrack_l4proto *l4proto; __u8 l4num; int ret; if (!cda[CTA_TIMEOUT_L4PROTO] || !cda[CTA_TIMEOUT_DATA]) return -EINVAL; l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find(l4num); /* This protocol is not supported, skip. */ if (l4proto->l4proto != l4num) { ret = -EOPNOTSUPP; goto err; } ret = ctnl_timeout_parse_policy(NULL, l4proto, info->net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err; return 0; err: return ret; } static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 l3num, const struct nf_conntrack_l4proto *l4proto, const unsigned int *timeouts) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; struct nlattr *nest_parms; int ret; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(l3num)) || nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto)) goto nla_put_failure; nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA); if (!nest_parms) goto nla_put_failure; ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static int cttimeout_default_get(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { const struct nf_conntrack_l4proto *l4proto; unsigned int *timeouts = NULL; struct sk_buff *skb2; __u16 l3num; __u8 l4num; int ret; if (!cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO]) return -EINVAL; l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find(l4num); if (l4proto->l4proto != l4num) return -EOPNOTSUPP; switch (l4proto->l4proto) { case IPPROTO_ICMP: timeouts = &nf_icmp_pernet(info->net)->timeout; break; case IPPROTO_TCP: timeouts = nf_tcp_pernet(info->net)->timeouts; break; case IPPROTO_UDP: timeouts = nf_udp_pernet(info->net)->timeouts; break; case IPPROTO_ICMPV6: timeouts = &nf_icmpv6_pernet(info->net)->timeout; break; case IPPROTO_SCTP: #ifdef CONFIG_NF_CT_PROTO_SCTP timeouts = nf_sctp_pernet(info->net)->timeouts; #endif break; case IPPROTO_GRE: #ifdef CONFIG_NF_CT_PROTO_GRE timeouts = nf_gre_pernet(info->net)->timeouts; #endif break; case 255: timeouts = &nf_generic_pernet(info->net)->timeout; break; default: WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto); break; } if (!timeouts) return -EOPNOTSUPP; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) return -ENOMEM; ret = cttimeout_default_fill_info(info->net, skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, const char *name) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); struct ctnl_timeout *timeout, *matching = NULL; list_for_each_entry_rcu(timeout, &pernet->nfct_timeout_list, head) { if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; if (!refcount_inc_not_zero(&timeout->timeout->refcnt)) goto err; matching = timeout; __module_get(THIS_MODULE); break; } err: return matching ? matching->timeout : NULL; } static void ctnl_timeout_put(struct nf_ct_timeout *timeout) { if (refcount_dec_and_test(&timeout->refcnt)) kfree_rcu(timeout, rcu); module_put(THIS_MODULE); } static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = { [IPCTNL_MSG_TIMEOUT_NEW] = { .call = cttimeout_new_timeout, .type = NFNL_CB_MUTEX, .attr_count = CTA_TIMEOUT_MAX, .policy = cttimeout_nla_policy }, [IPCTNL_MSG_TIMEOUT_GET] = { .call = cttimeout_get_timeout, .type = NFNL_CB_MUTEX, .attr_count = CTA_TIMEOUT_MAX, .policy = cttimeout_nla_policy }, [IPCTNL_MSG_TIMEOUT_DELETE] = { .call = cttimeout_del_timeout, .type = NFNL_CB_MUTEX, .attr_count = CTA_TIMEOUT_MAX, .policy = cttimeout_nla_policy }, [IPCTNL_MSG_TIMEOUT_DEFAULT_SET] = { .call = cttimeout_default_set, .type = NFNL_CB_MUTEX, .attr_count = CTA_TIMEOUT_MAX, .policy = cttimeout_nla_policy }, [IPCTNL_MSG_TIMEOUT_DEFAULT_GET] = { .call = cttimeout_default_get, .type = NFNL_CB_MUTEX, .attr_count = CTA_TIMEOUT_MAX, .policy = cttimeout_nla_policy }, }; static const struct nfnetlink_subsystem cttimeout_subsys = { .name = "conntrack_timeout", .subsys_id = NFNL_SUBSYS_CTNETLINK_TIMEOUT, .cb_count = IPCTNL_MSG_TIMEOUT_MAX, .cb = cttimeout_cb, }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_TIMEOUT); static int __net_init cttimeout_net_init(struct net *net) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); INIT_LIST_HEAD(&pernet->nfct_timeout_list); INIT_LIST_HEAD(&pernet->nfct_timeout_freelist); return 0; } static void __net_exit cttimeout_net_pre_exit(struct net *net) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); struct ctnl_timeout *cur, *tmp; list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_list, head) { list_del_rcu(&cur->head); list_add(&cur->free_head, &pernet->nfct_timeout_freelist); } /* core calls synchronize_rcu() after this */ } static void __net_exit cttimeout_net_exit(struct net *net) { struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); struct ctnl_timeout *cur, *tmp; if (list_empty(&pernet->nfct_timeout_freelist)) return; nf_ct_untimeout(net, NULL); list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, free_head) { list_del(&cur->free_head); if (refcount_dec_and_test(&cur->timeout->refcnt)) kfree_rcu(cur->timeout, rcu); kfree_rcu(cur, rcu_head); module_put(THIS_MODULE); } } static struct pernet_operations cttimeout_ops = { .init = cttimeout_net_init, .pre_exit = cttimeout_net_pre_exit, .exit = cttimeout_net_exit, .id = &nfct_timeout_id, .size = sizeof(struct nfct_timeout_pernet), }; static const struct nf_ct_timeout_hooks hooks = { .timeout_find_get = ctnl_timeout_find_get, .timeout_put = ctnl_timeout_put, }; static int __init cttimeout_init(void) { int ret; ret = register_pernet_subsys(&cttimeout_ops); if (ret < 0) return ret; ret = nfnetlink_subsys_register(&cttimeout_subsys); if (ret < 0) { pr_err("cttimeout_init: cannot register cttimeout with " "nfnetlink.\n"); goto err_out; } RCU_INIT_POINTER(nf_ct_timeout_hook, &hooks); return 0; err_out: unregister_pernet_subsys(&cttimeout_ops); return ret; } static void __exit cttimeout_exit(void) { nfnetlink_subsys_unregister(&cttimeout_subsys); unregister_pernet_subsys(&cttimeout_ops); RCU_INIT_POINTER(nf_ct_timeout_hook, NULL); synchronize_net(); } module_init(cttimeout_init); module_exit(cttimeout_exit); |
| 77 26 51 60 60 60 20 18 2 20 20 20 20 20 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * MLO link handling * * Copyright (C) 2022-2026 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "key.h" #include "debugfs_netdev.h" static void ieee80211_update_apvlan_links(struct ieee80211_sub_if_data *sdata) { unsigned long rem = ~sdata->vif.valid_links & GENMASK(IEEE80211_MLD_MAX_NUM_LINKS - 1, 0); struct ieee80211_local *local = sdata->local; unsigned long add = sdata->vif.valid_links; struct wiphy *wiphy = local->hw.wiphy; struct ieee80211_sub_if_data *vlan; struct ieee80211_link_data *link; struct sta_info *sta; list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { int link_id; if (vlan->wdev.use_4addr) { sta = wiphy_dereference(wiphy, vlan->u.vlan.sta); if (sta) add = add & sta->sta.valid_links; } if (add == vlan->vif.valid_links) continue; for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { vlan->wdev.valid_links |= BIT(link_id); ether_addr_copy(vlan->wdev.links[link_id].addr, sdata->wdev.links[link_id].addr); } for_each_set_bit(link_id, &rem, IEEE80211_MLD_MAX_NUM_LINKS) { vlan->wdev.valid_links &= ~BIT(link_id); eth_zero_addr(vlan->wdev.links[link_id].addr); } ieee80211_vif_set_links(vlan, add, 0); for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { link = sdata_dereference(vlan->link[link_id], vlan); ieee80211_link_vlan_copy_chanctx(link); } } } void ieee80211_apvlan_link_setup(struct ieee80211_sub_if_data *sdata) { struct ieee80211_sub_if_data *ap_bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); u16 new_links = ap_bss->vif.valid_links; unsigned long add; int link_id; if (!ap_bss->vif.valid_links) return; add = new_links; for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { sdata->wdev.valid_links |= BIT(link_id); ether_addr_copy(sdata->wdev.links[link_id].addr, ap_bss->wdev.links[link_id].addr); } ieee80211_vif_set_links(sdata, new_links, 0); } void ieee80211_apvlan_link_clear(struct ieee80211_sub_if_data *sdata) { if (!sdata->wdev.valid_links) return; sdata->wdev.valid_links = 0; ieee80211_vif_clear_links(sdata); } void ieee80211_link_setup(struct ieee80211_link_data *link) { if (link->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_mgd_setup_link(link); } void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, int link_id, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf) { bool deflink = link_id < 0; if (link_id < 0) link_id = 0; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { struct ieee80211_sub_if_data *ap_bss; struct ieee80211_bss_conf *ap_bss_conf; ap_bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); if (deflink) ap_bss_conf = &ap_bss->vif.bss_conf; else ap_bss_conf = sdata_dereference(ap_bss->vif.link_conf[link_id], ap_bss); memcpy(link_conf, ap_bss_conf, sizeof(*link_conf)); } link->sdata = sdata; link->link_id = link_id; link->conf = link_conf; link_conf->link_id = link_id; link_conf->vif = &sdata->vif; link->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; link->user_power_level = sdata->local->user_power_level; link_conf->txpower = INT_MIN; wiphy_work_init(&link->csa.finalize_work, ieee80211_csa_finalize_work); wiphy_work_init(&link->color_change_finalize_work, ieee80211_color_change_finalize_work); wiphy_delayed_work_init(&link->color_collision_detect_work, ieee80211_color_collision_detection_work); wiphy_hrtimer_work_init(&link->dfs_cac_timer_work, ieee80211_dfs_cac_timer_work); if (!deflink) { switch (sdata->vif.type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: ether_addr_copy(link_conf->addr, sdata->wdev.links[link_id].addr); link_conf->bssid = link_conf->addr; WARN_ON(!(sdata->wdev.valid_links & BIT(link_id))); break; case NL80211_IFTYPE_STATION: /* station sets the bssid in ieee80211_mgd_setup_link */ break; default: WARN_ON(1); } ieee80211_link_debugfs_add(link); } rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf); rcu_assign_pointer(sdata->link[link_id], link); } void ieee80211_link_stop(struct ieee80211_link_data *link) { if (link->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_mgd_stop_link(link); wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, &link->color_collision_detect_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->color_change_finalize_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->csa.finalize_work); if (link->sdata->wdev.links[link->link_id].cac_started) { wiphy_hrtimer_work_cancel(link->sdata->local->hw.wiphy, &link->dfs_cac_timer_work); cfg80211_cac_event(link->sdata->dev, &link->conf->chanreq.oper, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL, link->link_id); } ieee80211_link_release_channel(link); } struct link_container { struct ieee80211_link_data data; struct ieee80211_bss_conf conf; }; static void ieee80211_tear_down_links(struct ieee80211_sub_if_data *sdata, struct link_container **links, u16 mask) { struct ieee80211_link_data *link; LIST_HEAD(keys); unsigned int link_id; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { if (!(mask & BIT(link_id))) continue; link = &links[link_id]->data; if (link_id == 0 && !link) link = &sdata->deflink; if (WARN_ON(!link)) continue; ieee80211_remove_link_keys(link, &keys); ieee80211_link_debugfs_remove(link); ieee80211_link_stop(link); } synchronize_rcu(); ieee80211_free_key_list(sdata->local, &keys); } static void ieee80211_free_links(struct ieee80211_sub_if_data *sdata, struct link_container **links) { unsigned int link_id; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) kfree(links[link_id]); } static int ieee80211_check_dup_link_addrs(struct ieee80211_sub_if_data *sdata) { unsigned int i, j; for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { struct ieee80211_link_data *link1; link1 = sdata_dereference(sdata->link[i], sdata); if (!link1) continue; for (j = i + 1; j < IEEE80211_MLD_MAX_NUM_LINKS; j++) { struct ieee80211_link_data *link2; link2 = sdata_dereference(sdata->link[j], sdata); if (!link2) continue; if (ether_addr_equal(link1->conf->addr, link2->conf->addr)) return -EALREADY; } } return 0; } static void ieee80211_set_vif_links_bitmaps(struct ieee80211_sub_if_data *sdata, u16 valid_links, u16 dormant_links) { sdata->vif.valid_links = valid_links; sdata->vif.dormant_links = dormant_links; if (!valid_links || WARN((~valid_links & dormant_links) || !(valid_links & ~dormant_links), "Invalid links: valid=0x%x, dormant=0x%x", valid_links, dormant_links)) { sdata->vif.active_links = 0; sdata->vif.dormant_links = 0; return; } switch (sdata->vif.type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* in an AP all links are always active */ sdata->vif.active_links = valid_links; /* AP links are not expected to be disabled */ WARN_ON(dormant_links); break; case NL80211_IFTYPE_STATION: if (sdata->vif.active_links) break; sdata->vif.active_links = valid_links & ~dormant_links; WARN_ON(hweight16(sdata->vif.active_links) > 1); break; default: WARN_ON(1); } } static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata, struct link_container **to_free, u16 new_links, u16 dormant_links) { u16 old_links = sdata->vif.valid_links; u16 old_active = sdata->vif.active_links; unsigned long add = new_links & ~old_links; unsigned long rem = old_links & ~new_links; unsigned long sta_rem = rem; unsigned int link_id; int ret; struct link_container *links[IEEE80211_MLD_MAX_NUM_LINKS] = {}, *link; struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]; struct ieee80211_link_data *old_data[IEEE80211_MLD_MAX_NUM_LINKS]; bool use_deflink = old_links == 0; /* set for error case */ bool non_sta = sdata->vif.type != NL80211_IFTYPE_STATION; struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); memset(to_free, 0, sizeof(links)); if (old_links == new_links && dormant_links == sdata->vif.dormant_links) return 0; if (!old_links || !new_links) WARN_ON(sta_info_flush(sdata, -1) > 0); /* if there were no old links, need to clear the pointers to deflink */ if (!old_links) rem |= BIT(0); /* allocate new link structures first */ for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { link = kzalloc_obj(*link); if (!link) { ret = -ENOMEM; goto free; } links[link_id] = link; } /* keep track of the old pointers for the driver */ BUILD_BUG_ON(sizeof(old) != sizeof(sdata->vif.link_conf)); memcpy(old, sdata->vif.link_conf, sizeof(old)); /* and for us in error cases */ BUILD_BUG_ON(sizeof(old_data) != sizeof(sdata->link)); memcpy(old_data, sdata->link, sizeof(old_data)); /* grab old links to free later */ for_each_set_bit(link_id, &rem, IEEE80211_MLD_MAX_NUM_LINKS) { if (rcu_access_pointer(sdata->link[link_id]) != &sdata->deflink) { /* * we must have allocated the data through this path so * we know we can free both at the same time */ to_free[link_id] = container_of(rcu_access_pointer(sdata->link[link_id]), typeof(*links[link_id]), data); } RCU_INIT_POINTER(sdata->link[link_id], NULL); RCU_INIT_POINTER(sdata->vif.link_conf[link_id], NULL); } if (!old_links) ieee80211_debugfs_recreate_netdev(sdata, true); /* link them into data structures */ for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { WARN_ON(!use_deflink && rcu_access_pointer(sdata->link[link_id]) == &sdata->deflink); link = links[link_id]; ieee80211_link_init(sdata, link_id, &link->data, &link->conf); ieee80211_link_setup(&link->data); if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) ieee80211_set_wmm_default(&link->data, true, non_sta); } if (new_links == 0) ieee80211_link_init(sdata, -1, &sdata->deflink, &sdata->vif.bss_conf); ret = ieee80211_check_dup_link_addrs(sdata); if (!ret) { /* for keys we will not be able to undo this */ ieee80211_tear_down_links(sdata, to_free, rem); ieee80211_set_vif_links_bitmaps(sdata, new_links, dormant_links); /* tell the driver */ if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) ret = drv_change_vif_links(sdata->local, sdata, old_links & old_active, new_links & sdata->vif.active_links, old); if (!new_links) ieee80211_debugfs_recreate_netdev(sdata, false); if (sdata->vif.type == NL80211_IFTYPE_AP) ieee80211_update_apvlan_links(sdata); } /* * Ignore errors if we are only removing links as removal should * always succeed */ if (!new_links) ret = 0; if (ret) { /* restore config */ memcpy(sdata->link, old_data, sizeof(old_data)); memcpy(sdata->vif.link_conf, old, sizeof(old)); ieee80211_set_vif_links_bitmaps(sdata, old_links, dormant_links); for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { ieee80211_link_debugfs_remove(&links[link_id]->data); ieee80211_link_stop(&links[link_id]->data); } /* and free (only) the newly allocated links */ memset(to_free, 0, sizeof(links)); goto free; } /* try to remove links that are now invalid from (MLO) stations */ list_for_each_entry(sta, &sdata->local->sta_list, list) { unsigned long rem_links = sta->sta.valid_links & sta_rem; if (sta->sdata != sdata) continue; /* * skip stations that would have no links left, * those will be removed completely later */ if (sta->sta.valid_links == rem_links) continue; for_each_set_bit(link_id, &rem_links, IEEE80211_MLD_MAX_NUM_LINKS) ieee80211_sta_remove_link(sta, link_id); } /* * Remove stations using any removed links. Note that due * to the above station link removal, this only removes * stations that were skipped above because they'd have no * links left after link removal. */ for_each_set_bit(link_id, &sta_rem, IEEE80211_MLD_MAX_NUM_LINKS) sta_info_flush(sdata, link_id); /* use deflink/bss_conf again if and only if there are no more links */ use_deflink = new_links == 0; goto deinit; free: /* if we failed during allocation, only free all */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { kfree(links[link_id]); links[link_id] = NULL; } deinit: if (use_deflink) ieee80211_link_init(sdata, -1, &sdata->deflink, &sdata->vif.bss_conf); return ret; } int ieee80211_vif_set_links(struct ieee80211_sub_if_data *sdata, u16 new_links, u16 dormant_links) { struct link_container *links[IEEE80211_MLD_MAX_NUM_LINKS]; int ret; ret = ieee80211_vif_update_links(sdata, links, new_links, dormant_links); ieee80211_free_links(sdata, links); return ret; } static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, u16 active_links) { struct ieee80211_bss_conf *link_confs[IEEE80211_MLD_MAX_NUM_LINKS]; struct ieee80211_local *local = sdata->local; u16 old_active = sdata->vif.active_links; unsigned long rem = old_active & ~active_links; unsigned long add = active_links & ~old_active; struct sta_info *sta; unsigned int link_id; int ret, i; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EINVAL; if (active_links & ~ieee80211_vif_usable_links(&sdata->vif)) return -EINVAL; /* nothing to do */ if (old_active == active_links) return 0; for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) link_confs[i] = sdata_dereference(sdata->vif.link_conf[i], sdata); if (add) { sdata->vif.active_links |= active_links; ret = drv_change_vif_links(local, sdata, old_active, sdata->vif.active_links, link_confs); if (ret) { sdata->vif.active_links = old_active; return ret; } } for_each_set_bit(link_id, &rem, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_teardown_tdls_peers(link); __ieee80211_link_release_channel(link, true); /* * If CSA is (still) active while the link is deactivated, * just schedule the channel switch work for the time we * had previously calculated, and we'll take the process * from there. */ if (link->conf->csa_active) wiphy_hrtimer_work_queue(local->hw.wiphy, &link->u.mgd.csa.switch_work, link->u.mgd.csa.time - ktime_get_boottime()); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); /* * This call really should not fail. Unfortunately, it appears * that this may happen occasionally with some drivers. Should * it happen, we are stuck in a bad place as going backwards is * not really feasible. * * So lets just tell link_use_channel that it must not fail to * assign the channel context (from mac80211's perspective) and * assume the driver is going to trigger a recovery flow if it * had a failure. * That really is not great nor guaranteed to work. But at least * the internal mac80211 state remains consistent and there is * a chance that we can recover. */ ret = _ieee80211_link_use_channel(link, &link->conf->chanreq, IEEE80211_CHANCTX_SHARED, true); WARN_ON_ONCE(ret); /* * inform about the link info changed parameters after all * stations are also added */ } list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; /* this is very temporary, but do it anyway */ __ieee80211_sta_recalc_aggregates(sta, old_active | active_links); ret = drv_change_sta_links(local, sdata, &sta->sta, old_active, old_active | active_links); WARN_ON_ONCE(ret); } ret = ieee80211_key_switch_links(sdata, rem, add); WARN_ON_ONCE(ret); list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; __ieee80211_sta_recalc_aggregates(sta, active_links); ret = drv_change_sta_links(local, sdata, &sta->sta, old_active | active_links, active_links); WARN_ON_ONCE(ret); /* * Do it again, just in case - the driver might very * well have called ieee80211_sta_recalc_aggregates() * from there when filling in the new links, which * would set it wrong since the vif's active links are * not switched yet... */ __ieee80211_sta_recalc_aggregates(sta, active_links); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_mgd_set_link_qos_params(link); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_ERP_PREAMBLE | BSS_CHANGED_ERP_SLOT | BSS_CHANGED_HT | BSS_CHANGED_BASIC_RATES | BSS_CHANGED_BSSID | BSS_CHANGED_CQM | BSS_CHANGED_QOS | BSS_CHANGED_TXPOWER | BSS_CHANGED_BANDWIDTH | BSS_CHANGED_TWT | BSS_CHANGED_HE_OBSS_PD | BSS_CHANGED_HE_BSS_COLOR); } old_active = sdata->vif.active_links; sdata->vif.active_links = active_links; if (rem) { ret = drv_change_vif_links(local, sdata, old_active, active_links, link_confs); WARN_ON_ONCE(ret); } return 0; } int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; u16 old_active; int ret; lockdep_assert_wiphy(local->hw.wiphy); if (WARN_ON(!active_links)) return -EINVAL; old_active = sdata->vif.active_links; if (old_active == active_links) return 0; if (!drv_can_activate_links(local, sdata, active_links)) return -EINVAL; if (old_active & active_links) { /* * if there's at least one link that stays active across * the change then switch to it (to those) first, and * then enable the additional links */ ret = _ieee80211_set_active_links(sdata, old_active & active_links); if (!ret) ret = _ieee80211_set_active_links(sdata, active_links); } else { /* otherwise switch directly */ ret = _ieee80211_set_active_links(sdata, active_links); } return ret; } EXPORT_SYMBOL_GPL(ieee80211_set_active_links); void ieee80211_set_active_links_async(struct ieee80211_vif *vif, u16 active_links) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (WARN_ON(!active_links)) return; if (!ieee80211_sdata_running(sdata)) return; if (sdata->vif.type != NL80211_IFTYPE_STATION) return; if (active_links & ~ieee80211_vif_usable_links(&sdata->vif)) return; /* nothing to do */ if (sdata->vif.active_links == active_links) return; sdata->desired_active_links = active_links; wiphy_work_queue(sdata->local->hw.wiphy, &sdata->activate_links_work); } EXPORT_SYMBOL_GPL(ieee80211_set_active_links_async); |
| 9 14 14 5 5 8 8 2 2 2 2 2 7 7 8 7 7 7 7 7 6 6 5 5 2 5 16 5 14 2 2 24 24 24 13 10 10 10 10 10 10 10 24 24 13 13 4 24 24 13 24 24 13 13 24 13 13 13 13 10 10 2 5 5 7 12 1 12 12 8 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 | /* * JFFS2 -- Journalling Flash File System, Version 2. * * Copyright © 2006 NEC Corporation * * Created by KaiGai Kohei <kaigai@ak.jp.nec.com> * * For licensing information, see the file 'LICENCE' in this directory. * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define JFFS2_XATTR_IS_CORRUPTED 1 #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/crc32.h> #include <linux/jffs2.h> #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> #include <linux/mtd/mtd.h> #include "nodelist.h" /* -------- xdatum related functions ---------------- * xattr_datum_hashkey(xprefix, xname, xvalue, xsize) * is used to calcurate xdatum hashkey. The reminder of hashkey into XATTRINDEX_HASHSIZE is * the index of the xattr name/value pair cache (c->xattrindex). * is_xattr_datum_unchecked(c, xd) * returns 1, if xdatum contains any unchecked raw nodes. if all raw nodes are not * unchecked, it returns 0. * unload_xattr_datum(c, xd) * is used to release xattr name/value pair and detach from c->xattrindex. * reclaim_xattr_datum(c) * is used to reclaim xattr name/value pairs on the xattr name/value pair cache when * memory usage by cache is over c->xdatum_mem_threshold. Currently, this threshold * is hard coded as 32KiB. * do_verify_xattr_datum(c, xd) * is used to load the xdatum informations without name/value pair from the medium. * It's necessary once, because those informations are not collected during mounting * process when EBS is enabled. * 0 will be returned, if success. An negative return value means recoverable error, and * positive return value means unrecoverable error. Thus, caller must remove this xdatum * and xref when it returned positive value. * do_load_xattr_datum(c, xd) * is used to load name/value pair from the medium. * The meanings of return value is same as do_verify_xattr_datum(). * load_xattr_datum(c, xd) * is used to be as a wrapper of do_verify_xattr_datum() and do_load_xattr_datum(). * If xd need to call do_verify_xattr_datum() at first, it's called before calling * do_load_xattr_datum(). The meanings of return value is same as do_verify_xattr_datum(). * save_xattr_datum(c, xd) * is used to write xdatum to medium. xd->version will be incremented. * create_xattr_datum(c, xprefix, xname, xvalue, xsize) * is used to create new xdatum and write to medium. * unrefer_xattr_datum(c, xd) * is used to delete a xdatum. When nobody refers this xdatum, JFFS2_XFLAGS_DEAD * is set on xd->flags and chained xattr_dead_list or release it immediately. * In the first case, the garbage collector release it later. * -------------------------------------------------- */ static uint32_t xattr_datum_hashkey(int xprefix, const char *xname, const char *xvalue, int xsize) { int name_len = strlen(xname); return crc32(xprefix, xname, name_len) ^ crc32(xprefix, xvalue, xsize); } static int is_xattr_datum_unchecked(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { struct jffs2_raw_node_ref *raw; int rc = 0; spin_lock(&c->erase_completion_lock); for (raw=xd->node; raw != (void *)xd; raw=raw->next_in_ino) { if (ref_flags(raw) == REF_UNCHECKED) { rc = 1; break; } } spin_unlock(&c->erase_completion_lock); return rc; } static void unload_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem) */ D1(dbg_xattr("%s: xid=%u, version=%u\n", __func__, xd->xid, xd->version)); if (xd->xname) { c->xdatum_mem_usage -= (xd->name_len + 1 + xd->value_len); kfree(xd->xname); } list_del_init(&xd->xindex); xd->hashkey = 0; xd->xname = NULL; xd->xvalue = NULL; } static void reclaim_xattr_datum(struct jffs2_sb_info *c) { /* must be called under down_write(xattr_sem) */ struct jffs2_xattr_datum *xd, *_xd; uint32_t target, before; static int index = 0; int count; if (c->xdatum_mem_threshold > c->xdatum_mem_usage) return; before = c->xdatum_mem_usage; target = c->xdatum_mem_usage * 4 / 5; /* 20% reduction */ for (count = 0; count < XATTRINDEX_HASHSIZE; count++) { list_for_each_entry_safe(xd, _xd, &c->xattrindex[index], xindex) { if (xd->flags & JFFS2_XFLAGS_HOT) { xd->flags &= ~JFFS2_XFLAGS_HOT; } else if (!(xd->flags & JFFS2_XFLAGS_BIND)) { unload_xattr_datum(c, xd); } if (c->xdatum_mem_usage <= target) goto out; } index = (index+1) % XATTRINDEX_HASHSIZE; } out: JFFS2_NOTICE("xdatum_mem_usage from %u byte to %u byte (%u byte reclaimed)\n", before, c->xdatum_mem_usage, before - c->xdatum_mem_usage); } static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem) */ struct jffs2_eraseblock *jeb; struct jffs2_raw_node_ref *raw; struct jffs2_raw_xattr rx; size_t readlen; uint32_t crc, offset, totlen; int rc; spin_lock(&c->erase_completion_lock); offset = ref_offset(xd->node); if (ref_flags(xd->node) == REF_PRISTINE) goto complete; spin_unlock(&c->erase_completion_lock); rc = jffs2_flash_read(c, offset, sizeof(rx), &readlen, (char *)&rx); if (rc || readlen != sizeof(rx)) { JFFS2_WARNING("jffs2_flash_read()=%d, req=%zu, read=%zu at %#08x\n", rc, sizeof(rx), readlen, offset); return rc ? rc : -EIO; } crc = crc32(0, &rx, sizeof(rx) - 4); if (crc != je32_to_cpu(rx.node_crc)) { JFFS2_ERROR("node CRC failed at %#08x, read=%#08x, calc=%#08x\n", offset, je32_to_cpu(rx.hdr_crc), crc); xd->flags |= JFFS2_XFLAGS_INVALID; return JFFS2_XATTR_IS_CORRUPTED; } totlen = PAD(sizeof(rx) + rx.name_len + 1 + je16_to_cpu(rx.value_len)); if (je16_to_cpu(rx.magic) != JFFS2_MAGIC_BITMASK || je16_to_cpu(rx.nodetype) != JFFS2_NODETYPE_XATTR || je32_to_cpu(rx.totlen) != totlen || je32_to_cpu(rx.xid) != xd->xid || je32_to_cpu(rx.version) != xd->version) { JFFS2_ERROR("inconsistent xdatum at %#08x, magic=%#04x/%#04x, " "nodetype=%#04x/%#04x, totlen=%u/%u, xid=%u/%u, version=%u/%u\n", offset, je16_to_cpu(rx.magic), JFFS2_MAGIC_BITMASK, je16_to_cpu(rx.nodetype), JFFS2_NODETYPE_XATTR, je32_to_cpu(rx.totlen), totlen, je32_to_cpu(rx.xid), xd->xid, je32_to_cpu(rx.version), xd->version); xd->flags |= JFFS2_XFLAGS_INVALID; return JFFS2_XATTR_IS_CORRUPTED; } xd->xprefix = rx.xprefix; xd->name_len = rx.name_len; xd->value_len = je16_to_cpu(rx.value_len); xd->data_crc = je32_to_cpu(rx.data_crc); spin_lock(&c->erase_completion_lock); complete: for (raw=xd->node; raw != (void *)xd; raw=raw->next_in_ino) { jeb = &c->blocks[ref_offset(raw) / c->sector_size]; totlen = PAD(ref_totlen(c, jeb, raw)); if (ref_flags(raw) == REF_UNCHECKED) { c->unchecked_size -= totlen; c->used_size += totlen; jeb->unchecked_size -= totlen; jeb->used_size += totlen; } raw->flash_offset = ref_offset(raw) | ((xd->node==raw) ? REF_PRISTINE : REF_NORMAL); } spin_unlock(&c->erase_completion_lock); /* unchecked xdatum is chained with c->xattr_unchecked */ list_del_init(&xd->xindex); dbg_xattr("success on verifying xdatum (xid=%u, version=%u)\n", xd->xid, xd->version); return 0; } static int do_load_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem) */ char *data; size_t readlen; uint32_t crc, length; int i, ret, retry = 0; BUG_ON(ref_flags(xd->node) != REF_PRISTINE); BUG_ON(!list_empty(&xd->xindex)); retry: length = xd->name_len + 1 + xd->value_len; data = kmalloc(length, GFP_KERNEL); if (!data) return -ENOMEM; ret = jffs2_flash_read(c, ref_offset(xd->node)+sizeof(struct jffs2_raw_xattr), length, &readlen, data); if (ret || length!=readlen) { JFFS2_WARNING("jffs2_flash_read() returned %d, request=%d, readlen=%zu, at %#08x\n", ret, length, readlen, ref_offset(xd->node)); kfree(data); return ret ? ret : -EIO; } data[xd->name_len] = '\0'; crc = crc32(0, data, length); if (crc != xd->data_crc) { JFFS2_WARNING("node CRC failed (JFFS2_NODETYPE_XATTR)" " at %#08x, read: 0x%08x calculated: 0x%08x\n", ref_offset(xd->node), xd->data_crc, crc); kfree(data); xd->flags |= JFFS2_XFLAGS_INVALID; return JFFS2_XATTR_IS_CORRUPTED; } xd->flags |= JFFS2_XFLAGS_HOT; xd->xname = data; xd->xvalue = data + xd->name_len+1; c->xdatum_mem_usage += length; xd->hashkey = xattr_datum_hashkey(xd->xprefix, xd->xname, xd->xvalue, xd->value_len); i = xd->hashkey % XATTRINDEX_HASHSIZE; list_add(&xd->xindex, &c->xattrindex[i]); if (!retry) { retry = 1; reclaim_xattr_datum(c); if (!xd->xname) goto retry; } dbg_xattr("success on loading xdatum (xid=%u, xprefix=%u, xname='%s')\n", xd->xid, xd->xprefix, xd->xname); return 0; } static int load_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem); * rc < 0 : recoverable error, try again * rc = 0 : success * rc > 0 : Unrecoverable error, this node should be deleted. */ int rc = 0; BUG_ON(xd->flags & JFFS2_XFLAGS_DEAD); if (xd->xname) return 0; if (xd->flags & JFFS2_XFLAGS_INVALID) return JFFS2_XATTR_IS_CORRUPTED; if (unlikely(is_xattr_datum_unchecked(c, xd))) rc = do_verify_xattr_datum(c, xd); if (!rc) rc = do_load_xattr_datum(c, xd); return rc; } static int save_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem) */ struct jffs2_raw_xattr rx; struct kvec vecs[2]; size_t length; int rc, totlen; uint32_t phys_ofs = write_ofs(c); BUG_ON(!xd->xname); BUG_ON(xd->flags & (JFFS2_XFLAGS_DEAD|JFFS2_XFLAGS_INVALID)); vecs[0].iov_base = ℞ vecs[0].iov_len = sizeof(rx); vecs[1].iov_base = xd->xname; vecs[1].iov_len = xd->name_len + 1 + xd->value_len; totlen = vecs[0].iov_len + vecs[1].iov_len; /* Setup raw-xattr */ memset(&rx, 0, sizeof(rx)); rx.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); rx.nodetype = cpu_to_je16(JFFS2_NODETYPE_XATTR); rx.totlen = cpu_to_je32(PAD(totlen)); rx.hdr_crc = cpu_to_je32(crc32(0, &rx, sizeof(struct jffs2_unknown_node) - 4)); rx.xid = cpu_to_je32(xd->xid); rx.version = cpu_to_je32(++xd->version); rx.xprefix = xd->xprefix; rx.name_len = xd->name_len; rx.value_len = cpu_to_je16(xd->value_len); rx.data_crc = cpu_to_je32(crc32(0, vecs[1].iov_base, vecs[1].iov_len)); rx.node_crc = cpu_to_je32(crc32(0, &rx, sizeof(struct jffs2_raw_xattr) - 4)); rc = jffs2_flash_writev(c, vecs, 2, phys_ofs, &length, 0); if (rc || totlen != length) { JFFS2_WARNING("jffs2_flash_writev()=%d, req=%u, wrote=%zu, at %#08x\n", rc, totlen, length, phys_ofs); rc = rc ? rc : -EIO; if (length) jffs2_add_physical_node_ref(c, phys_ofs | REF_OBSOLETE, PAD(totlen), NULL); return rc; } /* success */ jffs2_add_physical_node_ref(c, phys_ofs | REF_PRISTINE, PAD(totlen), (void *)xd); dbg_xattr("success on saving xdatum (xid=%u, version=%u, xprefix=%u, xname='%s')\n", xd->xid, xd->version, xd->xprefix, xd->xname); return 0; } static struct jffs2_xattr_datum *create_xattr_datum(struct jffs2_sb_info *c, int xprefix, const char *xname, const char *xvalue, int xsize) { /* must be called under down_write(xattr_sem) */ struct jffs2_xattr_datum *xd; uint32_t hashkey, name_len; char *data; int i, rc; /* Search xattr_datum has same xname/xvalue by index */ hashkey = xattr_datum_hashkey(xprefix, xname, xvalue, xsize); i = hashkey % XATTRINDEX_HASHSIZE; list_for_each_entry(xd, &c->xattrindex[i], xindex) { if (xd->hashkey==hashkey && xd->xprefix==xprefix && xd->value_len==xsize && !strcmp(xd->xname, xname) && !memcmp(xd->xvalue, xvalue, xsize)) { atomic_inc(&xd->refcnt); return xd; } } /* Not found, Create NEW XATTR-Cache */ name_len = strlen(xname); xd = jffs2_alloc_xattr_datum(); if (!xd) return ERR_PTR(-ENOMEM); data = kmalloc(name_len + 1 + xsize, GFP_KERNEL); if (!data) { jffs2_free_xattr_datum(xd); return ERR_PTR(-ENOMEM); } strcpy(data, xname); memcpy(data + name_len + 1, xvalue, xsize); atomic_set(&xd->refcnt, 1); xd->xid = ++c->highest_xid; xd->flags |= JFFS2_XFLAGS_HOT; xd->xprefix = xprefix; xd->hashkey = hashkey; xd->xname = data; xd->xvalue = data + name_len + 1; xd->name_len = name_len; xd->value_len = xsize; xd->data_crc = crc32(0, data, xd->name_len + 1 + xd->value_len); rc = save_xattr_datum(c, xd); if (rc) { kfree(xd->xname); jffs2_free_xattr_datum(xd); return ERR_PTR(rc); } /* Insert Hash Index */ i = hashkey % XATTRINDEX_HASHSIZE; list_add(&xd->xindex, &c->xattrindex[i]); c->xdatum_mem_usage += (xd->name_len + 1 + xd->value_len); reclaim_xattr_datum(c); return xd; } static void unrefer_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem) */ if (atomic_dec_and_lock(&xd->refcnt, &c->erase_completion_lock)) { unload_xattr_datum(c, xd); xd->flags |= JFFS2_XFLAGS_DEAD; if (xd->node == (void *)xd) { BUG_ON(!(xd->flags & JFFS2_XFLAGS_INVALID)); jffs2_free_xattr_datum(xd); } else { list_add(&xd->xindex, &c->xattr_dead_list); } spin_unlock(&c->erase_completion_lock); dbg_xattr("xdatum(xid=%u, version=%u) was removed.\n", xd->xid, xd->version); } } /* -------- xref related functions ------------------ * verify_xattr_ref(c, ref) * is used to load xref information from medium. Because summary data does not * contain xid/ino, it's necessary to verify once while mounting process. * save_xattr_ref(c, ref) * is used to write xref to medium. If delete marker is marked, it write * a delete marker of xref into medium. * create_xattr_ref(c, ic, xd) * is used to create a new xref and write to medium. * delete_xattr_ref(c, ref) * is used to delete jffs2_xattr_ref. It marks xref XREF_DELETE_MARKER, * and allows GC to reclaim those physical nodes. * jffs2_xattr_delete_inode(c, ic) * is called to remove xrefs related to obsolete inode when inode is unlinked. * jffs2_xattr_free_inode(c, ic) * is called to release xattr related objects when unmounting. * check_xattr_ref_inode(c, ic) * is used to confirm inode does not have duplicate xattr name/value pair. * jffs2_xattr_do_crccheck_inode(c, ic) * is used to force xattr data integrity check during the initial gc scan. * -------------------------------------------------- */ static int verify_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref) { struct jffs2_eraseblock *jeb; struct jffs2_raw_node_ref *raw; struct jffs2_raw_xref rr; size_t readlen; uint32_t crc, offset, totlen; int rc; spin_lock(&c->erase_completion_lock); if (ref_flags(ref->node) != REF_UNCHECKED) goto complete; offset = ref_offset(ref->node); spin_unlock(&c->erase_completion_lock); rc = jffs2_flash_read(c, offset, sizeof(rr), &readlen, (char *)&rr); if (rc || sizeof(rr) != readlen) { JFFS2_WARNING("jffs2_flash_read()=%d, req=%zu, read=%zu, at %#08x\n", rc, sizeof(rr), readlen, offset); return rc ? rc : -EIO; } /* obsolete node */ crc = crc32(0, &rr, sizeof(rr) - 4); if (crc != je32_to_cpu(rr.node_crc)) { JFFS2_ERROR("node CRC failed at %#08x, read=%#08x, calc=%#08x\n", offset, je32_to_cpu(rr.node_crc), crc); return JFFS2_XATTR_IS_CORRUPTED; } if (je16_to_cpu(rr.magic) != JFFS2_MAGIC_BITMASK || je16_to_cpu(rr.nodetype) != JFFS2_NODETYPE_XREF || je32_to_cpu(rr.totlen) != PAD(sizeof(rr))) { JFFS2_ERROR("inconsistent xref at %#08x, magic=%#04x/%#04x, " "nodetype=%#04x/%#04x, totlen=%u/%zu\n", offset, je16_to_cpu(rr.magic), JFFS2_MAGIC_BITMASK, je16_to_cpu(rr.nodetype), JFFS2_NODETYPE_XREF, je32_to_cpu(rr.totlen), PAD(sizeof(rr))); return JFFS2_XATTR_IS_CORRUPTED; } ref->ino = je32_to_cpu(rr.ino); ref->xid = je32_to_cpu(rr.xid); ref->xseqno = je32_to_cpu(rr.xseqno); if (ref->xseqno > c->highest_xseqno) c->highest_xseqno = (ref->xseqno & ~XREF_DELETE_MARKER); spin_lock(&c->erase_completion_lock); complete: for (raw=ref->node; raw != (void *)ref; raw=raw->next_in_ino) { jeb = &c->blocks[ref_offset(raw) / c->sector_size]; totlen = PAD(ref_totlen(c, jeb, raw)); if (ref_flags(raw) == REF_UNCHECKED) { c->unchecked_size -= totlen; c->used_size += totlen; jeb->unchecked_size -= totlen; jeb->used_size += totlen; } raw->flash_offset = ref_offset(raw) | ((ref->node==raw) ? REF_PRISTINE : REF_NORMAL); } spin_unlock(&c->erase_completion_lock); dbg_xattr("success on verifying xref (ino=%u, xid=%u) at %#08x\n", ref->ino, ref->xid, ref_offset(ref->node)); return 0; } static int save_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref) { /* must be called under down_write(xattr_sem) */ struct jffs2_raw_xref rr; size_t length; uint32_t xseqno, phys_ofs = write_ofs(c); int ret; rr.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); rr.nodetype = cpu_to_je16(JFFS2_NODETYPE_XREF); rr.totlen = cpu_to_je32(PAD(sizeof(rr))); rr.hdr_crc = cpu_to_je32(crc32(0, &rr, sizeof(struct jffs2_unknown_node) - 4)); xseqno = (c->highest_xseqno += 2); if (is_xattr_ref_dead(ref)) { xseqno |= XREF_DELETE_MARKER; rr.ino = cpu_to_je32(ref->ino); rr.xid = cpu_to_je32(ref->xid); } else { rr.ino = cpu_to_je32(ref->ic->ino); rr.xid = cpu_to_je32(ref->xd->xid); } rr.xseqno = cpu_to_je32(xseqno); rr.node_crc = cpu_to_je32(crc32(0, &rr, sizeof(rr) - 4)); ret = jffs2_flash_write(c, phys_ofs, sizeof(rr), &length, (char *)&rr); if (ret || sizeof(rr) != length) { JFFS2_WARNING("jffs2_flash_write() returned %d, request=%zu, retlen=%zu, at %#08x\n", ret, sizeof(rr), length, phys_ofs); ret = ret ? ret : -EIO; if (length) jffs2_add_physical_node_ref(c, phys_ofs | REF_OBSOLETE, PAD(sizeof(rr)), NULL); return ret; } /* success */ ref->xseqno = xseqno; jffs2_add_physical_node_ref(c, phys_ofs | REF_PRISTINE, PAD(sizeof(rr)), (void *)ref); dbg_xattr("success on saving xref (ino=%u, xid=%u)\n", ref->ic->ino, ref->xd->xid); return 0; } static struct jffs2_xattr_ref *create_xattr_ref(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic, struct jffs2_xattr_datum *xd) { /* must be called under down_write(xattr_sem) */ struct jffs2_xattr_ref *ref; int ret; ref = jffs2_alloc_xattr_ref(); if (!ref) return ERR_PTR(-ENOMEM); ref->ic = ic; ref->xd = xd; ret = save_xattr_ref(c, ref); if (ret) { jffs2_free_xattr_ref(ref); return ERR_PTR(ret); } /* Chain to inode */ ref->next = ic->xref; ic->xref = ref; return ref; /* success */ } static void delete_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref) { /* must be called under down_write(xattr_sem) */ struct jffs2_xattr_datum *xd; xd = ref->xd; ref->xseqno |= XREF_DELETE_MARKER; ref->ino = ref->ic->ino; ref->xid = ref->xd->xid; spin_lock(&c->erase_completion_lock); ref->next = c->xref_dead_list; c->xref_dead_list = ref; spin_unlock(&c->erase_completion_lock); dbg_xattr("xref(ino=%u, xid=%u, xseqno=%u) was removed.\n", ref->ino, ref->xid, ref->xseqno); unrefer_xattr_datum(c, xd); } void jffs2_xattr_delete_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic) { /* It's called from jffs2_evict_inode() on inode removing. When an inode with XATTR is removed, those XATTRs must be removed. */ struct jffs2_xattr_ref *ref, *_ref; if (!ic || ic->pino_nlink > 0) return; down_write(&c->xattr_sem); for (ref = ic->xref; ref; ref = _ref) { _ref = ref->next; delete_xattr_ref(c, ref); } ic->xref = NULL; up_write(&c->xattr_sem); } void jffs2_xattr_free_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic) { /* It's called from jffs2_free_ino_caches() until unmounting FS. */ struct jffs2_xattr_datum *xd; struct jffs2_xattr_ref *ref, *_ref; down_write(&c->xattr_sem); for (ref = ic->xref; ref; ref = _ref) { _ref = ref->next; xd = ref->xd; if (atomic_dec_and_test(&xd->refcnt)) { unload_xattr_datum(c, xd); jffs2_free_xattr_datum(xd); } jffs2_free_xattr_ref(ref); } ic->xref = NULL; up_write(&c->xattr_sem); } static int check_xattr_ref_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic) { /* success of check_xattr_ref_inode() means that inode (ic) dose not have * duplicate name/value pairs. If duplicate name/value pair would be found, * one will be removed. */ struct jffs2_xattr_ref *ref, *cmp, **pref, **pcmp; int rc = 0; if (likely(ic->flags & INO_FLAGS_XATTR_CHECKED)) return 0; down_write(&c->xattr_sem); retry: rc = 0; for (ref=ic->xref, pref=&ic->xref; ref; pref=&ref->next, ref=ref->next) { if (!ref->xd->xname) { rc = load_xattr_datum(c, ref->xd); if (unlikely(rc > 0)) { *pref = ref->next; delete_xattr_ref(c, ref); goto retry; } else if (unlikely(rc < 0)) goto out; } for (cmp=ref->next, pcmp=&ref->next; cmp; pcmp=&cmp->next, cmp=cmp->next) { if (!cmp->xd->xname) { ref->xd->flags |= JFFS2_XFLAGS_BIND; rc = load_xattr_datum(c, cmp->xd); ref->xd->flags &= ~JFFS2_XFLAGS_BIND; if (unlikely(rc > 0)) { *pcmp = cmp->next; delete_xattr_ref(c, cmp); goto retry; } else if (unlikely(rc < 0)) goto out; } if (ref->xd->xprefix == cmp->xd->xprefix && !strcmp(ref->xd->xname, cmp->xd->xname)) { if (ref->xseqno > cmp->xseqno) { *pcmp = cmp->next; delete_xattr_ref(c, cmp); } else { *pref = ref->next; delete_xattr_ref(c, ref); } goto retry; } } } ic->flags |= INO_FLAGS_XATTR_CHECKED; out: up_write(&c->xattr_sem); return rc; } void jffs2_xattr_do_crccheck_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic) { check_xattr_ref_inode(c, ic); } /* -------- xattr subsystem functions --------------- * jffs2_init_xattr_subsystem(c) * is used to initialize semaphore and list_head, and some variables. * jffs2_find_xattr_datum(c, xid) * is used to lookup xdatum while scanning process. * jffs2_clear_xattr_subsystem(c) * is used to release any xattr related objects. * jffs2_build_xattr_subsystem(c) * is used to associate xdatum and xref while super block building process. * jffs2_setup_xattr_datum(c, xid, version) * is used to insert xdatum while scanning process. * -------------------------------------------------- */ void jffs2_init_xattr_subsystem(struct jffs2_sb_info *c) { int i; for (i=0; i < XATTRINDEX_HASHSIZE; i++) INIT_LIST_HEAD(&c->xattrindex[i]); INIT_LIST_HEAD(&c->xattr_unchecked); INIT_LIST_HEAD(&c->xattr_dead_list); c->xref_dead_list = NULL; c->xref_temp = NULL; init_rwsem(&c->xattr_sem); c->highest_xid = 0; c->highest_xseqno = 0; c->xdatum_mem_usage = 0; c->xdatum_mem_threshold = 32 * 1024; /* Default 32KB */ } static struct jffs2_xattr_datum *jffs2_find_xattr_datum(struct jffs2_sb_info *c, uint32_t xid) { struct jffs2_xattr_datum *xd; int i = xid % XATTRINDEX_HASHSIZE; /* It's only used in scanning/building process. */ BUG_ON(!(c->flags & (JFFS2_SB_FLAG_SCANNING|JFFS2_SB_FLAG_BUILDING))); list_for_each_entry(xd, &c->xattrindex[i], xindex) { if (xd->xid==xid) return xd; } return NULL; } void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c) { struct jffs2_xattr_datum *xd, *_xd; struct jffs2_xattr_ref *ref, *_ref; int i; for (ref=c->xref_temp; ref; ref = _ref) { _ref = ref->next; jffs2_free_xattr_ref(ref); } for (ref=c->xref_dead_list; ref; ref = _ref) { _ref = ref->next; jffs2_free_xattr_ref(ref); } for (i=0; i < XATTRINDEX_HASHSIZE; i++) { list_for_each_entry_safe(xd, _xd, &c->xattrindex[i], xindex) { list_del(&xd->xindex); kfree(xd->xname); jffs2_free_xattr_datum(xd); } } list_for_each_entry_safe(xd, _xd, &c->xattr_dead_list, xindex) { list_del(&xd->xindex); jffs2_free_xattr_datum(xd); } list_for_each_entry_safe(xd, _xd, &c->xattr_unchecked, xindex) { list_del(&xd->xindex); jffs2_free_xattr_datum(xd); } } #define XREF_TMPHASH_SIZE (128) int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) { struct jffs2_xattr_ref *ref, *_ref; struct jffs2_xattr_ref **xref_tmphash; struct jffs2_xattr_datum *xd, *_xd; struct jffs2_inode_cache *ic; struct jffs2_raw_node_ref *raw; int i, xdatum_count = 0, xdatum_unchecked_count = 0, xref_count = 0; int xdatum_orphan_count = 0, xref_orphan_count = 0, xref_dead_count = 0; BUG_ON(!(c->flags & JFFS2_SB_FLAG_BUILDING)); xref_tmphash = kzalloc_objs(struct jffs2_xattr_ref *, XREF_TMPHASH_SIZE); if (!xref_tmphash) return -ENOMEM; /* Phase.1 : Merge same xref */ for (ref=c->xref_temp; ref; ref=_ref) { struct jffs2_xattr_ref *tmp; _ref = ref->next; if (ref_flags(ref->node) != REF_PRISTINE) { if (verify_xattr_ref(c, ref)) { BUG_ON(ref->node->next_in_ino != (void *)ref); ref->node->next_in_ino = NULL; jffs2_mark_node_obsolete(c, ref->node); jffs2_free_xattr_ref(ref); continue; } } i = (ref->ino ^ ref->xid) % XREF_TMPHASH_SIZE; for (tmp=xref_tmphash[i]; tmp; tmp=tmp->next) { if (tmp->ino == ref->ino && tmp->xid == ref->xid) break; } if (tmp) { raw = ref->node; if (ref->xseqno > tmp->xseqno) { tmp->xseqno = ref->xseqno; raw->next_in_ino = tmp->node; tmp->node = raw; } else { raw->next_in_ino = tmp->node->next_in_ino; tmp->node->next_in_ino = raw; } jffs2_free_xattr_ref(ref); continue; } else { ref->next = xref_tmphash[i]; xref_tmphash[i] = ref; } } c->xref_temp = NULL; /* Phase.2 : Bind xref with inode_cache and xattr_datum */ for (i=0; i < XREF_TMPHASH_SIZE; i++) { for (ref=xref_tmphash[i]; ref; ref=_ref) { xref_count++; _ref = ref->next; if (is_xattr_ref_dead(ref)) { ref->next = c->xref_dead_list; c->xref_dead_list = ref; xref_dead_count++; continue; } /* At this point, ref->xid and ref->ino contain XID and inode number. ref->xd and ref->ic are not valid yet. */ xd = jffs2_find_xattr_datum(c, ref->xid); ic = jffs2_get_ino_cache(c, ref->ino); if (!xd || !ic || !ic->pino_nlink) { dbg_xattr("xref(ino=%u, xid=%u, xseqno=%u) is orphan.\n", ref->ino, ref->xid, ref->xseqno); ref->xseqno |= XREF_DELETE_MARKER; ref->next = c->xref_dead_list; c->xref_dead_list = ref; xref_orphan_count++; continue; } ref->xd = xd; ref->ic = ic; atomic_inc(&xd->refcnt); ref->next = ic->xref; ic->xref = ref; } } /* Phase.3 : Link unchecked xdatum to xattr_unchecked list */ for (i=0; i < XATTRINDEX_HASHSIZE; i++) { list_for_each_entry_safe(xd, _xd, &c->xattrindex[i], xindex) { xdatum_count++; list_del_init(&xd->xindex); if (!atomic_read(&xd->refcnt)) { dbg_xattr("xdatum(xid=%u, version=%u) is orphan.\n", xd->xid, xd->version); xd->flags |= JFFS2_XFLAGS_DEAD; list_add(&xd->xindex, &c->xattr_unchecked); xdatum_orphan_count++; continue; } if (is_xattr_datum_unchecked(c, xd)) { dbg_xattr("unchecked xdatum(xid=%u, version=%u)\n", xd->xid, xd->version); list_add(&xd->xindex, &c->xattr_unchecked); xdatum_unchecked_count++; } } } /* build complete */ JFFS2_NOTICE("complete building xattr subsystem, %u of xdatum" " (%u unchecked, %u orphan) and " "%u of xref (%u dead, %u orphan) found.\n", xdatum_count, xdatum_unchecked_count, xdatum_orphan_count, xref_count, xref_dead_count, xref_orphan_count); kfree(xref_tmphash); return 0; } struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, uint32_t xid, uint32_t version) { struct jffs2_xattr_datum *xd; xd = jffs2_find_xattr_datum(c, xid); if (!xd) { xd = jffs2_alloc_xattr_datum(); if (!xd) return ERR_PTR(-ENOMEM); xd->xid = xid; xd->version = version; if (xd->xid > c->highest_xid) c->highest_xid = xd->xid; list_add_tail(&xd->xindex, &c->xattrindex[xid % XATTRINDEX_HASHSIZE]); } return xd; } /* -------- xattr subsystem functions --------------- * xprefix_to_handler(xprefix) * is used to translate xprefix into xattr_handler. * jffs2_listxattr(dentry, buffer, size) * is an implementation of listxattr handler on jffs2. * do_jffs2_getxattr(inode, xprefix, xname, buffer, size) * is an implementation of getxattr handler on jffs2. * do_jffs2_setxattr(inode, xprefix, xname, buffer, size, flags) * is an implementation of setxattr handler on jffs2. * -------------------------------------------------- */ const struct xattr_handler * const jffs2_xattr_handlers[] = { &jffs2_user_xattr_handler, #ifdef CONFIG_JFFS2_FS_SECURITY &jffs2_security_xattr_handler, #endif &jffs2_trusted_xattr_handler, NULL }; static const char *jffs2_xattr_prefix(int xprefix, struct dentry *dentry) { const struct xattr_handler *ret = NULL; switch (xprefix) { case JFFS2_XPREFIX_USER: ret = &jffs2_user_xattr_handler; break; #ifdef CONFIG_JFFS2_FS_SECURITY case JFFS2_XPREFIX_SECURITY: ret = &jffs2_security_xattr_handler; break; #endif #ifdef CONFIG_JFFS2_FS_POSIX_ACL case JFFS2_XPREFIX_ACL_ACCESS: ret = &nop_posix_acl_access; break; case JFFS2_XPREFIX_ACL_DEFAULT: ret = &nop_posix_acl_default; break; #endif case JFFS2_XPREFIX_TRUSTED: ret = &jffs2_trusted_xattr_handler; break; default: return NULL; } if (!xattr_handler_can_list(ret, dentry)) return NULL; return xattr_prefix(ret); } ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) { struct inode *inode = d_inode(dentry); struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); struct jffs2_inode_cache *ic = f->inocache; struct jffs2_xattr_ref *ref, **pref; struct jffs2_xattr_datum *xd; const char *prefix; ssize_t prefix_len, len, rc; int retry = 0; rc = check_xattr_ref_inode(c, ic); if (unlikely(rc)) return rc; down_read(&c->xattr_sem); retry: len = 0; for (ref=ic->xref, pref=&ic->xref; ref; pref=&ref->next, ref=ref->next) { BUG_ON(ref->ic != ic); xd = ref->xd; if (!xd->xname) { /* xdatum is unchached */ if (!retry) { retry = 1; up_read(&c->xattr_sem); down_write(&c->xattr_sem); goto retry; } else { rc = load_xattr_datum(c, xd); if (unlikely(rc > 0)) { *pref = ref->next; delete_xattr_ref(c, ref); goto retry; } else if (unlikely(rc < 0)) goto out; } } prefix = jffs2_xattr_prefix(xd->xprefix, dentry); if (!prefix) continue; prefix_len = strlen(prefix); rc = prefix_len + xd->name_len + 1; if (buffer) { if (rc > size - len) { rc = -ERANGE; goto out; } memcpy(buffer, prefix, prefix_len); buffer += prefix_len; memcpy(buffer, xd->xname, xd->name_len); buffer += xd->name_len; *buffer++ = 0; } len += rc; } rc = len; out: if (!retry) { up_read(&c->xattr_sem); } else { up_write(&c->xattr_sem); } return rc; } int do_jffs2_getxattr(struct inode *inode, int xprefix, const char *xname, char *buffer, size_t size) { struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); struct jffs2_inode_cache *ic = f->inocache; struct jffs2_xattr_datum *xd; struct jffs2_xattr_ref *ref, **pref; int rc, retry = 0; rc = check_xattr_ref_inode(c, ic); if (unlikely(rc)) return rc; down_read(&c->xattr_sem); retry: for (ref=ic->xref, pref=&ic->xref; ref; pref=&ref->next, ref=ref->next) { BUG_ON(ref->ic!=ic); xd = ref->xd; if (xd->xprefix != xprefix) continue; if (!xd->xname) { /* xdatum is unchached */ if (!retry) { retry = 1; up_read(&c->xattr_sem); down_write(&c->xattr_sem); goto retry; } else { rc = load_xattr_datum(c, xd); if (unlikely(rc > 0)) { *pref = ref->next; delete_xattr_ref(c, ref); goto retry; } else if (unlikely(rc < 0)) { goto out; } } } if (!strcmp(xname, xd->xname)) { rc = xd->value_len; if (buffer) { if (size < rc) { rc = -ERANGE; } else { memcpy(buffer, xd->xvalue, rc); } } goto out; } } rc = -ENODATA; out: if (!retry) { up_read(&c->xattr_sem); } else { up_write(&c->xattr_sem); } return rc; } int do_jffs2_setxattr(struct inode *inode, int xprefix, const char *xname, const char *buffer, size_t size, int flags) { struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); struct jffs2_inode_cache *ic = f->inocache; struct jffs2_xattr_datum *xd; struct jffs2_xattr_ref *ref, *newref, **pref; uint32_t length, request; int rc; rc = check_xattr_ref_inode(c, ic); if (unlikely(rc)) return rc; request = PAD(sizeof(struct jffs2_raw_xattr) + strlen(xname) + 1 + size); if (request > c->sector_size - c->cleanmarker_size) return -ERANGE; rc = jffs2_reserve_space(c, request, &length, ALLOC_NORMAL, JFFS2_SUMMARY_XATTR_SIZE); if (rc) { JFFS2_WARNING("jffs2_reserve_space()=%d, request=%u\n", rc, request); return rc; } /* Find existing xattr */ down_write(&c->xattr_sem); retry: for (ref=ic->xref, pref=&ic->xref; ref; pref=&ref->next, ref=ref->next) { xd = ref->xd; if (xd->xprefix != xprefix) continue; if (!xd->xname) { rc = load_xattr_datum(c, xd); if (unlikely(rc > 0)) { *pref = ref->next; delete_xattr_ref(c, ref); goto retry; } else if (unlikely(rc < 0)) goto out; } if (!strcmp(xd->xname, xname)) { if (flags & XATTR_CREATE) { rc = -EEXIST; goto out; } if (!buffer) { ref->ino = ic->ino; ref->xid = xd->xid; ref->xseqno |= XREF_DELETE_MARKER; rc = save_xattr_ref(c, ref); if (!rc) { *pref = ref->next; spin_lock(&c->erase_completion_lock); ref->next = c->xref_dead_list; c->xref_dead_list = ref; spin_unlock(&c->erase_completion_lock); unrefer_xattr_datum(c, xd); } else { ref->ic = ic; ref->xd = xd; ref->xseqno &= ~XREF_DELETE_MARKER; } goto out; } goto found; } } /* not found */ if (flags & XATTR_REPLACE) { rc = -ENODATA; goto out; } if (!buffer) { rc = -ENODATA; goto out; } found: xd = create_xattr_datum(c, xprefix, xname, buffer, size); if (IS_ERR(xd)) { rc = PTR_ERR(xd); goto out; } up_write(&c->xattr_sem); jffs2_complete_reservation(c); /* create xattr_ref */ request = PAD(sizeof(struct jffs2_raw_xref)); rc = jffs2_reserve_space(c, request, &length, ALLOC_NORMAL, JFFS2_SUMMARY_XREF_SIZE); down_write(&c->xattr_sem); if (rc) { JFFS2_WARNING("jffs2_reserve_space()=%d, request=%u\n", rc, request); unrefer_xattr_datum(c, xd); up_write(&c->xattr_sem); return rc; } if (ref) *pref = ref->next; newref = create_xattr_ref(c, ic, xd); if (IS_ERR(newref)) { if (ref) { ref->next = ic->xref; ic->xref = ref; } rc = PTR_ERR(newref); unrefer_xattr_datum(c, xd); } else if (ref) { delete_xattr_ref(c, ref); } out: up_write(&c->xattr_sem); jffs2_complete_reservation(c); return rc; } /* -------- garbage collector functions ------------- * jffs2_garbage_collect_xattr_datum(c, xd, raw) * is used to move xdatum into new node. * jffs2_garbage_collect_xattr_ref(c, ref, raw) * is used to move xref into new node. * jffs2_verify_xattr(c) * is used to call do_verify_xattr_datum() before garbage collecting. * jffs2_release_xattr_datum(c, xd) * is used to release an in-memory object of xdatum. * jffs2_release_xattr_ref(c, ref) * is used to release an in-memory object of xref. * -------------------------------------------------- */ int jffs2_garbage_collect_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd, struct jffs2_raw_node_ref *raw) { uint32_t totlen, length, old_ofs; int rc = 0; down_write(&c->xattr_sem); if (xd->node != raw) goto out; if (xd->flags & (JFFS2_XFLAGS_DEAD|JFFS2_XFLAGS_INVALID)) goto out; rc = load_xattr_datum(c, xd); if (unlikely(rc)) { rc = (rc > 0) ? 0 : rc; goto out; } old_ofs = ref_offset(xd->node); totlen = PAD(sizeof(struct jffs2_raw_xattr) + xd->name_len + 1 + xd->value_len); rc = jffs2_reserve_space_gc(c, totlen, &length, JFFS2_SUMMARY_XATTR_SIZE); if (rc) { JFFS2_WARNING("jffs2_reserve_space_gc()=%d, request=%u\n", rc, totlen); goto out; } rc = save_xattr_datum(c, xd); if (!rc) dbg_xattr("xdatum (xid=%u, version=%u) GC'ed from %#08x to %08x\n", xd->xid, xd->version, old_ofs, ref_offset(xd->node)); out: if (!rc) jffs2_mark_node_obsolete(c, raw); up_write(&c->xattr_sem); return rc; } int jffs2_garbage_collect_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref, struct jffs2_raw_node_ref *raw) { uint32_t totlen, length, old_ofs; int rc = 0; down_write(&c->xattr_sem); BUG_ON(!ref->node); if (ref->node != raw) goto out; if (is_xattr_ref_dead(ref) && (raw->next_in_ino == (void *)ref)) goto out; old_ofs = ref_offset(ref->node); totlen = ref_totlen(c, c->gcblock, ref->node); rc = jffs2_reserve_space_gc(c, totlen, &length, JFFS2_SUMMARY_XREF_SIZE); if (rc) { JFFS2_WARNING("%s: jffs2_reserve_space_gc() = %d, request = %u\n", __func__, rc, totlen); goto out; } rc = save_xattr_ref(c, ref); if (!rc) dbg_xattr("xref (ino=%u, xid=%u) GC'ed from %#08x to %08x\n", ref->ic->ino, ref->xd->xid, old_ofs, ref_offset(ref->node)); out: if (!rc) jffs2_mark_node_obsolete(c, raw); up_write(&c->xattr_sem); return rc; } int jffs2_verify_xattr(struct jffs2_sb_info *c) { struct jffs2_xattr_datum *xd, *_xd; struct jffs2_eraseblock *jeb; struct jffs2_raw_node_ref *raw; uint32_t totlen; int rc; down_write(&c->xattr_sem); list_for_each_entry_safe(xd, _xd, &c->xattr_unchecked, xindex) { rc = do_verify_xattr_datum(c, xd); if (rc < 0) continue; list_del_init(&xd->xindex); spin_lock(&c->erase_completion_lock); for (raw=xd->node; raw != (void *)xd; raw=raw->next_in_ino) { if (ref_flags(raw) != REF_UNCHECKED) continue; jeb = &c->blocks[ref_offset(raw) / c->sector_size]; totlen = PAD(ref_totlen(c, jeb, raw)); c->unchecked_size -= totlen; c->used_size += totlen; jeb->unchecked_size -= totlen; jeb->used_size += totlen; raw->flash_offset = ref_offset(raw) | ((xd->node == (void *)raw) ? REF_PRISTINE : REF_NORMAL); } if (xd->flags & JFFS2_XFLAGS_DEAD) list_add(&xd->xindex, &c->xattr_dead_list); spin_unlock(&c->erase_completion_lock); } up_write(&c->xattr_sem); return list_empty(&c->xattr_unchecked) ? 1 : 0; } void jffs2_release_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *xd) { /* must be called under spin_lock(&c->erase_completion_lock) */ if (atomic_read(&xd->refcnt) || xd->node != (void *)xd) return; list_del(&xd->xindex); jffs2_free_xattr_datum(xd); } void jffs2_release_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref) { /* must be called under spin_lock(&c->erase_completion_lock) */ struct jffs2_xattr_ref *tmp, **ptmp; if (ref->node != (void *)ref) return; for (tmp=c->xref_dead_list, ptmp=&c->xref_dead_list; tmp; ptmp=&tmp->next, tmp=tmp->next) { if (ref == tmp) { *ptmp = tmp->next; break; } } jffs2_free_xattr_ref(ref); } |
| 8 17 5 6 11 12 12 12 3 1 13 11 2 11 8 3 11 11 1 10 11 10 11 10 11 11 6 6 6 6 6 6 6 11 5 6 6 6 6 6 3 3 3 3 2 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 5 3 2 5 5 5 5 14 1 12 13 7 2 5 9 9 1 8 8 3 6 8 9 9 8 1 1 9 25 11 9 31 1 1 2 1 26 19 3 3 3 1 1 25 25 25 25 9 9 8 8 8 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) static struct bpf_local_storage_map_bucket * select_bucket(struct bpf_local_storage_map *smap, struct bpf_local_storage *local_storage) { return &smap->buckets[hash_ptr(local_storage, smap->bucket_log)]; } static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (!map->ops->map_local_storage_charge) return 0; return map->ops->map_local_storage_charge(smap, owner, size); } static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (map->ops->map_local_storage_uncharge) map->ops->map_local_storage_uncharge(smap, owner, size); } static struct bpf_local_storage __rcu ** owner_storage(struct bpf_local_storage_map *smap, void *owner) { struct bpf_map *map = &smap->map; return map->ops->map_owner_storage_ptr(owner); } static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->snode); } static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); } struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool swap_uptrs) { struct bpf_local_storage_elem *selem; if (mem_charge(smap, owner, smap->elem_size)) return NULL; selem = bpf_map_kmalloc_nolock(&smap->map, smap->elem_size, __GFP_ZERO, NUMA_NO_NODE); if (selem) { RCU_INIT_POINTER(SDATA(selem)->smap, smap); atomic_set(&selem->state, 0); if (value) { /* No need to call check_and_init_map_value as memory is zero init */ copy_map_value(&smap->map, SDATA(selem)->data, value); if (swap_uptrs) bpf_obj_swap_uptrs(smap->map.record, SDATA(selem)->data, value); } return selem; } mem_uncharge(smap, owner, smap->elem_size); return NULL; } static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; /* * RCU Tasks Trace grace period implies RCU grace period, do * kfree() directly. */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); kfree(local_storage); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, bool reuse_now) { if (!local_storage) return; if (reuse_now) { kfree_rcu(local_storage, rcu); return; } call_rcu_tasks_trace(&local_storage->rcu, bpf_local_storage_free_trace_rcu); } static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); if (smap) bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); /* * RCU Tasks Trace grace period implies RCU grace period, do * kfree() directly. */ kfree(selem); } void bpf_selem_free(struct bpf_local_storage_elem *selem, bool reuse_now) { struct bpf_local_storage_map *smap; smap = rcu_dereference_check(SDATA(selem)->smap, 1); if (reuse_now) { if (smap) bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); kfree_rcu(selem, rcu); return; } call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); } static void bpf_selem_free_list(struct hlist_head *list, bool reuse_now) { struct bpf_local_storage_elem *selem; struct hlist_node *n; /* The "_safe" iteration is needed. * The loop is not removing the selem from the list * but bpf_selem_free will use the selem->rcu_head * which is union-ized with the selem->free_node. */ hlist_for_each_entry_safe(selem, n, list, free_node) bpf_selem_free(selem, reuse_now); } static void bpf_selem_unlink_storage_nolock_misc(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, struct bpf_local_storage *local_storage, bool free_local_storage, bool pin_owner) { void *owner = local_storage->owner; u32 uncharge = smap->elem_size; if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); if (pin_owner && !refcount_inc_not_zero(&local_storage->owner_refcnt)) return; uncharge += free_local_storage ? sizeof(*local_storage) : 0; mem_uncharge(smap, local_storage->owner, uncharge); local_storage->mem_charge -= uncharge; if (free_local_storage) { local_storage->owner = NULL; /* After this RCU_INIT, owner may be freed and cannot be used */ RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); } if (pin_owner) refcount_dec(&local_storage->owner_refcnt); } /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, struct hlist_head *free_selem_list) { struct bpf_local_storage_map *smap; bool free_local_storage; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); bpf_selem_unlink_storage_nolock_misc(selem, smap, local_storage, free_local_storage, false); hlist_del_init_rcu(&selem->snode); hlist_add_head(&selem->free_node, free_selem_list); return free_local_storage; } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); local_storage->mem_charge += smap->elem_size; RCU_INIT_POINTER(selem->local_storage, local_storage); hlist_add_head_rcu(&selem->snode, &local_storage->list); } static int bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage *local_storage; struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned long flags; int err; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (err) return err; hlist_del_init_rcu(&selem->map_node); raw_res_spin_unlock_irqrestore(&b->lock, flags); return 0; } static void bpf_selem_unlink_map_nolock(struct bpf_local_storage_elem *selem) { hlist_del_init_rcu(&selem->map_node); } int bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map_bucket *b; unsigned long flags; int err; b = select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (err) return err; hlist_add_head_rcu(&selem->map_node, &b->list); raw_res_spin_unlock_irqrestore(&b->lock, flags); return 0; } static void bpf_selem_link_map_nolock(struct bpf_local_storage_map_bucket *b, struct bpf_local_storage_elem *selem) { hlist_add_head_rcu(&selem->map_node, &b->list); } /* * Unlink an selem from map and local storage with lock held. * This is the common path used by local storages to delete an selem. */ int bpf_selem_unlink(struct bpf_local_storage_elem *selem) { struct bpf_local_storage *local_storage; bool free_local_storage = false; HLIST_HEAD(selem_free_list); unsigned long flags; int err; if (in_nmi()) return -EOPNOTSUPP; if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return 0; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (err) return err; if (likely(selem_linked_to_storage(selem))) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ err = bpf_selem_unlink_map(selem); if (err) goto out; free_local_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, &selem_free_list); } out: raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&selem_free_list, false); if (free_local_storage) bpf_local_storage_free(local_storage, false); return err; } /* * Unlink an selem from map and local storage with lockless fallback if callers * are racing or rqspinlock returns error. It should only be called by * bpf_local_storage_destroy() or bpf_local_storage_map_free(). */ static void bpf_selem_unlink_nofail(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map_bucket *b) { bool in_map_free = !!b, free_storage = false; struct bpf_local_storage *local_storage; struct bpf_local_storage_map *smap; unsigned long flags; int err, unlink = 0; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); if (smap) { b = b ? : select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (!err) { /* * Call bpf_obj_free_fields() under b->lock to make sure it is done * exactly once for an selem. Safe to free special fields immediately * as no BPF program should be referencing the selem. */ if (likely(selem_linked_to_map(selem))) { hlist_del_init_rcu(&selem->map_node); bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); unlink++; } raw_res_spin_unlock_irqrestore(&b->lock, flags); } /* * Highly unlikely scenario: resource leak * * When map_free(selem1), destroy(selem1) and destroy(selem2) are racing * and both selem belong to the same bucket, if destroy(selem2) acquired * b->lock and block for too long, neither map_free(selem1) and * destroy(selem1) will be able to free the special field associated * with selem1 as raw_res_spin_lock_irqsave() returns -ETIMEDOUT. */ WARN_ON_ONCE(err && in_map_free); if (!err || in_map_free) RCU_INIT_POINTER(SDATA(selem)->smap, NULL); } if (local_storage) { err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (!err) { if (likely(selem_linked_to_storage(selem))) { free_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); /* * Okay to skip clearing owner_storage and storage->owner in * destroy() since the owner is going away. No user or bpf * programs should be able to reference it. */ if (smap && in_map_free) bpf_selem_unlink_storage_nolock_misc( selem, smap, local_storage, free_storage, true); hlist_del_init_rcu(&selem->snode); unlink++; } raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); } /* * Highly unlikely scenario: memory leak * * When destroy() fails to acqurire local_storage->lock and initializes * selem->local_storage to NULL before any racing map_free() sees the same * selem, no one will free the local storage. */ WARN_ON_ONCE(err && !in_map_free); if (!err || !in_map_free) RCU_INIT_POINTER(selem->local_storage, NULL); } if (unlink != 2) atomic_or(in_map_free ? SELEM_MAP_UNLINKED : SELEM_STORAGE_UNLINKED, &selem->state); /* * Normally, an selem can be unlinked under local_storage->lock and b->lock, and * then freed after an RCU grace period. However, if destroy() and map_free() are * racing or rqspinlock returns errors in unlikely situations (unlink != 2), free * the selem only after both map_free() and destroy() see the selem. */ if (unlink == 2 || atomic_cmpxchg(&selem->state, SELEM_UNLINKED, SELEM_TOFREE) == SELEM_UNLINKED) bpf_selem_free(selem, true); if (free_storage) bpf_local_storage_free(local_storage, true); } void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { unsigned long flags; int err; /* spinlock is needed to avoid racing with the * parallel delete. Otherwise, publishing an already * deleted sdata to the cache will become a use-after-free * problem in the next bpf_local_storage_lookup(). */ err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (err) return; if (selem_linked_to_storage(selem)) rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, u64 map_flags) { if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; return 0; } int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *first_selem) { struct bpf_local_storage *prev_storage, *storage; struct bpf_local_storage **owner_storage_ptr; struct bpf_local_storage_map_bucket *b; unsigned long flags; int err; err = mem_charge(smap, owner, sizeof(*storage)); if (err) return err; storage = bpf_map_kmalloc_nolock(&smap->map, sizeof(*storage), __GFP_ZERO, NUMA_NO_NODE); if (!storage) { err = -ENOMEM; goto uncharge; } INIT_HLIST_HEAD(&storage->list); raw_res_spin_lock_init(&storage->lock); storage->owner = owner; storage->mem_charge = sizeof(*storage); refcount_set(&storage->owner_refcnt, 1); bpf_selem_link_storage_nolock(storage, first_selem); b = select_bucket(smap, storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (err) goto uncharge; bpf_selem_link_map_nolock(b, first_selem); owner_storage_ptr = (struct bpf_local_storage **)owner_storage(smap, owner); /* Publish storage to the owner. * Instead of using any lock of the kernel object (i.e. owner), * cmpxchg will work with any kernel object regardless what * the running context is, bh, irq...etc. * * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) * is protected by the storage->lock. Hence, when freeing * the owner->storage, the storage->lock must be held before * setting owner->storage ptr to NULL. */ prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); if (unlikely(prev_storage)) { bpf_selem_unlink_map_nolock(first_selem); raw_res_spin_unlock_irqrestore(&b->lock, flags); err = -EAGAIN; goto uncharge; } raw_res_spin_unlock_irqrestore(&b->lock, flags); return 0; uncharge: bpf_local_storage_free(storage, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } /* sk cannot be going away because it is linking new elem * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). * Otherwise, it will become a leak (and other memory issues * during map destruction). */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, bool swap_uptrs) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; struct bpf_local_storage_map_bucket *b; HLIST_HEAD(old_selem_free_list); unsigned long flags, b_flags; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); local_storage = rcu_dereference_check(*owner_storage(smap, owner), bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); selem = bpf_selem_alloc(smap, owner, value, swap_uptrs); if (!selem) return ERR_PTR(-ENOMEM); err = bpf_local_storage_alloc(owner, smap, selem); if (err) { bpf_selem_free(selem, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } return SDATA(selem); } if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { /* Hoping to find an old_sdata to do inline update * such that it can avoid taking the local_storage->lock * and changing the lists. */ old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } } /* A lookup has just been done before and concluded a new selem is * needed. The chance of an unnecessary alloc is unlikely. */ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, swap_uptrs); if (!alloc_selem) return ERR_PTR(-ENOMEM); err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (err) goto free_selem; /* Recheck local_storage->list under local_storage->lock */ if (unlikely(hlist_empty(&local_storage->list))) { /* A parallel del is happening and local_storage is going * away. It has just been checked before, so very * unlikely. Return instead of retry to keep things * simple. */ err = -EAGAIN; goto unlock; } old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) goto unlock; if (old_sdata && (map_flags & BPF_F_LOCK)) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); selem = SELEM(old_sdata); goto unlock; } b = select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, b_flags); if (err) goto unlock; alloc_selem = NULL; /* First, link the new selem to the map */ bpf_selem_link_map_nolock(b, selem); /* Second, link (and publish) the new selem to local_storage */ bpf_selem_link_storage_nolock(local_storage, selem); /* Third, remove old selem, SELEM(old_sdata) */ if (old_sdata) { bpf_selem_unlink_map_nolock(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), &old_selem_free_list); } raw_res_spin_unlock_irqrestore(&b->lock, b_flags); unlock: raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); free_selem: bpf_selem_free_list(&old_selem_free_list, false); if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); bpf_selem_free(alloc_selem, true); } return err ? ERR_PTR(err) : SDATA(selem); } static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; spin_lock(&cache->idx_lock); for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { if (cache->idx_usage_counts[i] < min_usage) { min_usage = cache->idx_usage_counts[i]; res = i; /* Found a free cache_idx */ if (!min_usage) break; } } cache->idx_usage_counts[res]++; spin_unlock(&cache->idx_lock); return res; } static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || /* Enforce BTF for userspace sk dumping */ !attr->btf_key_type_id || !attr->btf_value_type_id) return -EINVAL; if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { if (!btf_type_is_i32(key_type)) return -EINVAL; return 0; } /* * Destroy local storage when the owner is going away. Caller must uncharge memory * if memory charging is used. */ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { struct bpf_local_storage_elem *selem; /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added to or deleted from the * local_storage->list by the bpf_prog or by the bpf_map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ hlist_for_each_entry_rcu(selem, &local_storage->list, snode) bpf_selem_unlink_nofail(selem, NULL); if (!refcount_dec_and_test(&local_storage->owner_refcnt)) { while (refcount_read(&local_storage->owner_refcnt)) cpu_relax(); /* * Paired with refcount_dec() in bpf_selem_unlink_nofail() * to make sure destroy() sees the correct local_storage->mem_charge. */ smp_mb(); } return local_storage->mem_charge; } u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) { struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; u64 usage = sizeof(*smap); /* The dynamically callocated selems are not counted currently. */ usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); return usage; } struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache) { struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; int err; smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; } for (i = 0; i < nbuckets; i++) { INIT_HLIST_HEAD(&smap->buckets[i].list); raw_res_spin_lock_init(&smap->buckets[i].lock); } smap->elem_size = offsetof(struct bpf_local_storage_elem, sdata.data[attr->value_size]); smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; free_smap: kvfree(smap->buckets); bpf_map_area_free(smap); return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache) { struct bpf_local_storage_map_bucket *b; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; unsigned int i; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(cache, smap->cache_idx); /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU * read sections should be prevented via bpf_map_inc_not_zero. */ synchronize_rcu(); /* bpf prog and the userspace can no longer access this map * now. No new selem (of this map) can be added * to the owner->storage or to the map bucket's list. * * The elem of this map can be cleaned up here * or when the storage is freed e.g. * by bpf_sk_storage_free() during __sk_destruct(). */ for (i = 0; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); /* No one is adding to b->list now */ restart: hlist_for_each_entry_rcu(selem, &b->list, map_node) { bpf_selem_unlink_nofail(selem, b); if (need_resched()) { cond_resched_rcu(); goto restart; } } rcu_read_unlock(); } /* While freeing the storage we may still need to access the map. * * e.g. when bpf_sk_storage_free() has unlinked selem from the map * which then made the above while((selem = ...)) loop * exit immediately. * * However, while freeing the storage one still needs to access the * smap->elem_size to do the uncharging in * bpf_selem_unlink_storage_nolock(). * * Hence, wait another rcu grace period for the storage to be freed. */ synchronize_rcu(); /* smap remains in use regardless of kmalloc_nolock, so wait unconditionally. */ rcu_barrier_tasks_trace(); rcu_barrier(); kvfree(smap->buckets); bpf_map_area_free(smap); } |
| 1 1 1 2 27 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * procfs-based user access to knfsd statistics * * /proc/net/rpc/nfsd * * Format: * rc <hits> <misses> <nocache> * Statistsics for the reply cache * fh <stale> <deprecated filehandle cache stats> * statistics for filehandle lookup * io <bytes-read> <bytes-written> * statistics for IO throughput * th <threads> <deprecated thread usage histogram stats> * number of threads * ra <deprecated ra-cache stats> * * plus generic RPC stats (see net/sunrpc/stats.c) * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/seq_file.h> #include <linux/module.h> #include <linux/sunrpc/stats.h> #include <net/net_namespace.h> #include "nfsd.h" #include "netns.h" #include "stats.h" static int nfsd_show(struct seq_file *seq, void *v) { struct net *net = pde_data(file_inode(seq->file)); struct nfsd_net *nn = net_generic(net, nfsd_net_id); int i; seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n", percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_FH_STALE]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_READ]), percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_WRITE])); /* thread usage: */ seq_printf(seq, "th %u 0", atomic_read(&nfsd_th_cnt)); /* deprecated thread usage histogram stats */ for (i = 0; i < 10; i++) seq_puts(seq, " 0.000"); /* deprecated ra-cache stats */ seq_puts(seq, "\nra 0 0 0 0 0 0 0 0 0 0 0 0\n"); /* show my rpc info */ svc_seq_show(seq, &nn->nfsd_svcstats); #ifdef CONFIG_NFSD_V4 /* Show count for individual nfsv4 operations */ /* Writing operation numbers 0 1 2 also for maintaining uniformity */ seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1); for (i = 0; i <= LAST_NFS4_OP; i++) { seq_printf(seq, " %lld", percpu_counter_sum_positive(&nn->counter[NFSD_STATS_NFS4_OP(i)])); } seq_printf(seq, "\nwdeleg_getattr %lld", percpu_counter_sum_positive(&nn->cb_counter[OP_CB_GETATTR])); seq_putc(seq, '\n'); #endif return 0; } DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); struct proc_dir_entry *nfsd_proc_stat_init(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); return svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops); } void nfsd_proc_stat_shutdown(struct net *net) { svc_proc_unregister(net, "nfsd"); } |
| 21 22 22 22 22 22 20 20 | 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 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: hwvalid - I/O request validation * * Copyright (C) 2000 - 2026, Intel Corp. * *****************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #define _COMPONENT ACPI_HARDWARE ACPI_MODULE_NAME("hwvalid") /* Local prototypes */ static acpi_status acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width); /* * Protected I/O ports. Some ports are always illegal, and some are * conditionally illegal. This table must remain ordered by port address. * * The table is used to implement the Microsoft port access rules that * first appeared in Windows XP. Some ports are always illegal, and some * ports are only illegal if the BIOS calls _OSI with nothing newer than * the specific _OSI strings. * * This provides ACPICA with the desired port protections and * Microsoft compatibility. * * Description of port entries: * DMA: DMA controller * PIC0: Programmable Interrupt Controller (8259A) * PIT1: System Timer 1 * PIT2: System Timer 2 failsafe * RTC: Real-time clock * CMOS: Extended CMOS * DMA1: DMA 1 page registers * DMA1L: DMA 1 Ch 0 low page * DMA2: DMA 2 page registers * DMA2L: DMA 2 low page refresh * ARBC: Arbitration control * SETUP: Reserved system board setup * POS: POS channel select * PIC1: Cascaded PIC * IDMA: ISA DMA * ELCR: PIC edge/level registers * PCI: PCI configuration space */ static const struct acpi_port_info acpi_protected_ports[] = { {"DMA", 0x0000, 0x000F, ACPI_OSI_WIN_XP}, {"PIC0", 0x0020, 0x0021, ACPI_ALWAYS_ILLEGAL}, {"PIT1", 0x0040, 0x0043, ACPI_OSI_WIN_XP}, {"PIT2", 0x0048, 0x004B, ACPI_OSI_WIN_XP}, {"RTC", 0x0070, 0x0071, ACPI_OSI_WIN_XP}, {"CMOS", 0x0074, 0x0076, ACPI_OSI_WIN_XP}, {"DMA1", 0x0081, 0x0083, ACPI_OSI_WIN_XP}, {"DMA1L", 0x0087, 0x0087, ACPI_OSI_WIN_XP}, {"DMA2", 0x0089, 0x008B, ACPI_OSI_WIN_XP}, {"DMA2L", 0x008F, 0x008F, ACPI_OSI_WIN_XP}, {"ARBC", 0x0090, 0x0091, ACPI_OSI_WIN_XP}, {"SETUP", 0x0093, 0x0094, ACPI_OSI_WIN_XP}, {"POS", 0x0096, 0x0097, ACPI_OSI_WIN_XP}, {"PIC1", 0x00A0, 0x00A1, ACPI_ALWAYS_ILLEGAL}, {"IDMA", 0x00C0, 0x00DF, ACPI_OSI_WIN_XP}, {"ELCR", 0x04D0, 0x04D1, ACPI_ALWAYS_ILLEGAL}, {"PCI", 0x0CF8, 0x0CFF, ACPI_OSI_WIN_XP} }; #define ACPI_PORT_INFO_ENTRIES ACPI_ARRAY_LENGTH (acpi_protected_ports) /****************************************************************************** * * FUNCTION: acpi_hw_validate_io_request * * PARAMETERS: Address Address of I/O port/register * bit_width Number of bits (8,16,32) * * RETURN: Status * * DESCRIPTION: Validates an I/O request (address/length). Certain ports are * always illegal and some ports are only illegal depending on * the requests the BIOS AML code makes to the predefined * _OSI method. * ******************************************************************************/ static acpi_status acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) { u32 i; u32 byte_width; acpi_io_address last_address; const struct acpi_port_info *port_info; ACPI_FUNCTION_TRACE(hw_validate_io_request); /* Supported widths are 8/16/32 */ if ((bit_width != 8) && (bit_width != 16) && (bit_width != 32)) { ACPI_ERROR((AE_INFO, "Bad BitWidth parameter: %8.8X", bit_width)); return_ACPI_STATUS(AE_BAD_PARAMETER); } port_info = acpi_protected_ports; byte_width = ACPI_DIV_8(bit_width); last_address = address + byte_width - 1; ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X", ACPI_FORMAT_UINT64(address), ACPI_FORMAT_UINT64(last_address), byte_width)); /* Maximum 16-bit address in I/O space */ if (last_address > ACPI_UINT16_MAX) { ACPI_ERROR((AE_INFO, "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X", ACPI_FORMAT_UINT64(address), byte_width)); return_ACPI_STATUS(AE_LIMIT); } /* Exit if requested address is not within the protected port table */ if (address > acpi_protected_ports[ACPI_PORT_INFO_ENTRIES - 1].end) { return_ACPI_STATUS(AE_OK); } /* Check request against the list of protected I/O ports */ for (i = 0; i < ACPI_PORT_INFO_ENTRIES; i++, port_info++) { /* * Check if the requested address range will write to a reserved * port. There are four cases to consider: * * 1) Address range is contained completely in the port address range * 2) Address range overlaps port range at the port range start * 3) Address range overlaps port range at the port range end * 4) Address range completely encompasses the port range */ if ((address <= port_info->end) && (last_address >= port_info->start)) { /* Port illegality may depend on the _OSI calls made by the BIOS */ if (port_info->osi_dependency == ACPI_ALWAYS_ILLEGAL || acpi_gbl_osi_data == port_info->osi_dependency) { ACPI_DEBUG_PRINT((ACPI_DB_VALUES, "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)\n", ACPI_FORMAT_UINT64(address), byte_width, port_info->name, port_info->start, port_info->end)); return_ACPI_STATUS(AE_AML_ILLEGAL_ADDRESS); } } /* Finished if address range ends before the end of this port */ if (last_address <= port_info->end) { break; } } return_ACPI_STATUS(AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_read_port * * PARAMETERS: Address Address of I/O port/register to read * Value Where value (data) is returned * Width Number of bits * * RETURN: Status and value read from port * * DESCRIPTION: Read data from an I/O port or register. This is a front-end * to acpi_os_read_port that performs validation on both the port * address and the length. * *****************************************************************************/ acpi_status acpi_hw_read_port(acpi_io_address address, u32 *value, u32 width) { acpi_status status; u32 one_byte; u32 i; /* Truncate address to 16 bits if requested */ if (acpi_gbl_truncate_io_addresses) { address &= ACPI_UINT16_MAX; } /* Validate the entire request and perform the I/O */ status = acpi_hw_validate_io_request(address, width); if (ACPI_SUCCESS(status)) { status = acpi_os_read_port(address, value, width); return (status); } if (status != AE_AML_ILLEGAL_ADDRESS) { return (status); } /* * There has been a protection violation within the request. Fall * back to byte granularity port I/O and ignore the failing bytes. * This provides compatibility with other ACPI implementations. */ for (i = 0, *value = 0; i < width; i += 8) { /* Validate and read one byte */ if (acpi_hw_validate_io_request(address, 8) == AE_OK) { status = acpi_os_read_port(address, &one_byte, 8); if (ACPI_FAILURE(status)) { return (status); } *value |= (one_byte << i); } address++; } return (AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_write_port * * PARAMETERS: Address Address of I/O port/register to write * Value Value to write * Width Number of bits * * RETURN: Status * * DESCRIPTION: Write data to an I/O port or register. This is a front-end * to acpi_os_write_port that performs validation on both the port * address and the length. * *****************************************************************************/ acpi_status acpi_hw_write_port(acpi_io_address address, u32 value, u32 width) { acpi_status status; u32 i; /* Truncate address to 16 bits if requested */ if (acpi_gbl_truncate_io_addresses) { address &= ACPI_UINT16_MAX; } /* Validate the entire request and perform the I/O */ status = acpi_hw_validate_io_request(address, width); if (ACPI_SUCCESS(status)) { status = acpi_os_write_port(address, value, width); return (status); } if (status != AE_AML_ILLEGAL_ADDRESS) { return (status); } /* * There has been a protection violation within the request. Fall * back to byte granularity port I/O and ignore the failing bytes. * This provides compatibility with other ACPI implementations. */ for (i = 0; i < width; i += 8) { /* Validate and write one byte */ if (acpi_hw_validate_io_request(address, 8) == AE_OK) { status = acpi_os_write_port(address, (value >> i) & 0xFF, 8); if (ACPI_FAILURE(status)) { return (status); } } address++; } return (AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_validate_io_block * * PARAMETERS: Address Address of I/O port/register blobk * bit_width Number of bits (8,16,32) in each register * count Number of registers in the block * * RETURN: Status * * DESCRIPTION: Validates a block of I/O ports/registers. * ******************************************************************************/ acpi_status acpi_hw_validate_io_block(u64 address, u32 bit_width, u32 count) { acpi_status status; while (count--) { status = acpi_hw_validate_io_request((acpi_io_address)address, bit_width); if (ACPI_FAILURE(status)) return_ACPI_STATUS(status); address += ACPI_DIV_8(bit_width); } return_ACPI_STATUS(AE_OK); } |
| 40 40 34 34 34 41 41 41 41 40 34 34 34 40 40 40 40 40 40 40 40 40 40 29 40 40 40 40 40 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Multipath support for RPC * * Copyright (c) 2015, 2016, Primary Data, Inc. All rights reserved. * * Trond Myklebust <trond.myklebust@primarydata.com> * */ #include <linux/atomic.h> #include <linux/types.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/sunrpc/xprt.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/xprtmultipath.h> #include "sysfs.h" typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct rpc_xprt_switch *xps, const struct rpc_xprt *cur); static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular; static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin; static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall; static const struct rpc_xprt_iter_ops rpc_xprt_iter_listoffline; static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt) { if (unlikely(xprt_get(xprt) == NULL)) return; list_add_tail_rcu(&xprt->xprt_switch, &xps->xps_xprt_list); smp_wmb(); if (xps->xps_nxprts == 0) xps->xps_net = xprt->xprt_net; xps->xps_nxprts++; xps->xps_nactive++; } /** * rpc_xprt_switch_add_xprt - Add a new rpc_xprt to an rpc_xprt_switch * @xps: pointer to struct rpc_xprt_switch * @xprt: pointer to struct rpc_xprt * * Adds xprt to the end of the list of struct rpc_xprt in xps. */ void rpc_xprt_switch_add_xprt(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt) { if (xprt == NULL) return; spin_lock(&xps->xps_lock); if (xps->xps_net == xprt->xprt_net || xps->xps_net == NULL) xprt_switch_add_xprt_locked(xps, xprt); spin_unlock(&xps->xps_lock); rpc_sysfs_xprt_setup(xps, xprt, GFP_KERNEL); } static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, bool offline) { if (unlikely(xprt == NULL)) return; if (!test_bit(XPRT_OFFLINE, &xprt->state) && offline) xps->xps_nactive--; xps->xps_nxprts--; if (xps->xps_nxprts == 0) xps->xps_net = NULL; smp_wmb(); list_del_rcu(&xprt->xprt_switch); } /** * rpc_xprt_switch_remove_xprt - Removes an rpc_xprt from a rpc_xprt_switch * @xps: pointer to struct rpc_xprt_switch * @xprt: pointer to struct rpc_xprt * @offline: indicates if the xprt that's being removed is in an offline state * * Removes xprt from the list of struct rpc_xprt in xps. */ void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, bool offline) { spin_lock(&xps->xps_lock); xprt_switch_remove_xprt_locked(xps, xprt, offline); spin_unlock(&xps->xps_lock); xprt_put(xprt); } /** * rpc_xprt_switch_get_main_xprt - Get the 'main' xprt for an xprt switch. * @xps: pointer to struct rpc_xprt_switch. */ struct rpc_xprt *rpc_xprt_switch_get_main_xprt(struct rpc_xprt_switch *xps) { struct rpc_xprt_iter xpi; struct rpc_xprt *xprt; xprt_iter_init_listall(&xpi, xps); xprt = xprt_iter_get_next(&xpi); while (xprt && !xprt->main) { xprt_put(xprt); xprt = xprt_iter_get_next(&xpi); } xprt_iter_destroy(&xpi); return xprt; } static DEFINE_IDA(rpc_xprtswitch_ids); void xprt_multipath_cleanup_ids(void) { ida_destroy(&rpc_xprtswitch_ids); } static int xprt_switch_alloc_id(struct rpc_xprt_switch *xps, gfp_t gfp_flags) { int id; id = ida_alloc(&rpc_xprtswitch_ids, gfp_flags); if (id < 0) return id; xps->xps_id = id; return 0; } static void xprt_switch_free_id(struct rpc_xprt_switch *xps) { ida_free(&rpc_xprtswitch_ids, xps->xps_id); } /** * xprt_switch_alloc - Allocate a new struct rpc_xprt_switch * @xprt: pointer to struct rpc_xprt * @gfp_flags: allocation flags * * On success, returns an initialised struct rpc_xprt_switch, containing * the entry xprt. Returns NULL on failure. */ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, gfp_t gfp_flags) { struct rpc_xprt_switch *xps; xps = kmalloc_obj(*xps, gfp_flags); if (xps != NULL) { spin_lock_init(&xps->xps_lock); kref_init(&xps->xps_kref); xprt_switch_alloc_id(xps, gfp_flags); xps->xps_nxprts = xps->xps_nactive = 0; atomic_long_set(&xps->xps_queuelen, 0); xps->xps_net = NULL; INIT_LIST_HEAD(&xps->xps_xprt_list); xps->xps_iter_ops = &rpc_xprt_iter_singular; rpc_sysfs_xprt_switch_setup(xps, xprt, gfp_flags); xprt_switch_add_xprt_locked(xps, xprt); xps->xps_nunique_destaddr_xprts = 1; rpc_sysfs_xprt_setup(xps, xprt, gfp_flags); } return xps; } static void xprt_switch_free_entries(struct rpc_xprt_switch *xps) { spin_lock(&xps->xps_lock); while (!list_empty(&xps->xps_xprt_list)) { struct rpc_xprt *xprt; xprt = list_first_entry(&xps->xps_xprt_list, struct rpc_xprt, xprt_switch); xprt_switch_remove_xprt_locked(xps, xprt, true); spin_unlock(&xps->xps_lock); xprt_put(xprt); spin_lock(&xps->xps_lock); } spin_unlock(&xps->xps_lock); } static void xprt_switch_free(struct kref *kref) { struct rpc_xprt_switch *xps = container_of(kref, struct rpc_xprt_switch, xps_kref); xprt_switch_free_entries(xps); rpc_sysfs_xprt_switch_destroy(xps); xprt_switch_free_id(xps); kfree_rcu(xps, xps_rcu); } /** * xprt_switch_get - Return a reference to a rpc_xprt_switch * @xps: pointer to struct rpc_xprt_switch * * Returns a reference to xps unless the refcount is already zero. */ struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps) { if (xps != NULL && kref_get_unless_zero(&xps->xps_kref)) return xps; return NULL; } /** * xprt_switch_put - Release a reference to a rpc_xprt_switch * @xps: pointer to struct rpc_xprt_switch * * Release the reference to xps, and free it once the refcount is zero. */ void xprt_switch_put(struct rpc_xprt_switch *xps) { if (xps != NULL) kref_put(&xps->xps_kref, xprt_switch_free); } /** * rpc_xprt_switch_set_roundrobin - Set a round-robin policy on rpc_xprt_switch * @xps: pointer to struct rpc_xprt_switch * * Sets a round-robin default policy for iterators acting on xps. */ void rpc_xprt_switch_set_roundrobin(struct rpc_xprt_switch *xps) { if (READ_ONCE(xps->xps_iter_ops) != &rpc_xprt_iter_roundrobin) WRITE_ONCE(xps->xps_iter_ops, &rpc_xprt_iter_roundrobin); } static const struct rpc_xprt_iter_ops *xprt_iter_ops(const struct rpc_xprt_iter *xpi) { if (xpi->xpi_ops != NULL) return xpi->xpi_ops; return rcu_dereference(xpi->xpi_xpswitch)->xps_iter_ops; } static void xprt_iter_no_rewind(struct rpc_xprt_iter *xpi) { } static void xprt_iter_default_rewind(struct rpc_xprt_iter *xpi) { WRITE_ONCE(xpi->xpi_cursor, NULL); } static bool xprt_is_active(const struct rpc_xprt *xprt) { return (kref_read(&xprt->kref) != 0 && !test_bit(XPRT_OFFLINE, &xprt->state)); } static struct rpc_xprt *xprt_switch_find_first_entry(struct list_head *head) { struct rpc_xprt *pos; list_for_each_entry_rcu(pos, head, xprt_switch) { if (xprt_is_active(pos)) return pos; } return NULL; } static struct rpc_xprt *xprt_switch_find_first_entry_offline(struct list_head *head) { struct rpc_xprt *pos; list_for_each_entry_rcu(pos, head, xprt_switch) { if (!xprt_is_active(pos)) return pos; } return NULL; } static struct rpc_xprt *xprt_iter_first_entry(struct rpc_xprt_iter *xpi) { struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); if (xps == NULL) return NULL; return xprt_switch_find_first_entry(&xps->xps_xprt_list); } static struct rpc_xprt *_xprt_switch_find_current_entry(struct list_head *head, const struct rpc_xprt *cur, bool find_active) { struct rpc_xprt *pos; bool found = false; list_for_each_entry_rcu(pos, head, xprt_switch) { if (cur == pos) found = true; if (found && ((find_active && xprt_is_active(pos)) || (!find_active && !xprt_is_active(pos)))) return pos; } return NULL; } static struct rpc_xprt *xprt_switch_find_current_entry(struct list_head *head, const struct rpc_xprt *cur) { return _xprt_switch_find_current_entry(head, cur, true); } static struct rpc_xprt * _xprt_iter_current_entry(struct rpc_xprt_iter *xpi, struct rpc_xprt *first_entry(struct list_head *head), struct rpc_xprt *current_entry(struct list_head *head, const struct rpc_xprt *cur)) { struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); struct list_head *head; if (xps == NULL) return NULL; head = &xps->xps_xprt_list; if (xpi->xpi_cursor == NULL || xps->xps_nxprts < 2) return first_entry(head); return current_entry(head, xpi->xpi_cursor); } static struct rpc_xprt *xprt_iter_current_entry(struct rpc_xprt_iter *xpi) { return _xprt_iter_current_entry(xpi, xprt_switch_find_first_entry, xprt_switch_find_current_entry); } static struct rpc_xprt *xprt_switch_find_current_entry_offline(struct list_head *head, const struct rpc_xprt *cur) { return _xprt_switch_find_current_entry(head, cur, false); } static struct rpc_xprt *xprt_iter_current_entry_offline(struct rpc_xprt_iter *xpi) { return _xprt_iter_current_entry(xpi, xprt_switch_find_first_entry_offline, xprt_switch_find_current_entry_offline); } static bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, const struct sockaddr *sap) { struct list_head *head; struct rpc_xprt *pos; if (xps == NULL || sap == NULL) return false; head = &xps->xps_xprt_list; list_for_each_entry_rcu(pos, head, xprt_switch) { if (rpc_cmp_addr_port(sap, (struct sockaddr *)&pos->addr)) { pr_info("RPC: addr %s already in xprt switch\n", pos->address_strings[RPC_DISPLAY_ADDR]); return true; } } return false; } bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, const struct sockaddr *sap) { bool res; rcu_read_lock(); res = __rpc_xprt_switch_has_addr(xps, sap); rcu_read_unlock(); return res; } static struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, const struct rpc_xprt *cur, bool check_active) { struct rpc_xprt *pos, *prev = NULL; bool found = false; list_for_each_entry_rcu(pos, head, xprt_switch) { if (cur == prev) found = true; /* for request to return active transports return only * active, for request to return offline transports * return only offline */ if (found && ((check_active && xprt_is_active(pos)) || (!check_active && !xprt_is_active(pos)))) return pos; prev = pos; } return NULL; } static struct rpc_xprt *xprt_switch_set_next_cursor(struct rpc_xprt_switch *xps, struct rpc_xprt **cursor, xprt_switch_find_xprt_t find_next) { struct rpc_xprt *pos, *old; old = smp_load_acquire(cursor); pos = find_next(xps, old); smp_store_release(cursor, pos); return pos; } static struct rpc_xprt *xprt_iter_next_entry_multiple(struct rpc_xprt_iter *xpi, xprt_switch_find_xprt_t find_next) { struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); if (xps == NULL) return NULL; return xprt_switch_set_next_cursor(xps, &xpi->xpi_cursor, find_next); } static struct rpc_xprt *__xprt_switch_find_next_entry_roundrobin(struct list_head *head, const struct rpc_xprt *cur) { struct rpc_xprt *ret; ret = xprt_switch_find_next_entry(head, cur, true); if (ret != NULL) return ret; return xprt_switch_find_first_entry(head); } static struct rpc_xprt *xprt_switch_find_next_entry_roundrobin(struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) { struct list_head *head = &xps->xps_xprt_list; struct rpc_xprt *xprt; unsigned int nactive; for (;;) { unsigned long xprt_queuelen, xps_queuelen; xprt = __xprt_switch_find_next_entry_roundrobin(head, cur); if (!xprt) break; xprt_queuelen = atomic_long_read(&xprt->queuelen); xps_queuelen = atomic_long_read(&xps->xps_queuelen); nactive = READ_ONCE(xps->xps_nactive); /* Exit loop if xprt_queuelen <= average queue length */ if (xprt_queuelen * nactive <= xps_queuelen) break; cur = xprt; } return xprt; } static struct rpc_xprt *xprt_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi) { return xprt_iter_next_entry_multiple(xpi, xprt_switch_find_next_entry_roundrobin); } static struct rpc_xprt *xprt_switch_find_next_entry_all(struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) { return xprt_switch_find_next_entry(&xps->xps_xprt_list, cur, true); } static struct rpc_xprt *xprt_switch_find_next_entry_offline(struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) { return xprt_switch_find_next_entry(&xps->xps_xprt_list, cur, false); } static struct rpc_xprt *xprt_iter_next_entry_all(struct rpc_xprt_iter *xpi) { return xprt_iter_next_entry_multiple(xpi, xprt_switch_find_next_entry_all); } static struct rpc_xprt *xprt_iter_next_entry_offline(struct rpc_xprt_iter *xpi) { return xprt_iter_next_entry_multiple(xpi, xprt_switch_find_next_entry_offline); } /* * xprt_iter_rewind - Resets the xprt iterator * @xpi: pointer to rpc_xprt_iter * * Resets xpi to ensure that it points to the first entry in the list * of transports. */ void xprt_iter_rewind(struct rpc_xprt_iter *xpi) { rcu_read_lock(); xprt_iter_ops(xpi)->xpi_rewind(xpi); rcu_read_unlock(); } static void __xprt_iter_init(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps, const struct rpc_xprt_iter_ops *ops) { rcu_assign_pointer(xpi->xpi_xpswitch, xprt_switch_get(xps)); xpi->xpi_cursor = NULL; xpi->xpi_ops = ops; } /** * xprt_iter_init - Initialise an xprt iterator * @xpi: pointer to rpc_xprt_iter * @xps: pointer to rpc_xprt_switch * * Initialises the iterator to use the default iterator ops * as set in xps. This function is mainly intended for internal * use in the rpc_client. */ void xprt_iter_init(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps) { __xprt_iter_init(xpi, xps, NULL); } /** * xprt_iter_init_listall - Initialise an xprt iterator * @xpi: pointer to rpc_xprt_iter * @xps: pointer to rpc_xprt_switch * * Initialises the iterator to iterate once through the entire list * of entries in xps. */ void xprt_iter_init_listall(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps) { __xprt_iter_init(xpi, xps, &rpc_xprt_iter_listall); } void xprt_iter_init_listoffline(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps) { __xprt_iter_init(xpi, xps, &rpc_xprt_iter_listoffline); } /** * xprt_iter_xchg_switch - Atomically swap out the rpc_xprt_switch * @xpi: pointer to rpc_xprt_iter * @newswitch: pointer to a new rpc_xprt_switch or NULL * * Swaps out the existing xpi->xpi_xpswitch with a new value. */ struct rpc_xprt_switch *xprt_iter_xchg_switch(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *newswitch) { struct rpc_xprt_switch __rcu *oldswitch; /* Atomically swap out the old xpswitch */ oldswitch = xchg(&xpi->xpi_xpswitch, RCU_INITIALIZER(newswitch)); if (newswitch != NULL) xprt_iter_rewind(xpi); return rcu_dereference_protected(oldswitch, true); } /** * xprt_iter_destroy - Destroys the xprt iterator * @xpi: pointer to rpc_xprt_iter */ void xprt_iter_destroy(struct rpc_xprt_iter *xpi) { xprt_switch_put(xprt_iter_xchg_switch(xpi, NULL)); } /** * xprt_iter_xprt - Returns the rpc_xprt pointed to by the cursor * @xpi: pointer to rpc_xprt_iter * * Returns a pointer to the struct rpc_xprt that is currently * pointed to by the cursor. * Caller must be holding rcu_read_lock(). */ struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi) { WARN_ON_ONCE(!rcu_read_lock_held()); return xprt_iter_ops(xpi)->xpi_xprt(xpi); } static struct rpc_xprt *xprt_iter_get_helper(struct rpc_xprt_iter *xpi, struct rpc_xprt *(*fn)(struct rpc_xprt_iter *)) { struct rpc_xprt *ret; do { ret = fn(xpi); if (ret == NULL) break; ret = xprt_get(ret); } while (ret == NULL); return ret; } /** * xprt_iter_get_next - Returns the next rpc_xprt following the cursor * @xpi: pointer to rpc_xprt_iter * * Returns a reference to the struct rpc_xprt that immediately follows the * entry pointed to by the cursor. */ struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi) { struct rpc_xprt *xprt; rcu_read_lock(); xprt = xprt_iter_get_helper(xpi, xprt_iter_ops(xpi)->xpi_next); rcu_read_unlock(); return xprt; } /* Policy for always returning the first entry in the rpc_xprt_switch */ static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular = { .xpi_rewind = xprt_iter_no_rewind, .xpi_xprt = xprt_iter_first_entry, .xpi_next = xprt_iter_first_entry, }; /* Policy for round-robin iteration of entries in the rpc_xprt_switch */ static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin = { .xpi_rewind = xprt_iter_default_rewind, .xpi_xprt = xprt_iter_current_entry, .xpi_next = xprt_iter_next_entry_roundrobin, }; /* Policy for once-through iteration of entries in the rpc_xprt_switch */ static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall = { .xpi_rewind = xprt_iter_default_rewind, .xpi_xprt = xprt_iter_current_entry, .xpi_next = xprt_iter_next_entry_all, }; static const struct rpc_xprt_iter_ops rpc_xprt_iter_listoffline = { .xpi_rewind = xprt_iter_default_rewind, .xpi_xprt = xprt_iter_current_entry_offline, .xpi_next = xprt_iter_next_entry_offline, }; |
| 4 13 1 6 1 1 1 1 1 1 12 7 6 6 6 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Linux driver for Philips webcam USB and Video4Linux interface part. (C) 1999-2004 Nemosoft Unv. (C) 2004-2006 Luc Saillard (luc@saillard.org) (C) 2011 Hans de Goede <hdegoede@redhat.com> NOTE: this version of pwc is an unofficial (modified) release of pwc & pcwx driver and thus may have bugs that are not present in the original version. Please send bug reports and support requests to <luc@saillard.org>. The decompression routines have been implemented by reverse-engineering the Nemosoft binary pwcx module. Caveat emptor. */ /* This code forms the interface between the USB layers and the Philips specific stuff. Some adanved stuff of the driver falls under an NDA, signed between me and Philips B.V., Eindhoven, the Netherlands, and is thus not distributed in source form. The binary pwcx.o module contains the code that falls under the NDA. In case you're wondering: 'pwc' stands for "Philips WebCam", but I really didn't want to type 'philips_web_cam' every time (I'm lazy as any Linux kernel hacker, but I don't like uncomprehensible abbreviations without explanation). Oh yes, convention: to disctinguish between all the various pointers to device-structures, I use these names for the pointer variables: udev: struct usb_device * vdev: struct video_device (member of pwc_dev) pdev: struct pwc_devive * */ /* Contributors: - Alvarado: adding whitebalance code - Alistar Moire: QuickCam 3000 Pro device/product ID - Tony Hoyle: Creative Labs Webcam 5 device/product ID - Mark Burazin: solving hang in VIDIOCSYNC when camera gets unplugged - Jk Fang: Sotec Afina Eye ID - Xavier Roche: QuickCam Pro 4000 ID - Jens Knudsen: QuickCam Zoom ID - J. Debert: QuickCam for Notebooks ID - Pham Thanh Nam: webcam snapshot button as an event input device */ #include <linux/errno.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/poll.h> #include <linux/slab.h> #ifdef CONFIG_USB_PWC_INPUT_EVDEV #include <linux/usb/input.h> #endif #include <linux/vmalloc.h> #include <asm/io.h> #include "pwc.h" #include "pwc-kiara.h" #include "pwc-timon.h" #include "pwc-dec23.h" #include "pwc-dec1.h" #define CREATE_TRACE_POINTS #include <trace/events/pwc.h> /* Function prototypes and driver templates */ /* hotplug device table support */ static const struct usb_device_id pwc_device_table [] = { { USB_DEVICE(0x041E, 0x400C) }, /* Creative Webcam 5 */ { USB_DEVICE(0x041E, 0x4011) }, /* Creative Webcam Pro Ex */ { USB_DEVICE(0x046D, 0x08B0) }, /* Logitech QuickCam 3000 Pro */ { USB_DEVICE(0x046D, 0x08B1) }, /* Logitech QuickCam Notebook Pro */ { USB_DEVICE(0x046D, 0x08B2) }, /* Logitech QuickCam 4000 Pro */ { USB_DEVICE(0x046D, 0x08B3) }, /* Logitech QuickCam Zoom (old model) */ { USB_DEVICE(0x046D, 0x08B4) }, /* Logitech QuickCam Zoom (new model) */ { USB_DEVICE(0x046D, 0x08B5) }, /* Logitech QuickCam Orbit/Sphere */ { USB_DEVICE(0x046D, 0x08B6) }, /* Logitech/Cisco VT Camera */ { USB_DEVICE(0x046D, 0x08B7) }, /* Logitech ViewPort AV 100 */ { USB_DEVICE(0x046D, 0x08B8) }, /* Logitech QuickCam */ { USB_DEVICE(0x0471, 0x0302) }, /* Philips PCA645VC */ { USB_DEVICE(0x0471, 0x0303) }, /* Philips PCA646VC */ { USB_DEVICE(0x0471, 0x0304) }, /* Askey VC010 type 2 */ { USB_DEVICE(0x0471, 0x0307) }, /* Philips PCVC675K (Vesta) */ { USB_DEVICE(0x0471, 0x0308) }, /* Philips PCVC680K (Vesta Pro) */ { USB_DEVICE(0x0471, 0x030C) }, /* Philips PCVC690K (Vesta Pro Scan) */ { USB_DEVICE(0x0471, 0x0310) }, /* Philips PCVC730K (ToUCam Fun)/PCVC830 (ToUCam II) */ { USB_DEVICE(0x0471, 0x0311) }, /* Philips PCVC740K (ToUCam Pro)/PCVC840 (ToUCam II) */ { USB_DEVICE(0x0471, 0x0312) }, /* Philips PCVC750K (ToUCam Pro Scan) */ { USB_DEVICE(0x0471, 0x0313) }, /* Philips PCVC720K/40 (ToUCam XS) */ { USB_DEVICE(0x0471, 0x0329) }, /* Philips SPC 900NC webcam */ { USB_DEVICE(0x0471, 0x032C) }, /* Philips SPC 880NC webcam */ { USB_DEVICE(0x04CC, 0x8116) }, /* Sotec Afina Eye */ { USB_DEVICE(0x055D, 0x9000) }, /* Samsung MPC-C10 */ { USB_DEVICE(0x055D, 0x9001) }, /* Samsung MPC-C30 */ { USB_DEVICE(0x055D, 0x9002) }, /* Samsung SNC-35E (Ver3.0) */ { USB_DEVICE(0x069A, 0x0001) }, /* Askey VC010 type 1 */ { USB_DEVICE(0x06BE, 0x8116) }, /* AME Co. Afina Eye */ { USB_DEVICE(0x0d81, 0x1900) }, /* Visionite VCS-UC300 */ { USB_DEVICE(0x0d81, 0x1910) }, /* Visionite VCS-UM100 */ { } }; MODULE_DEVICE_TABLE(usb, pwc_device_table); static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id *id); static void usb_pwc_disconnect(struct usb_interface *intf); static void pwc_isoc_cleanup(struct pwc_device *pdev); static struct usb_driver pwc_driver = { .name = "Philips webcam", /* name */ .id_table = pwc_device_table, .probe = usb_pwc_probe, /* probe() */ .disconnect = usb_pwc_disconnect, /* disconnect() */ }; #define MAX_DEV_HINTS 20 #define MAX_ISOC_ERRORS 20 #ifdef CONFIG_USB_PWC_DEBUG int pwc_trace = PWC_DEBUG_LEVEL; #endif static int power_save = -1; static int leds[2] = { 100, 0 }; /***/ static const struct v4l2_file_operations pwc_fops = { .owner = THIS_MODULE, .open = v4l2_fh_open, .release = vb2_fop_release, .read = vb2_fop_read, .poll = vb2_fop_poll, .mmap = vb2_fop_mmap, .unlocked_ioctl = video_ioctl2, }; static const struct video_device pwc_template = { .name = "Philips Webcam", /* Filled in later */ .release = video_device_release_empty, .fops = &pwc_fops, .ioctl_ops = &pwc_ioctl_ops, }; /***************************************************************************/ /* Private functions */ static void *pwc_alloc_urb_buffer(struct usb_device *dev, size_t size, dma_addr_t *dma_handle) { struct device *dmadev = dev->bus->sysdev; void *buffer = kmalloc(size, GFP_KERNEL); if (!buffer) return NULL; *dma_handle = dma_map_single(dmadev, buffer, size, DMA_FROM_DEVICE); if (dma_mapping_error(dmadev, *dma_handle)) { kfree(buffer); return NULL; } return buffer; } static void pwc_free_urb_buffer(struct usb_device *dev, size_t size, void *buffer, dma_addr_t dma_handle) { struct device *dmadev = dev->bus->sysdev; dma_unmap_single(dmadev, dma_handle, size, DMA_FROM_DEVICE); kfree(buffer); } static struct pwc_frame_buf *pwc_get_next_fill_buf(struct pwc_device *pdev) { unsigned long flags = 0; struct pwc_frame_buf *buf = NULL; spin_lock_irqsave(&pdev->queued_bufs_lock, flags); if (list_empty(&pdev->queued_bufs)) goto leave; buf = list_entry(pdev->queued_bufs.next, struct pwc_frame_buf, list); list_del(&buf->list); leave: spin_unlock_irqrestore(&pdev->queued_bufs_lock, flags); return buf; } static void pwc_snapshot_button(struct pwc_device *pdev, int down) { if (down) { PWC_TRACE("Snapshot button pressed.\n"); } else { PWC_TRACE("Snapshot button released.\n"); } #ifdef CONFIG_USB_PWC_INPUT_EVDEV if (pdev->button_dev) { input_report_key(pdev->button_dev, KEY_CAMERA, down); input_sync(pdev->button_dev); } #endif } static void pwc_frame_complete(struct pwc_device *pdev) { struct pwc_frame_buf *fbuf = pdev->fill_buf; /* The ToUCam Fun CMOS sensor causes the firmware to send 2 or 3 bogus frames on the USB wire after an exposure change. This conditition is however detected in the cam and a bit is set in the header. */ if (pdev->type == 730) { unsigned char *ptr = (unsigned char *)fbuf->data; if (ptr[1] == 1 && ptr[0] & 0x10) { PWC_TRACE("Hyundai CMOS sensor bug. Dropping frame.\n"); pdev->drop_frames += 2; } if ((ptr[0] ^ pdev->vmirror) & 0x01) { pwc_snapshot_button(pdev, ptr[0] & 0x01); } if ((ptr[0] ^ pdev->vmirror) & 0x02) { if (ptr[0] & 0x02) PWC_TRACE("Image is mirrored.\n"); else PWC_TRACE("Image is normal.\n"); } pdev->vmirror = ptr[0] & 0x03; /* Sometimes the trailer of the 730 is still sent as a 4 byte packet after a short frame; this condition is filtered out specifically. A 4 byte frame doesn't make sense anyway. So we get either this sequence: drop_bit set -> 4 byte frame -> short frame -> good frame Or this one: drop_bit set -> short frame -> good frame So we drop either 3 or 2 frames in all! */ if (fbuf->filled == 4) pdev->drop_frames++; } else if (pdev->type == 740 || pdev->type == 720) { unsigned char *ptr = (unsigned char *)fbuf->data; if ((ptr[0] ^ pdev->vmirror) & 0x01) { pwc_snapshot_button(pdev, ptr[0] & 0x01); } pdev->vmirror = ptr[0] & 0x03; } /* In case we were instructed to drop the frame, do so silently. */ if (pdev->drop_frames > 0) { pdev->drop_frames--; } else { /* Check for underflow first */ if (fbuf->filled < pdev->frame_total_size) { PWC_DEBUG_FLOW("Frame buffer underflow (%d bytes); discarded.\n", fbuf->filled); } else { fbuf->vb.field = V4L2_FIELD_NONE; fbuf->vb.sequence = pdev->vframe_count; vb2_buffer_done(&fbuf->vb.vb2_buf, VB2_BUF_STATE_DONE); pdev->fill_buf = NULL; pdev->vsync = 0; } } /* !drop_frames */ pdev->vframe_count++; } /* This gets called for the Isochronous pipe (video). This is done in * interrupt time, so it has to be fast, not crash, and not stall. Neat. */ static void pwc_isoc_handler(struct urb *urb) { struct pwc_device *pdev = (struct pwc_device *)urb->context; struct device *dmadev = urb->dev->bus->sysdev; int i, fst, flen; unsigned char *iso_buf = NULL; trace_pwc_handler_enter(urb, pdev); if (urb->status == -ENOENT || urb->status == -ECONNRESET || urb->status == -ESHUTDOWN) { PWC_DEBUG_OPEN("URB (%p) unlinked %ssynchronously.\n", urb, urb->status == -ENOENT ? "" : "a"); return; } if (pdev->fill_buf == NULL) pdev->fill_buf = pwc_get_next_fill_buf(pdev); if (urb->status != 0) { const char *errmsg; errmsg = "Unknown"; switch(urb->status) { case -ENOSR: errmsg = "Buffer error (overrun)"; break; case -EPIPE: errmsg = "Stalled (device not responding)"; break; case -EOVERFLOW: errmsg = "Babble (bad cable?)"; break; case -EPROTO: errmsg = "Bit-stuff error (bad cable?)"; break; case -EILSEQ: errmsg = "CRC/Timeout (could be anything)"; break; case -ETIME: errmsg = "Device does not respond"; break; } PWC_ERROR("pwc_isoc_handler() called with status %d [%s].\n", urb->status, errmsg); /* Give up after a number of contiguous errors */ if (++pdev->visoc_errors > MAX_ISOC_ERRORS) { PWC_ERROR("Too many ISOC errors, bailing out.\n"); if (pdev->fill_buf) { vb2_buffer_done(&pdev->fill_buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); pdev->fill_buf = NULL; } } pdev->vsync = 0; /* Drop the current frame */ goto handler_end; } /* Reset ISOC error counter. We did get here, after all. */ pdev->visoc_errors = 0; dma_sync_single_for_cpu(dmadev, urb->transfer_dma, urb->transfer_buffer_length, DMA_FROM_DEVICE); /* vsync: 0 = don't copy data 1 = sync-hunt 2 = synched */ /* Compact data */ for (i = 0; i < urb->number_of_packets; i++) { fst = urb->iso_frame_desc[i].status; flen = urb->iso_frame_desc[i].actual_length; iso_buf = urb->transfer_buffer + urb->iso_frame_desc[i].offset; if (fst != 0) { PWC_ERROR("Iso frame %d has error %d\n", i, fst); continue; } if (flen > 0 && pdev->vsync) { struct pwc_frame_buf *fbuf = pdev->fill_buf; if (pdev->vsync == 1) { fbuf->vb.vb2_buf.timestamp = ktime_get_ns(); pdev->vsync = 2; } if (flen + fbuf->filled > pdev->frame_total_size) { PWC_ERROR("Frame overflow (%d > %d)\n", flen + fbuf->filled, pdev->frame_total_size); pdev->vsync = 0; /* Let's wait for an EOF */ } else { memcpy(fbuf->data + fbuf->filled, iso_buf, flen); fbuf->filled += flen; } } if (flen < pdev->vlast_packet_size) { /* Shorter packet... end of frame */ if (pdev->vsync == 2) pwc_frame_complete(pdev); if (pdev->fill_buf == NULL) pdev->fill_buf = pwc_get_next_fill_buf(pdev); if (pdev->fill_buf) { pdev->fill_buf->filled = 0; pdev->vsync = 1; } } pdev->vlast_packet_size = flen; } dma_sync_single_for_device(dmadev, urb->transfer_dma, urb->transfer_buffer_length, DMA_FROM_DEVICE); handler_end: trace_pwc_handler_exit(urb, pdev); i = usb_submit_urb(urb, GFP_ATOMIC); if (i != 0) PWC_ERROR("Error (%d) re-submitting urb in pwc_isoc_handler.\n", i); } /* Both v4l2_lock and vb_queue_lock should be locked when calling this */ static int pwc_isoc_init(struct pwc_device *pdev) { struct usb_device *udev; struct urb *urb; int i, j, ret; struct usb_interface *intf; struct usb_host_interface *idesc = NULL; int compression = 0; /* 0..3 = uncompressed..high */ pdev->vsync = 0; pdev->vlast_packet_size = 0; pdev->fill_buf = NULL; pdev->vframe_count = 0; pdev->visoc_errors = 0; udev = pdev->udev; retry: /* We first try with low compression and then retry with a higher compression setting if there is not enough bandwidth. */ ret = pwc_set_video_mode(pdev, pdev->width, pdev->height, pdev->pixfmt, pdev->vframes, &compression, 1); /* Get the current alternate interface, adjust packet size */ intf = usb_ifnum_to_if(udev, 0); if (intf) idesc = usb_altnum_to_altsetting(intf, pdev->valternate); if (!idesc) return -EIO; /* Search video endpoint */ pdev->vmax_packet_size = -1; for (i = 0; i < idesc->desc.bNumEndpoints; i++) { if ((idesc->endpoint[i].desc.bEndpointAddress & 0xF) == pdev->vendpoint) { pdev->vmax_packet_size = le16_to_cpu(idesc->endpoint[i].desc.wMaxPacketSize); break; } } if (pdev->vmax_packet_size < 0 || pdev->vmax_packet_size > ISO_MAX_FRAME_SIZE) { PWC_ERROR("Failed to find packet size for video endpoint in current alternate setting.\n"); return -ENFILE; /* Odd error, that should be noticeable */ } /* Set alternate interface */ PWC_DEBUG_OPEN("Setting alternate interface %d\n", pdev->valternate); ret = usb_set_interface(pdev->udev, 0, pdev->valternate); if (ret == -ENOSPC && compression < 3) { compression++; goto retry; } if (ret < 0) return ret; /* Allocate and init Isochronuous urbs */ for (i = 0; i < MAX_ISO_BUFS; i++) { urb = usb_alloc_urb(ISO_FRAMES_PER_DESC, GFP_KERNEL); if (urb == NULL) { pwc_isoc_cleanup(pdev); return -ENOMEM; } pdev->urbs[i] = urb; PWC_DEBUG_MEMORY("Allocated URB at 0x%p\n", urb); urb->interval = 1; // devik urb->dev = udev; urb->pipe = usb_rcvisocpipe(udev, pdev->vendpoint); urb->transfer_flags = URB_ISO_ASAP | URB_NO_TRANSFER_DMA_MAP; urb->transfer_buffer_length = ISO_BUFFER_SIZE; urb->transfer_buffer = pwc_alloc_urb_buffer(udev, urb->transfer_buffer_length, &urb->transfer_dma); if (urb->transfer_buffer == NULL) { PWC_ERROR("Failed to allocate urb buffer %d\n", i); pwc_isoc_cleanup(pdev); return -ENOMEM; } urb->complete = pwc_isoc_handler; urb->context = pdev; urb->start_frame = 0; urb->number_of_packets = ISO_FRAMES_PER_DESC; for (j = 0; j < ISO_FRAMES_PER_DESC; j++) { urb->iso_frame_desc[j].offset = j * ISO_MAX_FRAME_SIZE; urb->iso_frame_desc[j].length = pdev->vmax_packet_size; } } /* link */ for (i = 0; i < MAX_ISO_BUFS; i++) { ret = usb_submit_urb(pdev->urbs[i], GFP_KERNEL); if (ret == -ENOSPC && compression < 3) { compression++; pwc_isoc_cleanup(pdev); goto retry; } if (ret) { PWC_ERROR("isoc_init() submit_urb %d failed with error %d\n", i, ret); pwc_isoc_cleanup(pdev); return ret; } PWC_DEBUG_MEMORY("URB 0x%p submitted.\n", pdev->urbs[i]); } /* All is done... */ PWC_DEBUG_OPEN("<< pwc_isoc_init()\n"); return 0; } static void pwc_iso_stop(struct pwc_device *pdev) { int i; /* Unlinking ISOC buffers one by one */ for (i = 0; i < MAX_ISO_BUFS; i++) { if (pdev->urbs[i]) { PWC_DEBUG_MEMORY("Unlinking URB %p\n", pdev->urbs[i]); usb_kill_urb(pdev->urbs[i]); } } } static void pwc_iso_free(struct pwc_device *pdev) { int i; /* Freeing ISOC buffers one by one */ for (i = 0; i < MAX_ISO_BUFS; i++) { struct urb *urb = pdev->urbs[i]; if (urb) { PWC_DEBUG_MEMORY("Freeing URB\n"); if (urb->transfer_buffer) pwc_free_urb_buffer(urb->dev, urb->transfer_buffer_length, urb->transfer_buffer, urb->transfer_dma); usb_free_urb(urb); pdev->urbs[i] = NULL; } } } /* Both v4l2_lock and vb_queue_lock should be locked when calling this */ static void pwc_isoc_cleanup(struct pwc_device *pdev) { PWC_DEBUG_OPEN(">> pwc_isoc_cleanup()\n"); pwc_iso_stop(pdev); pwc_iso_free(pdev); usb_set_interface(pdev->udev, 0, 0); PWC_DEBUG_OPEN("<< pwc_isoc_cleanup()\n"); } /* Must be called with vb_queue_lock hold */ static void pwc_cleanup_queued_bufs(struct pwc_device *pdev, enum vb2_buffer_state state) { unsigned long flags = 0; spin_lock_irqsave(&pdev->queued_bufs_lock, flags); while (!list_empty(&pdev->queued_bufs)) { struct pwc_frame_buf *buf; buf = list_entry(pdev->queued_bufs.next, struct pwc_frame_buf, list); list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, state); } spin_unlock_irqrestore(&pdev->queued_bufs_lock, flags); } #ifdef CONFIG_USB_PWC_DEBUG static const char *pwc_sensor_type_to_string(unsigned int sensor_type) { switch(sensor_type) { case 0x00: return "Hyundai CMOS sensor"; case 0x20: return "Sony CCD sensor + TDA8787"; case 0x2E: return "Sony CCD sensor + Exas 98L59"; case 0x2F: return "Sony CCD sensor + ADI 9804"; case 0x30: return "Sharp CCD sensor + TDA8787"; case 0x3E: return "Sharp CCD sensor + Exas 98L59"; case 0x3F: return "Sharp CCD sensor + ADI 9804"; case 0x40: return "UPA 1021 sensor"; case 0x100: return "VGA sensor"; case 0x101: return "PAL MR sensor"; default: return "unknown type of sensor"; } } #endif /***************************************************************************/ /* Video4Linux functions */ static void pwc_video_release(struct v4l2_device *v) { struct pwc_device *pdev = container_of(v, struct pwc_device, v4l2_dev); v4l2_ctrl_handler_free(&pdev->ctrl_handler); v4l2_device_unregister(&pdev->v4l2_dev); kfree(pdev->ctrl_buf); kfree(pdev); } /***************************************************************************/ /* Videobuf2 operations */ static int queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct pwc_device *pdev = vb2_get_drv_priv(vq); int size; if (*nbuffers < MIN_FRAMES) *nbuffers = MIN_FRAMES; else if (*nbuffers > MAX_FRAMES) *nbuffers = MAX_FRAMES; *nplanes = 1; size = pwc_get_size(pdev, MAX_WIDTH, MAX_HEIGHT); sizes[0] = PAGE_ALIGN(pwc_image_sizes[size][0] * pwc_image_sizes[size][1] * 3 / 2); return 0; } static int buffer_init(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct pwc_frame_buf *buf = container_of(vbuf, struct pwc_frame_buf, vb); /* need vmalloc since frame buffer > 128K */ buf->data = vzalloc(PWC_FRAME_SIZE); if (buf->data == NULL) return -ENOMEM; return 0; } static int buffer_prepare(struct vb2_buffer *vb) { struct pwc_device *pdev = vb2_get_drv_priv(vb->vb2_queue); /* Don't allow queueing new buffers after device disconnection */ if (!pdev->udev) return -ENODEV; return 0; } static void buffer_finish(struct vb2_buffer *vb) { struct pwc_device *pdev = vb2_get_drv_priv(vb->vb2_queue); struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct pwc_frame_buf *buf = container_of(vbuf, struct pwc_frame_buf, vb); if (vb->state == VB2_BUF_STATE_DONE) { /* * Application has called dqbuf and is getting back a buffer * we've filled, take the pwc data we've stored in buf->data * and decompress it into a usable format, storing the result * in the vb2_buffer. */ pwc_decompress(pdev, buf); } } static void buffer_cleanup(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct pwc_frame_buf *buf = container_of(vbuf, struct pwc_frame_buf, vb); vfree(buf->data); } static void buffer_queue(struct vb2_buffer *vb) { struct pwc_device *pdev = vb2_get_drv_priv(vb->vb2_queue); struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct pwc_frame_buf *buf = container_of(vbuf, struct pwc_frame_buf, vb); unsigned long flags = 0; /* Check the device has not disconnected between prep and queuing */ if (!pdev->udev) { vb2_buffer_done(vb, VB2_BUF_STATE_ERROR); return; } spin_lock_irqsave(&pdev->queued_bufs_lock, flags); list_add_tail(&buf->list, &pdev->queued_bufs); spin_unlock_irqrestore(&pdev->queued_bufs_lock, flags); } static int start_streaming(struct vb2_queue *vq, unsigned int count) { struct pwc_device *pdev = vb2_get_drv_priv(vq); int r; if (!pdev->udev) { pwc_cleanup_queued_bufs(pdev, VB2_BUF_STATE_QUEUED); return -ENODEV; } if (mutex_lock_interruptible(&pdev->v4l2_lock)) { pwc_cleanup_queued_bufs(pdev, VB2_BUF_STATE_QUEUED); return -ERESTARTSYS; } /* Turn on camera and set LEDS on */ pwc_camera_power(pdev, 1); pwc_set_leds(pdev, leds[0], leds[1]); r = pwc_isoc_init(pdev); if (r) { /* If we failed turn camera and LEDS back off */ pwc_set_leds(pdev, 0, 0); pwc_camera_power(pdev, 0); /* And cleanup any queued bufs!! */ pwc_cleanup_queued_bufs(pdev, VB2_BUF_STATE_QUEUED); if (pdev->fill_buf) { vb2_buffer_done(&pdev->fill_buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); pdev->fill_buf = NULL; } } mutex_unlock(&pdev->v4l2_lock); return r; } static void stop_streaming(struct vb2_queue *vq) { struct pwc_device *pdev = vb2_get_drv_priv(vq); mutex_lock(&pdev->v4l2_lock); if (pdev->udev) { pwc_set_leds(pdev, 0, 0); pwc_camera_power(pdev, 0); pwc_isoc_cleanup(pdev); } pwc_cleanup_queued_bufs(pdev, VB2_BUF_STATE_ERROR); if (pdev->fill_buf) vb2_buffer_done(&pdev->fill_buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); mutex_unlock(&pdev->v4l2_lock); } static const struct vb2_ops pwc_vb_queue_ops = { .queue_setup = queue_setup, .buf_init = buffer_init, .buf_prepare = buffer_prepare, .buf_finish = buffer_finish, .buf_cleanup = buffer_cleanup, .buf_queue = buffer_queue, .start_streaming = start_streaming, .stop_streaming = stop_streaming, }; /***************************************************************************/ /* USB functions */ /* This function gets called when a new device is plugged in or the usb core * is loaded. */ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); struct pwc_device *pdev = NULL; int vendor_id, product_id, type_id; int rc; int features = 0; int compression = 0; int my_power_save = power_save; char serial_number[30], *name; vendor_id = le16_to_cpu(udev->descriptor.idVendor); product_id = le16_to_cpu(udev->descriptor.idProduct); /* Check if we can handle this device */ PWC_DEBUG_PROBE("probe() called [%04X %04X], if %d\n", vendor_id, product_id, intf->altsetting->desc.bInterfaceNumber); /* the interfaces are probed one by one. We are only interested in the video interface (0) now. Interface 1 is the Audio Control, and interface 2 Audio itself. */ if (intf->altsetting->desc.bInterfaceNumber > 0) return -ENODEV; if (vendor_id == 0x0471) { switch (product_id) { case 0x0302: PWC_INFO("Philips PCA645VC USB webcam detected.\n"); name = "Philips 645 webcam"; type_id = 645; break; case 0x0303: PWC_INFO("Philips PCA646VC USB webcam detected.\n"); name = "Philips 646 webcam"; type_id = 646; break; case 0x0304: PWC_INFO("Askey VC010 type 2 USB webcam detected.\n"); name = "Askey VC010 webcam"; type_id = 646; break; case 0x0307: PWC_INFO("Philips PCVC675K (Vesta) USB webcam detected.\n"); name = "Philips 675 webcam"; type_id = 675; break; case 0x0308: PWC_INFO("Philips PCVC680K (Vesta Pro) USB webcam detected.\n"); name = "Philips 680 webcam"; type_id = 680; break; case 0x030C: PWC_INFO("Philips PCVC690K (Vesta Pro Scan) USB webcam detected.\n"); name = "Philips 690 webcam"; type_id = 690; break; case 0x0310: PWC_INFO("Philips PCVC730K (ToUCam Fun)/PCVC830 (ToUCam II) USB webcam detected.\n"); name = "Philips 730 webcam"; type_id = 730; break; case 0x0311: PWC_INFO("Philips PCVC740K (ToUCam Pro)/PCVC840 (ToUCam II) USB webcam detected.\n"); name = "Philips 740 webcam"; type_id = 740; break; case 0x0312: PWC_INFO("Philips PCVC750K (ToUCam Pro Scan) USB webcam detected.\n"); name = "Philips 750 webcam"; type_id = 750; break; case 0x0313: PWC_INFO("Philips PCVC720K/40 (ToUCam XS) USB webcam detected.\n"); name = "Philips 720K/40 webcam"; type_id = 720; break; case 0x0329: PWC_INFO("Philips SPC 900NC USB webcam detected.\n"); name = "Philips SPC 900NC webcam"; type_id = 740; break; case 0x032C: PWC_INFO("Philips SPC 880NC USB webcam detected.\n"); name = "Philips SPC 880NC webcam"; type_id = 740; break; default: return -ENODEV; } } else if (vendor_id == 0x069A) { switch(product_id) { case 0x0001: PWC_INFO("Askey VC010 type 1 USB webcam detected.\n"); name = "Askey VC010 webcam"; type_id = 645; break; default: return -ENODEV; } } else if (vendor_id == 0x046d) { switch(product_id) { case 0x08b0: PWC_INFO("Logitech QuickCam Pro 3000 USB webcam detected.\n"); name = "Logitech QuickCam Pro 3000"; type_id = 740; /* CCD sensor */ break; case 0x08b1: PWC_INFO("Logitech QuickCam Notebook Pro USB webcam detected.\n"); name = "Logitech QuickCam Notebook Pro"; type_id = 740; /* CCD sensor */ break; case 0x08b2: PWC_INFO("Logitech QuickCam 4000 Pro USB webcam detected.\n"); name = "Logitech QuickCam Pro 4000"; type_id = 740; /* CCD sensor */ if (my_power_save == -1) my_power_save = 1; break; case 0x08b3: PWC_INFO("Logitech QuickCam Zoom USB webcam detected.\n"); name = "Logitech QuickCam Zoom"; type_id = 740; /* CCD sensor */ break; case 0x08B4: PWC_INFO("Logitech QuickCam Zoom (new model) USB webcam detected.\n"); name = "Logitech QuickCam Zoom"; type_id = 740; /* CCD sensor */ if (my_power_save == -1) my_power_save = 1; break; case 0x08b5: PWC_INFO("Logitech QuickCam Orbit/Sphere USB webcam detected.\n"); name = "Logitech QuickCam Orbit"; type_id = 740; /* CCD sensor */ if (my_power_save == -1) my_power_save = 1; features |= FEATURE_MOTOR_PANTILT; break; case 0x08b6: PWC_INFO("Logitech/Cisco VT Camera webcam detected.\n"); name = "Cisco VT Camera"; type_id = 740; /* CCD sensor */ break; case 0x08b7: PWC_INFO("Logitech ViewPort AV 100 webcam detected.\n"); name = "Logitech ViewPort AV 100"; type_id = 740; /* CCD sensor */ break; case 0x08b8: /* Where this released? */ PWC_INFO("Logitech QuickCam detected (reserved ID).\n"); name = "Logitech QuickCam (res.)"; type_id = 730; /* Assuming CMOS */ break; default: return -ENODEV; } } else if (vendor_id == 0x055d) { /* I don't know the difference between the C10 and the C30; I suppose the difference is the sensor, but both cameras work equally well with a type_id of 675 */ switch(product_id) { case 0x9000: PWC_INFO("Samsung MPC-C10 USB webcam detected.\n"); name = "Samsung MPC-C10"; type_id = 675; break; case 0x9001: PWC_INFO("Samsung MPC-C30 USB webcam detected.\n"); name = "Samsung MPC-C30"; type_id = 675; break; case 0x9002: PWC_INFO("Samsung SNC-35E (v3.0) USB webcam detected.\n"); name = "Samsung MPC-C30"; type_id = 740; break; default: return -ENODEV; } } else if (vendor_id == 0x041e) { switch(product_id) { case 0x400c: PWC_INFO("Creative Labs Webcam 5 detected.\n"); name = "Creative Labs Webcam 5"; type_id = 730; if (my_power_save == -1) my_power_save = 1; break; case 0x4011: PWC_INFO("Creative Labs Webcam Pro Ex detected.\n"); name = "Creative Labs Webcam Pro Ex"; type_id = 740; break; default: return -ENODEV; } } else if (vendor_id == 0x04cc) { switch(product_id) { case 0x8116: PWC_INFO("Sotec Afina Eye USB webcam detected.\n"); name = "Sotec Afina Eye"; type_id = 730; break; default: return -ENODEV; } } else if (vendor_id == 0x06be) { switch(product_id) { case 0x8116: /* This is essentially the same cam as the Sotec Afina Eye */ PWC_INFO("AME Co. Afina Eye USB webcam detected.\n"); name = "AME Co. Afina Eye"; type_id = 750; break; default: return -ENODEV; } } else if (vendor_id == 0x0d81) { switch(product_id) { case 0x1900: PWC_INFO("Visionite VCS-UC300 USB webcam detected.\n"); name = "Visionite VCS-UC300"; type_id = 740; /* CCD sensor */ break; case 0x1910: PWC_INFO("Visionite VCS-UM100 USB webcam detected.\n"); name = "Visionite VCS-UM100"; type_id = 730; /* CMOS sensor */ break; default: return -ENODEV; } } else return -ENODEV; /* Not any of the know types; but the list keeps growing. */ if (my_power_save == -1) my_power_save = 0; memset(serial_number, 0, 30); usb_string(udev, udev->descriptor.iSerialNumber, serial_number, 29); PWC_DEBUG_PROBE("Device serial number is %s\n", serial_number); if (udev->descriptor.bNumConfigurations > 1) PWC_WARNING("Warning: more than 1 configuration available.\n"); /* Allocate structure, initialize pointers, mutexes, etc. and link it to the usb_device */ pdev = kzalloc_obj(struct pwc_device); if (pdev == NULL) { PWC_ERROR("Oops, could not allocate memory for pwc_device.\n"); return -ENOMEM; } pdev->type = type_id; pdev->features = features; pwc_construct(pdev); /* set min/max sizes correct */ mutex_init(&pdev->v4l2_lock); mutex_init(&pdev->vb_queue_lock); spin_lock_init(&pdev->queued_bufs_lock); INIT_LIST_HEAD(&pdev->queued_bufs); pdev->udev = udev; pdev->power_save = my_power_save; /* Init videobuf2 queue structure */ pdev->vb_queue.type = V4L2_BUF_TYPE_VIDEO_CAPTURE; pdev->vb_queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_READ; pdev->vb_queue.drv_priv = pdev; pdev->vb_queue.buf_struct_size = sizeof(struct pwc_frame_buf); pdev->vb_queue.ops = &pwc_vb_queue_ops; pdev->vb_queue.mem_ops = &vb2_vmalloc_memops; pdev->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; pdev->vb_queue.lock = &pdev->vb_queue_lock; rc = vb2_queue_init(&pdev->vb_queue); if (rc < 0) { PWC_ERROR("Oops, could not initialize vb2 queue.\n"); goto err_free_mem; } /* Init video_device structure */ pdev->vdev = pwc_template; strscpy(pdev->vdev.name, name, sizeof(pdev->vdev.name)); pdev->vdev.queue = &pdev->vb_queue; video_set_drvdata(&pdev->vdev, pdev); pdev->release = le16_to_cpu(udev->descriptor.bcdDevice); PWC_DEBUG_PROBE("Release: %04x\n", pdev->release); /* Allocate USB command buffers */ pdev->ctrl_buf = kmalloc(sizeof(pdev->cmd_buf), GFP_KERNEL); if (!pdev->ctrl_buf) { PWC_ERROR("Oops, could not allocate memory for pwc_device.\n"); rc = -ENOMEM; goto err_free_mem; } #ifdef CONFIG_USB_PWC_DEBUG /* Query sensor type */ if (pwc_get_cmos_sensor(pdev, &rc) >= 0) { PWC_DEBUG_OPEN("This %s camera is equipped with a %s (%d).\n", pdev->vdev.name, pwc_sensor_type_to_string(rc), rc); } #endif /* Set the leds off */ pwc_set_leds(pdev, 0, 0); /* Setup initial videomode */ rc = pwc_set_video_mode(pdev, MAX_WIDTH, MAX_HEIGHT, V4L2_PIX_FMT_YUV420, 30, &compression, 1); if (rc) goto err_free_mem; /* Register controls (and read default values from camera */ rc = pwc_init_controls(pdev); if (rc) { PWC_ERROR("Failed to register v4l2 controls (%d).\n", rc); goto err_free_mem; } /* And powerdown the camera until streaming starts */ pwc_camera_power(pdev, 0); /* Register the v4l2_device structure */ pdev->v4l2_dev.release = pwc_video_release; rc = v4l2_device_register(&intf->dev, &pdev->v4l2_dev); if (rc) { PWC_ERROR("Failed to register v4l2-device (%d).\n", rc); goto err_free_controls; } pdev->v4l2_dev.ctrl_handler = &pdev->ctrl_handler; pdev->vdev.v4l2_dev = &pdev->v4l2_dev; pdev->vdev.lock = &pdev->v4l2_lock; pdev->vdev.device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING | V4L2_CAP_READWRITE; rc = video_register_device(&pdev->vdev, VFL_TYPE_VIDEO, -1); if (rc < 0) { PWC_ERROR("Failed to register as video device (%d).\n", rc); goto err_unregister_v4l2_dev; } PWC_INFO("Registered as %s.\n", video_device_node_name(&pdev->vdev)); #ifdef CONFIG_USB_PWC_INPUT_EVDEV /* register webcam snapshot button input device */ pdev->button_dev = input_allocate_device(); if (!pdev->button_dev) { rc = -ENOMEM; goto err_video_unreg; } usb_make_path(udev, pdev->button_phys, sizeof(pdev->button_phys)); strlcat(pdev->button_phys, "/input0", sizeof(pdev->button_phys)); pdev->button_dev->name = "PWC snapshot button"; pdev->button_dev->phys = pdev->button_phys; usb_to_input_id(pdev->udev, &pdev->button_dev->id); pdev->button_dev->dev.parent = &pdev->udev->dev; pdev->button_dev->evbit[0] = BIT_MASK(EV_KEY); pdev->button_dev->keybit[BIT_WORD(KEY_CAMERA)] = BIT_MASK(KEY_CAMERA); rc = input_register_device(pdev->button_dev); if (rc) { input_free_device(pdev->button_dev); pdev->button_dev = NULL; goto err_video_unreg; } #endif return 0; #ifdef CONFIG_USB_PWC_INPUT_EVDEV err_video_unreg: video_unregister_device(&pdev->vdev); #endif err_unregister_v4l2_dev: v4l2_device_unregister(&pdev->v4l2_dev); err_free_controls: v4l2_ctrl_handler_free(&pdev->ctrl_handler); err_free_mem: kfree(pdev->ctrl_buf); kfree(pdev); return rc; } /* The user yanked out the cable... */ static void usb_pwc_disconnect(struct usb_interface *intf) { struct v4l2_device *v = usb_get_intfdata(intf); struct pwc_device *pdev = container_of(v, struct pwc_device, v4l2_dev); mutex_lock(&pdev->vb_queue_lock); mutex_lock(&pdev->v4l2_lock); /* No need to keep the urbs around after disconnection */ if (pdev->vb_queue.streaming) pwc_isoc_cleanup(pdev); pdev->udev = NULL; v4l2_device_disconnect(&pdev->v4l2_dev); video_unregister_device(&pdev->vdev); mutex_unlock(&pdev->v4l2_lock); mutex_unlock(&pdev->vb_queue_lock); #ifdef CONFIG_USB_PWC_INPUT_EVDEV if (pdev->button_dev) input_unregister_device(pdev->button_dev); #endif v4l2_device_put(&pdev->v4l2_dev); } /* * Initialization code & module stuff */ static unsigned int leds_nargs; #ifdef CONFIG_USB_PWC_DEBUG module_param_named(trace, pwc_trace, int, 0644); #endif module_param(power_save, int, 0644); module_param_array(leds, int, &leds_nargs, 0444); #ifdef CONFIG_USB_PWC_DEBUG MODULE_PARM_DESC(trace, "For debugging purposes"); #endif MODULE_PARM_DESC(power_save, "Turn power saving for new cameras on or off"); MODULE_PARM_DESC(leds, "LED on,off time in milliseconds"); MODULE_DESCRIPTION("Philips & OEM USB webcam driver"); MODULE_AUTHOR("Luc Saillard <luc@saillard.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS("pwcx"); MODULE_VERSION( PWC_VERSION ); module_usb_driver(pwc_driver); |
| 3 1 3 6 1 6 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "main.h" #include <linux/errno.h> #include <linux/list.h> #include <linux/moduleparam.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include <net/genetlink.h> #include <net/netlink.h> #include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "netlink.h" char batadv_routing_algo[20] = "BATMAN_IV"; static struct hlist_head batadv_algo_list; /** * batadv_algo_init() - Initialize batman-adv algorithm management data * structures */ void batadv_algo_init(void) { INIT_HLIST_HEAD(&batadv_algo_list); } /** * batadv_algo_get() - Search for algorithm with specific name * @name: algorithm name to find * * Return: Pointer to batadv_algo_ops on success, NULL otherwise */ struct batadv_algo_ops *batadv_algo_get(const char *name) { struct batadv_algo_ops *bat_algo_ops = NULL; struct batadv_algo_ops *bat_algo_ops_tmp; hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) { if (strcmp(bat_algo_ops_tmp->name, name) != 0) continue; bat_algo_ops = bat_algo_ops_tmp; break; } return bat_algo_ops; } /** * batadv_algo_register() - Register callbacks for a mesh algorithm * @bat_algo_ops: mesh algorithm callbacks to add * * Return: 0 on success or negative error number in case of failure */ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) { struct batadv_algo_ops *bat_algo_ops_tmp; bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name); if (bat_algo_ops_tmp) { pr_info("Trying to register already registered routing algorithm: %s\n", bat_algo_ops->name); return -EEXIST; } /* all algorithms must implement all ops (for now) */ if (!bat_algo_ops->iface.enable || !bat_algo_ops->iface.disable || !bat_algo_ops->iface.update_mac || !bat_algo_ops->iface.primary_set || !bat_algo_ops->neigh.cmp || !bat_algo_ops->neigh.is_similar_or_better) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); return -EINVAL; } INIT_HLIST_NODE(&bat_algo_ops->list); hlist_add_head(&bat_algo_ops->list, &batadv_algo_list); return 0; } /** * batadv_algo_select() - Select algorithm of mesh interface * @bat_priv: the bat priv with all the mesh interface information * @name: name of the algorithm to select * * The algorithm callbacks for the mesh interface will be set when the algorithm * with the correct name was found. Any previous selected algorithm will not be * deinitialized and the new selected algorithm will also not be initialized. * It is therefore not allowed to call batadv_algo_select outside the creation * function of the mesh interface. * * Return: 0 on success or negative error number in case of failure */ int batadv_algo_select(struct batadv_priv *bat_priv, const char *name) { struct batadv_algo_ops *bat_algo_ops; bat_algo_ops = batadv_algo_get(name); if (!bat_algo_ops) return -EINVAL; bat_priv->algo_ops = bat_algo_ops; return 0; } /** * batadv_param_set_ra() - Validate and store routing_algo module parameter * @val: new value for the routing_algo module parameter * @kp: kernel parameter description used to store the value * * Check that the requested algorithm is known to batman-adv and then store * the name as the new default routing algorithm. * * Return: 0 on success or negative error number in case of failure */ static int batadv_param_set_ra(const char *val, const struct kernel_param *kp) { struct batadv_algo_ops *bat_algo_ops; char *algo_name = (char *)val; size_t name_len; name_len = strlen(algo_name); if (name_len > 0 && algo_name[name_len - 1] == '\n') algo_name[name_len - 1] = '\0'; bat_algo_ops = batadv_algo_get(algo_name); if (!bat_algo_ops) { pr_err("Routing algorithm '%s' is not supported\n", algo_name); return -EINVAL; } return param_set_copystring(algo_name, kp); } static const struct kernel_param_ops batadv_param_ops_ra = { .set = batadv_param_set_ra, .get = param_get_string, }; static struct kparam_string batadv_param_string_ra = { .maxlen = sizeof(batadv_routing_algo), .string = batadv_routing_algo, }; module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra, 0644); /** * batadv_algo_dump_entry() - fill in information about one supported routing * algorithm * @msg: netlink message to be sent back * @portid: Port to reply to * @seq: Sequence number of message * @bat_algo_ops: Algorithm to be dumped * * Return: Error number, or 0 on success */ static int batadv_algo_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_algo_ops *bat_algo_ops) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_ROUTING_ALGOS); if (!hdr) return -EMSGSIZE; if (nla_put_string(msg, BATADV_ATTR_ALGO_NAME, bat_algo_ops->name)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_algo_dump() - fill in information about supported routing * algorithms * @msg: netlink message to be sent back * @cb: Parameters to the netlink request * * Return: Length of reply message. */ int batadv_algo_dump(struct sk_buff *msg, struct netlink_callback *cb) { int portid = NETLINK_CB(cb->skb).portid; struct batadv_algo_ops *bat_algo_ops; int skip = cb->args[0]; int i = 0; hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { if (i++ < skip) continue; if (batadv_algo_dump_entry(msg, portid, cb->nlh->nlmsg_seq, bat_algo_ops)) { i--; break; } } cb->args[0] = i; return msg->len; } |
| 2 2 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 or MIT /* * Copyright (C) 2016 Noralf Trønnes * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #include <linux/export.h> #include <linux/io.h> #include <linux/iosys-map.h> #include <linux/module.h> #include <linux/slab.h> #include <drm/drm_device.h> #include <drm/drm_format_helper.h> #include <drm/drm_framebuffer.h> #include <drm/drm_fourcc.h> #include <drm/drm_print.h> #include <drm/drm_rect.h> #include "drm_format_internal.h" /** * drm_format_conv_state_init - Initialize format-conversion state * @state: The state to initialize * * Clears all fields in struct drm_format_conv_state. The state will * be empty with no preallocated resources. */ void drm_format_conv_state_init(struct drm_format_conv_state *state) { state->tmp.mem = NULL; state->tmp.size = 0; state->tmp.preallocated = false; } EXPORT_SYMBOL(drm_format_conv_state_init); /** * drm_format_conv_state_copy - Copy format-conversion state * @state: Destination state * @old_state: Source state * * Copies format-conversion state from @old_state to @state; except for * temporary storage. */ void drm_format_conv_state_copy(struct drm_format_conv_state *state, const struct drm_format_conv_state *old_state) { /* * So far, there's only temporary storage here, which we don't * duplicate. Just clear the fields. */ state->tmp.mem = NULL; state->tmp.size = 0; state->tmp.preallocated = false; } EXPORT_SYMBOL(drm_format_conv_state_copy); /** * drm_format_conv_state_reserve - Allocates storage for format conversion * @state: The format-conversion state * @new_size: The minimum allocation size * @flags: Flags for kmalloc() * * Allocates at least @new_size bytes and returns a pointer to the memory * range. After calling this function, previously returned memory blocks * are invalid. It's best to collect all memory requirements of a format * conversion and call this function once to allocate the range. * * Returns: * A pointer to the allocated memory range, or NULL otherwise. */ void *drm_format_conv_state_reserve(struct drm_format_conv_state *state, size_t new_size, gfp_t flags) { void *mem; if (new_size <= state->tmp.size) goto out; else if (state->tmp.preallocated) return NULL; mem = krealloc(state->tmp.mem, new_size, flags); if (!mem) return NULL; state->tmp.mem = mem; state->tmp.size = new_size; out: return state->tmp.mem; } EXPORT_SYMBOL(drm_format_conv_state_reserve); /** * drm_format_conv_state_release - Releases an format-conversion storage * @state: The format-conversion state * * Releases the memory range references by the format-conversion state. * After this call, all pointers to the memory are invalid. Prefer * drm_format_conv_state_init() for cleaning up and unloading a driver. */ void drm_format_conv_state_release(struct drm_format_conv_state *state) { if (state->tmp.preallocated) return; kfree(state->tmp.mem); state->tmp.mem = NULL; state->tmp.size = 0; } EXPORT_SYMBOL(drm_format_conv_state_release); static unsigned int clip_offset(const struct drm_rect *clip, unsigned int pitch, unsigned int cpp) { return clip->y1 * pitch + clip->x1 * cpp; } /** * drm_fb_clip_offset - Returns the clipping rectangles byte-offset in a framebuffer * @pitch: Framebuffer line pitch in byte * @format: Framebuffer format * @clip: Clip rectangle * * Returns: * The byte offset of the clip rectangle's top-left corner within the framebuffer. */ unsigned int drm_fb_clip_offset(unsigned int pitch, const struct drm_format_info *format, const struct drm_rect *clip) { return clip_offset(clip, pitch, format->cpp[0]); } EXPORT_SYMBOL(drm_fb_clip_offset); /* TODO: Make this function work with multi-plane formats. */ static int __drm_fb_xfrm(void *dst, unsigned long dst_pitch, unsigned long dst_pixsize, const void *vaddr, const struct drm_framebuffer *fb, const struct drm_rect *clip, bool vaddr_cached_hint, struct drm_format_conv_state *state, void (*xfrm_line)(void *dbuf, const void *sbuf, unsigned int npixels)) { unsigned long linepixels = drm_rect_width(clip); unsigned long lines = drm_rect_height(clip); size_t sbuf_len = linepixels * fb->format->cpp[0]; void *stmp = NULL; unsigned long i; const void *sbuf; /* * Some source buffers, such as DMA memory, use write-combine * caching, so reads are uncached. Speed up access by fetching * one line at a time. */ if (!vaddr_cached_hint) { stmp = drm_format_conv_state_reserve(state, sbuf_len, GFP_KERNEL); if (!stmp) return -ENOMEM; } if (!dst_pitch) dst_pitch = drm_rect_width(clip) * dst_pixsize; vaddr += clip_offset(clip, fb->pitches[0], fb->format->cpp[0]); for (i = 0; i < lines; ++i) { if (stmp) sbuf = memcpy(stmp, vaddr, sbuf_len); else sbuf = vaddr; xfrm_line(dst, sbuf, linepixels); vaddr += fb->pitches[0]; dst += dst_pitch; } return 0; } /* TODO: Make this function work with multi-plane formats. */ static int __drm_fb_xfrm_toio(void __iomem *dst, unsigned long dst_pitch, unsigned long dst_pixsize, const void *vaddr, const struct drm_framebuffer *fb, const struct drm_rect *clip, bool vaddr_cached_hint, struct drm_format_conv_state *state, void (*xfrm_line)(void *dbuf, const void *sbuf, unsigned int npixels)) { unsigned long linepixels = drm_rect_width(clip); unsigned long lines = drm_rect_height(clip); size_t dbuf_len = linepixels * dst_pixsize; size_t stmp_off = round_up(dbuf_len, ARCH_KMALLOC_MINALIGN); /* for sbuf alignment */ size_t sbuf_len = linepixels * fb->format->cpp[0]; void *stmp = NULL; unsigned long i; const void *sbuf; void *dbuf; if (vaddr_cached_hint) { dbuf = drm_format_conv_state_reserve(state, dbuf_len, GFP_KERNEL); } else { dbuf = drm_format_conv_state_reserve(state, stmp_off + sbuf_len, GFP_KERNEL); stmp = dbuf + stmp_off; } if (!dbuf) return -ENOMEM; if (!dst_pitch) dst_pitch = linepixels * dst_pixsize; vaddr += clip_offset(clip, fb->pitches[0], fb->format->cpp[0]); for (i = 0; i < lines; ++i) { if (stmp) sbuf = memcpy(stmp, vaddr, sbuf_len); else sbuf = vaddr; xfrm_line(dbuf, sbuf, linepixels); memcpy_toio(dst, dbuf, dbuf_len); vaddr += fb->pitches[0]; dst += dst_pitch; } return 0; } /* TODO: Make this function work with multi-plane formats. */ static int drm_fb_xfrm(struct iosys_map *dst, const unsigned int *dst_pitch, const u8 *dst_pixsize, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, bool vaddr_cached_hint, struct drm_format_conv_state *state, void (*xfrm_line)(void *dbuf, const void *sbuf, unsigned int npixels)) { static const unsigned int default_dst_pitch[DRM_FORMAT_MAX_PLANES] = { 0, 0, 0, 0 }; if (!dst_pitch) dst_pitch = default_dst_pitch; /* TODO: handle src in I/O memory here */ if (dst[0].is_iomem) return __drm_fb_xfrm_toio(dst[0].vaddr_iomem, dst_pitch[0], dst_pixsize[0], src[0].vaddr, fb, clip, vaddr_cached_hint, state, xfrm_line); else return __drm_fb_xfrm(dst[0].vaddr, dst_pitch[0], dst_pixsize[0], src[0].vaddr, fb, clip, vaddr_cached_hint, state, xfrm_line); } #define ALIGN_DOWN_PIXELS(end, n, a) \ ((end) - ((n) & ((a) - 1))) static __always_inline void drm_fb_xfrm_line_32to8(void *dbuf, const void *sbuf, unsigned int pixels, u32 (*xfrm_pixel)(u32)) { __le32 *dbuf32 = dbuf; u8 *dbuf8; const __le32 *sbuf32 = sbuf; const __le32 *send32 = sbuf32 + pixels; /* write 4 pixels at once */ while (sbuf32 < ALIGN_DOWN_PIXELS(send32, pixels, 4)) { u32 pix[4] = { le32_to_cpup(sbuf32), le32_to_cpup(sbuf32 + 1), le32_to_cpup(sbuf32 + 2), le32_to_cpup(sbuf32 + 3), }; /* write output bytes in reverse order for little endianness */ u32 val32 = xfrm_pixel(pix[0]) | (xfrm_pixel(pix[1]) << 8) | (xfrm_pixel(pix[2]) << 16) | (xfrm_pixel(pix[3]) << 24); *dbuf32++ = cpu_to_le32(val32); sbuf32 += ARRAY_SIZE(pix); } /* write trailing pixels */ dbuf8 = (u8 __force *)dbuf32; while (sbuf32 < send32) *dbuf8++ = xfrm_pixel(le32_to_cpup(sbuf32++)); } static __always_inline void drm_fb_xfrm_line_32to16(void *dbuf, const void *sbuf, unsigned int pixels, u32 (*xfrm_pixel)(u32)) { __le64 *dbuf64 = dbuf; __le32 *dbuf32; __le16 *dbuf16; const __le32 *sbuf32 = sbuf; const __le32 *send32 = sbuf32 + pixels; #if defined(CONFIG_64BIT) /* write 4 pixels at once */ while (sbuf32 < ALIGN_DOWN_PIXELS(send32, pixels, 4)) { u32 pix[4] = { le32_to_cpup(sbuf32), le32_to_cpup(sbuf32 + 1), le32_to_cpup(sbuf32 + 2), le32_to_cpup(sbuf32 + 3), }; /* write output bytes in reverse order for little endianness */ u64 val64 = ((u64)xfrm_pixel(pix[0])) | ((u64)xfrm_pixel(pix[1]) << 16) | ((u64)xfrm_pixel(pix[2]) << 32) | ((u64)xfrm_pixel(pix[3]) << 48); *dbuf64++ = cpu_to_le64(val64); sbuf32 += ARRAY_SIZE(pix); } #endif /* write 2 pixels at once */ dbuf32 = (__le32 __force *)dbuf64; while (sbuf32 < ALIGN_DOWN_PIXELS(send32, pixels, 2)) { u32 pix[2] = { le32_to_cpup(sbuf32), le32_to_cpup(sbuf32 + 1), }; /* write output bytes in reverse order for little endianness */ u32 val32 = xfrm_pixel(pix[0]) | (xfrm_pixel(pix[1]) << 16); *dbuf32++ = cpu_to_le32(val32); sbuf32 += ARRAY_SIZE(pix); } /* write trailing pixel */ dbuf16 = (__le16 __force *)dbuf32; while (sbuf32 < send32) *dbuf16++ = cpu_to_le16(xfrm_pixel(le32_to_cpup(sbuf32++))); } static __always_inline void drm_fb_xfrm_line_32to24(void *dbuf, const void *sbuf, unsigned int pixels, u32 (*xfrm_pixel)(u32)) { __le32 *dbuf32 = dbuf; u8 *dbuf8; const __le32 *sbuf32 = sbuf; const __le32 *send32 = sbuf32 + pixels; /* write pixels in chunks of 4 */ while (sbuf32 < ALIGN_DOWN_PIXELS(send32, pixels, 4)) { u32 val24[4] = { xfrm_pixel(le32_to_cpup(sbuf32)), xfrm_pixel(le32_to_cpup(sbuf32 + 1)), xfrm_pixel(le32_to_cpup(sbuf32 + 2)), xfrm_pixel(le32_to_cpup(sbuf32 + 3)), }; u32 out32[3] = { /* write output bytes in reverse order for little endianness */ ((val24[0] & 0x000000ff)) | ((val24[0] & 0x0000ff00)) | ((val24[0] & 0x00ff0000)) | ((val24[1] & 0x000000ff) << 24), ((val24[1] & 0x0000ff00) >> 8) | ((val24[1] & 0x00ff0000) >> 8) | ((val24[2] & 0x000000ff) << 16) | ((val24[2] & 0x0000ff00) << 16), ((val24[2] & 0x00ff0000) >> 16) | ((val24[3] & 0x000000ff) << 8) | ((val24[3] & 0x0000ff00) << 8) | ((val24[3] & 0x00ff0000) << 8), }; *dbuf32++ = cpu_to_le32(out32[0]); *dbuf32++ = cpu_to_le32(out32[1]); *dbuf32++ = cpu_to_le32(out32[2]); sbuf32 += ARRAY_SIZE(val24); } /* write trailing pixel */ dbuf8 = (u8 __force *)dbuf32; while (sbuf32 < send32) { u32 val24 = xfrm_pixel(le32_to_cpup(sbuf32++)); /* write output in reverse order for little endianness */ *dbuf8++ = (val24 & 0x000000ff); *dbuf8++ = (val24 & 0x0000ff00) >> 8; *dbuf8++ = (val24 & 0x00ff0000) >> 16; } } static __always_inline void drm_fb_xfrm_line_32to32(void *dbuf, const void *sbuf, unsigned int pixels, u32 (*xfrm_pixel)(u32)) { __le32 *dbuf32 = dbuf; const __le32 *sbuf32 = sbuf; const __le32 *send32 = sbuf32 + pixels; while (sbuf32 < send32) *dbuf32++ = cpu_to_le32(xfrm_pixel(le32_to_cpup(sbuf32++))); } /** * drm_fb_memcpy - Copy clip buffer * @dst: Array of destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * * This function copies parts of a framebuffer to display memory. Destination and * framebuffer formats must match. No conversion takes place. The parameters @dst, * @dst_pitch and @src refer to arrays. Each array must have at least as many entries * as there are planes in @fb's format. Each entry stores the value for the format's * respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). */ void drm_fb_memcpy(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip) { static const unsigned int default_dst_pitch[DRM_FORMAT_MAX_PLANES] = { 0, 0, 0, 0 }; const struct drm_format_info *format = fb->format; unsigned int i, y, lines = drm_rect_height(clip); if (!dst_pitch) dst_pitch = default_dst_pitch; for (i = 0; i < format->num_planes; ++i) { unsigned int bpp_i = drm_format_info_bpp(format, i); unsigned int cpp_i = DIV_ROUND_UP(bpp_i, 8); size_t len_i = DIV_ROUND_UP(drm_rect_width(clip) * bpp_i, 8); unsigned int dst_pitch_i = dst_pitch[i]; struct iosys_map dst_i = dst[i]; struct iosys_map src_i = src[i]; if (!dst_pitch_i) dst_pitch_i = len_i; iosys_map_incr(&src_i, clip_offset(clip, fb->pitches[i], cpp_i)); for (y = 0; y < lines; y++) { /* TODO: handle src_i in I/O memory here */ iosys_map_memcpy_to(&dst_i, 0, src_i.vaddr, len_i); iosys_map_incr(&src_i, fb->pitches[i]); iosys_map_incr(&dst_i, dst_pitch_i); } } } EXPORT_SYMBOL(drm_fb_memcpy); static void drm_fb_swab16_line(void *dbuf, const void *sbuf, unsigned int pixels) { u16 *dbuf16 = dbuf; const u16 *sbuf16 = sbuf; const u16 *send16 = sbuf16 + pixels; while (sbuf16 < send16) *dbuf16++ = swab16(*sbuf16++); } static void drm_fb_swab32_line(void *dbuf, const void *sbuf, unsigned int pixels) { u32 *dbuf32 = dbuf; const u32 *sbuf32 = sbuf; const u32 *send32 = sbuf32 + pixels; while (sbuf32 < send32) *dbuf32++ = swab32(*sbuf32++); } /** * drm_fb_swab - Swap bytes into clip buffer * @dst: Array of destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @cached: Source buffer is mapped cached (eg. not write-combined) * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and swaps per-pixel * bytes during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. If @cached is * false a temporary buffer is used to cache one pixel line at a time to speed up * slow uncached reads. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). */ void drm_fb_swab(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, bool cached, struct drm_format_conv_state *state) { const struct drm_format_info *format = fb->format; u8 cpp = DIV_ROUND_UP(drm_format_info_bpp(format, 0), 8); void (*swab_line)(void *dbuf, const void *sbuf, unsigned int npixels); switch (cpp) { case 4: swab_line = drm_fb_swab32_line; break; case 2: swab_line = drm_fb_swab16_line; break; default: drm_warn_once(fb->dev, "Format %p4cc has unsupported pixel size.\n", &format->format); return; } drm_fb_xfrm(dst, dst_pitch, &cpp, src, fb, clip, cached, state, swab_line); } EXPORT_SYMBOL(drm_fb_swab); static void drm_fb_xrgb8888_to_rgb332_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to8(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_rgb332); } /** * drm_fb_xrgb8888_to_rgb332 - Convert XRGB8888 to RGB332 clip buffer * @dst: Array of RGB332 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for RGB332 devices that don't support XRGB8888 natively. */ void drm_fb_xrgb8888_to_rgb332(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 1, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_rgb332_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb332); static void drm_fb_xrgb8888_to_rgb565_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to16(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_rgb565); } /** * drm_fb_xrgb8888_to_rgb565 - Convert XRGB8888 to RGB565 clip buffer * @dst: Array of RGB565 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for RGB565 devices that don't support XRGB8888 natively. */ void drm_fb_xrgb8888_to_rgb565(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 2, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_rgb565_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb565); static void drm_fb_xrgb8888_to_rgb565be_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to16(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_rgb565be); } /** * drm_fb_xrgb8888_to_rgb565be - Convert XRGB8888 to RGB565|DRM_FORMAT_BIG_ENDIAN clip buffer * @dst: Array of RGB565BE destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for RGB565BE devices that don't support XRGB8888 natively. */ void drm_fb_xrgb8888_to_rgb565be(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 2, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_rgb565be_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb565be); static void drm_fb_xrgb8888_to_xrgb1555_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to16(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_xrgb1555); } /** * drm_fb_xrgb8888_to_xrgb1555 - Convert XRGB8888 to XRGB1555 clip buffer * @dst: Array of XRGB1555 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts * the color format during the process. The parameters @dst, @dst_pitch and * @src refer to arrays. Each array must have at least as many entries as * there are planes in @fb's format. Each entry stores the value for the * format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for XRGB1555 devices that don't support * XRGB8888 natively. */ void drm_fb_xrgb8888_to_xrgb1555(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 2, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_xrgb1555_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_xrgb1555); static void drm_fb_xrgb8888_to_argb1555_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to16(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_argb1555); } /** * drm_fb_xrgb8888_to_argb1555 - Convert XRGB8888 to ARGB1555 clip buffer * @dst: Array of ARGB1555 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts * the color format during the process. The parameters @dst, @dst_pitch and * @src refer to arrays. Each array must have at least as many entries as * there are planes in @fb's format. Each entry stores the value for the * format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for ARGB1555 devices that don't support * XRGB8888 natively. It sets an opaque alpha channel as part of the conversion. */ void drm_fb_xrgb8888_to_argb1555(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 2, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_argb1555_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_argb1555); static void drm_fb_xrgb8888_to_rgba5551_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to16(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_rgba5551); } /** * drm_fb_xrgb8888_to_rgba5551 - Convert XRGB8888 to RGBA5551 clip buffer * @dst: Array of RGBA5551 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts * the color format during the process. The parameters @dst, @dst_pitch and * @src refer to arrays. Each array must have at least as many entries as * there are planes in @fb's format. Each entry stores the value for the * format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for RGBA5551 devices that don't support * XRGB8888 natively. It sets an opaque alpha channel as part of the conversion. */ void drm_fb_xrgb8888_to_rgba5551(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 2, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_rgba5551_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgba5551); static void drm_fb_xrgb8888_to_rgb888_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to24(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_rgb888); } /** * drm_fb_xrgb8888_to_rgb888 - Convert XRGB8888 to RGB888 clip buffer * @dst: Array of RGB888 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for RGB888 devices that don't natively * support XRGB8888. */ void drm_fb_xrgb8888_to_rgb888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 3, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_rgb888_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888); static void drm_fb_xrgb8888_to_bgr888_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to24(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_bgr888); } /** * drm_fb_xrgb8888_to_bgr888 - Convert XRGB8888 to BGR888 clip buffer * @dst: Array of BGR888 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for BGR888 devices that don't natively * support XRGB8888. */ void drm_fb_xrgb8888_to_bgr888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 3, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_bgr888_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_bgr888); static void drm_fb_xrgb8888_to_argb8888_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to32(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_argb8888); } /** * drm_fb_xrgb8888_to_argb8888 - Convert XRGB8888 to ARGB8888 clip buffer * @dst: Array of ARGB8888 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. The parameters @dst, @dst_pitch and @src refer * to arrays. Each array must have at least as many entries as there are planes in * @fb's format. Each entry stores the value for the format's respective color plane * at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for ARGB8888 devices that don't support XRGB8888 * natively. It sets an opaque alpha channel as part of the conversion. */ void drm_fb_xrgb8888_to_argb8888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 4, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_argb8888_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_argb8888); static void drm_fb_xrgb8888_to_abgr8888_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to32(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_abgr8888); } /** * drm_fb_xrgb8888_to_abgr8888 - Convert XRGB8888 to ABGR8888 clip buffer * @dst: Array of ABGR8888 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. The parameters @dst, @dst_pitch and @src refer * to arrays. Each array must have at least as many entries as there are planes in * @fb's format. Each entry stores the value for the format's respective color plane * at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for ABGR8888 devices that don't support XRGB8888 * natively. It sets an opaque alpha channel as part of the conversion. */ void drm_fb_xrgb8888_to_abgr8888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 4, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_abgr8888_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_abgr8888); static void drm_fb_xrgb8888_to_xbgr8888_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to32(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_xbgr8888); } /** * drm_fb_xrgb8888_to_xbgr8888 - Convert XRGB8888 to XBGR8888 clip buffer * @dst: Array of XBGR8888 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. The parameters @dst, @dst_pitch and @src refer * to arrays. Each array must have at least as many entries as there are planes in * @fb's format. Each entry stores the value for the format's respective color plane * at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for XBGR8888 devices that don't support XRGB8888 * natively. */ void drm_fb_xrgb8888_to_xbgr8888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 4, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_xbgr8888_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_xbgr8888); static void drm_fb_xrgb8888_to_bgrx8888_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to32(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_bgrx8888); } /** * drm_fb_xrgb8888_to_bgrx8888 - Convert XRGB8888 to BGRX8888 clip buffer * @dst: Array of BGRX8888 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. The parameters @dst, @dst_pitch and @src refer * to arrays. Each array must have at least as many entries as there are planes in * @fb's format. Each entry stores the value for the format's respective color plane * at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for BGRX8888 devices that don't support XRGB8888 * natively. */ void drm_fb_xrgb8888_to_bgrx8888(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 4, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_bgrx8888_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_bgrx8888); static void drm_fb_xrgb8888_to_xrgb2101010_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to32(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_xrgb2101010); } /** * drm_fb_xrgb8888_to_xrgb2101010 - Convert XRGB8888 to XRGB2101010 clip buffer * @dst: Array of XRGB2101010 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for XRGB2101010 devices that don't support XRGB8888 * natively. */ void drm_fb_xrgb8888_to_xrgb2101010(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 4, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_xrgb2101010_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_xrgb2101010); static void drm_fb_xrgb8888_to_argb2101010_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to32(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_argb2101010); } /** * drm_fb_xrgb8888_to_argb2101010 - Convert XRGB8888 to ARGB2101010 clip buffer * @dst: Array of ARGB2101010 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts * the color format during the process. The parameters @dst, @dst_pitch and * @src refer to arrays. Each array must have at least as many entries as * there are planes in @fb's format. Each entry stores the value for the * format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for ARGB2101010 devices that don't support XRGB8888 * natively. */ void drm_fb_xrgb8888_to_argb2101010(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 4, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_argb2101010_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_argb2101010); static void drm_fb_xrgb8888_to_gray8_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to8(dbuf, sbuf, pixels, drm_pixel_xrgb8888_to_r8_bt601); } /** * drm_fb_xrgb8888_to_gray8 - Convert XRGB8888 to grayscale * @dst: Array of 8-bit grayscale destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * DRM doesn't have native monochrome or grayscale support. Drivers can use this * function for grayscale devices that don't support XRGB8888 natively.Such * drivers can announce the commonly supported XR24 format to userspace and use * this function to convert to the native format. Monochrome drivers will use the * most significant bit, where 1 means foreground color and 0 background color. * ITU BT.601 is being used for the RGB -> luma (brightness) conversion. */ void drm_fb_xrgb8888_to_gray8(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 1, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_xrgb8888_to_gray8_line); } EXPORT_SYMBOL(drm_fb_xrgb8888_to_gray8); static void drm_fb_argb8888_to_argb4444_line(void *dbuf, const void *sbuf, unsigned int pixels) { drm_fb_xfrm_line_32to16(dbuf, sbuf, pixels, drm_pixel_argb8888_to_argb4444); } /** * drm_fb_argb8888_to_argb4444 - Convert ARGB8888 to ARGB4444 clip buffer * @dst: Array of ARGB4444 destination buffers * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of ARGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts * the color format during the process. The parameters @dst, @dst_pitch and * @src refer to arrays. Each array must have at least as many entries as * there are planes in @fb's format. Each entry stores the value for the * format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). * * Drivers can use this function for ARGB4444 devices that don't support * ARGB8888 natively. */ void drm_fb_argb8888_to_argb4444(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const u8 dst_pixsize[DRM_FORMAT_MAX_PLANES] = { 2, }; drm_fb_xfrm(dst, dst_pitch, dst_pixsize, src, fb, clip, false, state, drm_fb_argb8888_to_argb4444_line); } EXPORT_SYMBOL(drm_fb_argb8888_to_argb4444); static void drm_fb_gray8_to_gray2_line(void *dbuf, const void *sbuf, unsigned int pixels) { u8 *dbuf8 = dbuf; const u8 *sbuf8 = sbuf; u8 px; while (pixels) { unsigned int i, bits = min(pixels, 4U); u8 byte = 0; for (i = 0; i < bits; i++, pixels--) { byte >>= 2; px = (*sbuf8++ * 3 + 127) / 255; byte |= (px &= 0x03) << 6; } *dbuf8++ = byte; } } static void drm_fb_gray8_to_mono_line(void *dbuf, const void *sbuf, unsigned int pixels) { u8 *dbuf8 = dbuf; const u8 *sbuf8 = sbuf; while (pixels) { unsigned int i, bits = min(pixels, 8U); u8 byte = 0; for (i = 0; i < bits; i++, pixels--) { if (*sbuf8++ >= 128) byte |= BIT(i); } *dbuf8++ = byte; } } /** * drm_fb_xrgb8888_to_mono - Convert XRGB8888 to monochrome * @dst: Array of monochrome destination buffers (0=black, 1=white) * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). The first pixel (upper left corner of the clip rectangle) will * be converted and copied to the first bit (LSB) in the first byte of the monochrome * destination buffer. If the caller requires that the first pixel in a byte must * be located at an x-coordinate that is a multiple of 8, then the caller must take * care itself of supplying a suitable clip rectangle. * * DRM doesn't have native monochrome support. Drivers can use this function for * monochrome devices that don't support XRGB8888 natively. Such drivers can * announce the commonly supported XR24 format to userspace and use this function * to convert to the native format. * * This function uses drm_fb_xrgb8888_to_gray8() to convert to grayscale and * then the result is converted from grayscale to monochrome. */ void drm_fb_xrgb8888_to_mono(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const unsigned int default_dst_pitch[DRM_FORMAT_MAX_PLANES] = { 0, 0, 0, 0 }; unsigned int linepixels = drm_rect_width(clip); unsigned int lines = drm_rect_height(clip); unsigned int cpp = fb->format->cpp[0]; unsigned int len_src32 = linepixels * cpp; struct drm_device *dev = fb->dev; void *vaddr = src[0].vaddr; unsigned int dst_pitch_0; unsigned int y; u8 *mono = dst[0].vaddr, *gray8; u32 *src32; if (drm_WARN_ON(dev, fb->format->format != DRM_FORMAT_XRGB8888)) return; if (!dst_pitch) dst_pitch = default_dst_pitch; dst_pitch_0 = dst_pitch[0]; /* * The mono destination buffer contains 1 bit per pixel */ if (!dst_pitch_0) dst_pitch_0 = DIV_ROUND_UP(linepixels, 8); /* * The dma memory is write-combined so reads are uncached. * Speed up by fetching one line at a time. * * Also, format conversion from XR24 to monochrome are done * line-by-line but are converted to 8-bit grayscale as an * intermediate step. * * Allocate a buffer to be used for both copying from the cma * memory and to store the intermediate grayscale line pixels. */ src32 = drm_format_conv_state_reserve(state, len_src32 + linepixels, GFP_KERNEL); if (!src32) return; gray8 = (u8 *)src32 + len_src32; vaddr += clip_offset(clip, fb->pitches[0], cpp); for (y = 0; y < lines; y++) { src32 = memcpy(src32, vaddr, len_src32); drm_fb_xrgb8888_to_gray8_line(gray8, src32, linepixels); drm_fb_gray8_to_mono_line(mono, gray8, linepixels); vaddr += fb->pitches[0]; mono += dst_pitch_0; } } EXPORT_SYMBOL(drm_fb_xrgb8888_to_mono); /** * drm_fb_xrgb8888_to_gray2 - Convert XRGB8888 to gray2 * @dst: Array of gray2 destination buffer * @dst_pitch: Array of numbers of bytes between the start of two consecutive scanlines * within @dst; can be NULL if scanlines are stored next to each other. * @src: Array of XRGB8888 source buffers * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @state: Transform and conversion state * * This function copies parts of a framebuffer to display memory and converts the * color format during the process. Destination and framebuffer formats must match. The * parameters @dst, @dst_pitch and @src refer to arrays. Each array must have at * least as many entries as there are planes in @fb's format. Each entry stores the * value for the format's respective color plane at the same index. * * This function does not apply clipping on @dst (i.e. the destination is at the * top-left corner). The first pixel (upper left corner of the clip rectangle) will * be converted and copied to the two first bits (LSB) in the first byte of the gray2 * destination buffer. If the caller requires that the first pixel in a byte must * be located at an x-coordinate that is a multiple of 8, then the caller must take * care itself of supplying a suitable clip rectangle. * * DRM doesn't have native gray2 support. Drivers can use this function for * gray2 devices that don't support XRGB8888 natively. Such drivers can * announce the commonly supported XR24 format to userspace and use this function * to convert to the native format. * */ void drm_fb_xrgb8888_to_gray2(struct iosys_map *dst, const unsigned int *dst_pitch, const struct iosys_map *src, const struct drm_framebuffer *fb, const struct drm_rect *clip, struct drm_format_conv_state *state) { static const unsigned int default_dst_pitch[DRM_FORMAT_MAX_PLANES] = { 0, 0, 0, 0 }; unsigned int linepixels = drm_rect_width(clip); unsigned int lines = drm_rect_height(clip); unsigned int cpp = fb->format->cpp[0]; unsigned int len_src32 = linepixels * cpp; struct drm_device *dev = fb->dev; void *vaddr = src[0].vaddr; unsigned int dst_pitch_0; unsigned int y; u8 *gray2 = dst[0].vaddr, *gray8; u32 *src32; if (drm_WARN_ON(dev, fb->format->format != DRM_FORMAT_XRGB8888)) return; if (!dst_pitch) dst_pitch = default_dst_pitch; dst_pitch_0 = dst_pitch[0]; /* * The gray2 destination buffer contains 2 bit per pixel */ if (!dst_pitch_0) dst_pitch_0 = DIV_ROUND_UP(linepixels, 4); /* * The dma memory is write-combined so reads are uncached. * Speed up by fetching one line at a time. * * Also, format conversion from XR24 to gray2 are done * line-by-line but are converted to 8-bit grayscale as an * intermediate step. * * Allocate a buffer to be used for both copying from the cma * memory and to store the intermediate grayscale line pixels. */ src32 = drm_format_conv_state_reserve(state, len_src32 + linepixels, GFP_KERNEL); if (!src32) return; gray8 = (u8 *)src32 + len_src32; vaddr += clip_offset(clip, fb->pitches[0], cpp); for (y = 0; y < lines; y++) { src32 = memcpy(src32, vaddr, len_src32); drm_fb_xrgb8888_to_gray8_line(gray8, src32, linepixels); drm_fb_gray8_to_gray2_line(gray2, gray8, linepixels); vaddr += fb->pitches[0]; gray2 += dst_pitch_0; } } EXPORT_SYMBOL(drm_fb_xrgb8888_to_gray2); |
| 415 29 411 22 409 20 407 133 401 135 405 1 8 385 381 10 10 17 372 109 371 8 375 370 134 | 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 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "rsrc.h" #include "nop.h" struct io_nop { struct file *file; int result; int fd; unsigned int flags; __u64 extra1; __u64 extra2; }; #define NOP_FLAGS (IORING_NOP_INJECT_RESULT | IORING_NOP_FIXED_FILE | \ IORING_NOP_FIXED_BUFFER | IORING_NOP_FILE | \ IORING_NOP_TW | IORING_NOP_CQE32) int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); nop->flags = READ_ONCE(sqe->nop_flags); if (nop->flags & ~NOP_FLAGS) return -EINVAL; if (nop->flags & IORING_NOP_INJECT_RESULT) nop->result = READ_ONCE(sqe->len); else nop->result = 0; if (nop->flags & IORING_NOP_FILE) nop->fd = READ_ONCE(sqe->fd); else nop->fd = -1; if (nop->flags & IORING_NOP_FIXED_FILE) req->flags |= REQ_F_FIXED_FILE; if (nop->flags & IORING_NOP_FIXED_BUFFER) req->buf_index = READ_ONCE(sqe->buf_index); if (nop->flags & IORING_NOP_CQE32) { struct io_ring_ctx *ctx = req->ctx; if (!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED))) return -EINVAL; nop->extra1 = READ_ONCE(sqe->off); nop->extra2 = READ_ONCE(sqe->addr); } return 0; } int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); int ret = nop->result; if (nop->flags & IORING_NOP_FILE) { if (req->flags & REQ_F_FIXED_FILE) req->file = io_file_get_fixed(req, nop->fd, issue_flags); else req->file = io_file_get_normal(req, nop->fd); if (!req->file) { ret = -EBADF; goto done; } } if (nop->flags & IORING_NOP_FIXED_BUFFER) { if (!io_find_buf_node(req, issue_flags)) ret = -EFAULT; } done: if (ret < 0) req_set_fail(req); if (nop->flags & IORING_NOP_CQE32) io_req_set_res32(req, ret, 0, nop->extra1, nop->extra2); else io_req_set_res(req, ret, 0); if (nop->flags & IORING_NOP_TW) { req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); return IOU_ISSUE_SKIP_COMPLETE; } return IOU_COMPLETE; } |
| 1 1 2 2 2 1 3 7 1 6 2 1 1 1 1 1 6 6 1 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 | // 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 __free(fput) = NULL; filp = fget(fd); if (!filp) return -EBADF; /* Ensure the FD is a vfio FD. */ if (!kvm_vfio_file_is_valid(filp)) return -EINVAL; guard(mutex)(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file == filp) return -EEXIST; } kvf = kzalloc_obj(*kvf, GFP_KERNEL_ACCOUNT); if (!kvf) return -ENOMEM; kvf->file = get_file(filp); list_add_tail(&kvf->node, &kv->file_list); kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); return 0; } static void kvm_vfio_file_free(struct kvm_device *dev, struct kvm_vfio_file *kvf) { #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); } static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; guard(mutex)(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file == fd_file(f)) { kvm_vfio_file_free(dev, kvf); kvm_vfio_update_coherency(dev); return 0; } } return -ENOENT; } #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; if (copy_from_user(¶m, arg, sizeof(struct kvm_vfio_spapr_tce))) return -EFAULT; CLASS(fd, f)(param.groupfd); if (fd_empty(f)) return -EBADF; guard(mutex)(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != fd_file(f)) continue; if (!kvf->iommu_group) { kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file); if (WARN_ON_ONCE(!kvf->iommu_group)) return -EIO; } return kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd, kvf->iommu_group); } return -ENOENT; } #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) kvm_vfio_file_free(dev, kvf); 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 const 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_obj(*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); } |
| 68 11 31 68 11 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __SOUND_CONTROL_H #define __SOUND_CONTROL_H /* * Header file for control interface * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/rwsem.h> #include <linux/wait.h> #include <linux/nospec.h> #include <sound/asound.h> #define snd_kcontrol_chip(kcontrol) ((kcontrol)->private_data) struct snd_kcontrol; typedef int (snd_kcontrol_info_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_elem_info * uinfo); typedef int (snd_kcontrol_get_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_elem_value * ucontrol); typedef int (snd_kcontrol_put_t) (struct snd_kcontrol * kcontrol, struct snd_ctl_elem_value * ucontrol); typedef int (snd_kcontrol_tlv_rw_t)(struct snd_kcontrol *kcontrol, int op_flag, /* SNDRV_CTL_TLV_OP_XXX */ unsigned int size, unsigned int __user *tlv); /* internal flag for skipping validations */ #ifdef CONFIG_SND_CTL_DEBUG #define SNDRV_CTL_ELEM_ACCESS_SKIP_CHECK (1 << 24) #define snd_ctl_skip_validation(info) \ ((info)->access & SNDRV_CTL_ELEM_ACCESS_SKIP_CHECK) #else #define SNDRV_CTL_ELEM_ACCESS_SKIP_CHECK 0 #define snd_ctl_skip_validation(info) true #endif /* kernel only - LED bits */ #define SNDRV_CTL_ELEM_ACCESS_LED_SHIFT 25 #define SNDRV_CTL_ELEM_ACCESS_LED_MASK (7<<25) /* kernel three bits - LED group */ #define SNDRV_CTL_ELEM_ACCESS_SPK_LED (1<<25) /* kernel speaker (output) LED flag */ #define SNDRV_CTL_ELEM_ACCESS_MIC_LED (2<<25) /* kernel microphone (input) LED flag */ enum { SNDRV_CTL_TLV_OP_READ = 0, SNDRV_CTL_TLV_OP_WRITE = 1, SNDRV_CTL_TLV_OP_CMD = -1, }; struct snd_kcontrol_new { snd_ctl_elem_iface_t iface; /* interface identifier */ unsigned int device; /* device/client number */ unsigned int subdevice; /* subdevice (substream) number */ const char *name; /* ASCII name of item */ unsigned int index; /* index of item */ unsigned int access; /* access rights */ unsigned int count; /* count of same elements */ snd_kcontrol_info_t *info; snd_kcontrol_get_t *get; snd_kcontrol_put_t *put; union { snd_kcontrol_tlv_rw_t *c; const unsigned int *p; } tlv; unsigned long private_value; }; struct snd_kcontrol_volatile { struct snd_ctl_file *owner; /* locked */ unsigned int access; /* access rights */ }; struct snd_kcontrol { struct list_head list; /* list of controls */ struct snd_ctl_elem_id id; unsigned int count; /* count of same elements */ snd_kcontrol_info_t *info; snd_kcontrol_get_t *get; snd_kcontrol_put_t *put; union { snd_kcontrol_tlv_rw_t *c; const unsigned int *p; } tlv; unsigned long private_value; void *private_data; void (*private_free)(struct snd_kcontrol *kcontrol); struct snd_kcontrol_volatile vd[] __counted_by(count); /* volatile data */ }; #define snd_kcontrol(n) list_entry(n, struct snd_kcontrol, list) struct snd_kctl_event { struct list_head list; /* list of events */ struct snd_ctl_elem_id id; unsigned int mask; }; #define snd_kctl_event(n) list_entry(n, struct snd_kctl_event, list) struct pid; enum { SND_CTL_SUBDEV_PCM, SND_CTL_SUBDEV_RAWMIDI, SND_CTL_SUBDEV_ITEMS, }; struct snd_ctl_file { struct list_head list; /* list of all control files */ struct snd_card *card; struct pid *pid; int preferred_subdevice[SND_CTL_SUBDEV_ITEMS]; wait_queue_head_t change_sleep; spinlock_t read_lock; struct snd_fasync *fasync; int subscribed; /* read interface is activated */ struct list_head events; /* waiting events for read */ }; struct snd_ctl_layer_ops { struct snd_ctl_layer_ops *next; const char *module_name; void (*lregister)(struct snd_card *card); void (*ldisconnect)(struct snd_card *card); void (*lnotify)(struct snd_card *card, unsigned int mask, struct snd_kcontrol *kctl, unsigned int ioff); }; #define snd_ctl_file(n) list_entry(n, struct snd_ctl_file, list) typedef int (*snd_kctl_ioctl_func_t) (struct snd_card * card, struct snd_ctl_file * control, unsigned int cmd, unsigned long arg); void snd_ctl_notify(struct snd_card * card, unsigned int mask, struct snd_ctl_elem_id * id); void snd_ctl_notify_one(struct snd_card * card, unsigned int mask, struct snd_kcontrol * kctl, unsigned int ioff); struct snd_kcontrol *snd_ctl_new1(const struct snd_kcontrol_new * kcontrolnew, void * private_data); void snd_ctl_free_one(struct snd_kcontrol * kcontrol); int snd_ctl_add(struct snd_card * card, struct snd_kcontrol * kcontrol); int snd_ctl_remove(struct snd_card * card, struct snd_kcontrol * kcontrol); int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace); int snd_ctl_remove_id(struct snd_card * card, struct snd_ctl_elem_id *id); int snd_ctl_rename_id(struct snd_card * card, struct snd_ctl_elem_id *src_id, struct snd_ctl_elem_id *dst_id); void snd_ctl_rename(struct snd_card *card, struct snd_kcontrol *kctl, const char *name); int snd_ctl_activate_id(struct snd_card *card, struct snd_ctl_elem_id *id, int active); struct snd_kcontrol *snd_ctl_find_numid(struct snd_card *card, unsigned int numid); struct snd_kcontrol *snd_ctl_find_id(struct snd_card *card, const struct snd_ctl_elem_id *id); /** * snd_ctl_find_id_mixer - find the control instance with the given name string * @card: the card instance * @name: the name string * * Finds the control instance with the given name and * @SNDRV_CTL_ELEM_IFACE_MIXER. Other fields are set to zero. * * This is merely a wrapper to snd_ctl_find_id(). * * Return: The pointer of the instance if found, or %NULL if not. */ static inline struct snd_kcontrol * snd_ctl_find_id_mixer(struct snd_card *card, const char *name) { struct snd_ctl_elem_id id = {}; id.iface = SNDRV_CTL_ELEM_IFACE_MIXER; strscpy(id.name, name, sizeof(id.name)); return snd_ctl_find_id(card, &id); } int snd_ctl_create(struct snd_card *card); extern struct rw_semaphore snd_ioctl_rwsem; int snd_ctl_register_ioctl(snd_kctl_ioctl_func_t fcn); int snd_ctl_unregister_ioctl(snd_kctl_ioctl_func_t fcn); #ifdef CONFIG_COMPAT int snd_ctl_register_ioctl_compat(snd_kctl_ioctl_func_t fcn); int snd_ctl_unregister_ioctl_compat(snd_kctl_ioctl_func_t fcn); #else #define snd_ctl_register_ioctl_compat(fcn) #define snd_ctl_unregister_ioctl_compat(fcn) #endif int snd_ctl_request_layer(const char *module_name); void snd_ctl_register_layer(struct snd_ctl_layer_ops *lops); void snd_ctl_disconnect_layer(struct snd_ctl_layer_ops *lops); int snd_ctl_get_preferred_subdevice(struct snd_card *card, int type); static inline unsigned int snd_ctl_get_ioffnum(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id) { unsigned int ioff = id->numid - kctl->id.numid; return array_index_nospec(ioff, kctl->count); } static inline unsigned int snd_ctl_get_ioffidx(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id) { unsigned int ioff = id->index - kctl->id.index; return array_index_nospec(ioff, kctl->count); } static inline unsigned int snd_ctl_get_ioff(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id) { if (id->numid) { return snd_ctl_get_ioffnum(kctl, id); } else { return snd_ctl_get_ioffidx(kctl, id); } } static inline struct snd_ctl_elem_id *snd_ctl_build_ioff(struct snd_ctl_elem_id *dst_id, struct snd_kcontrol *src_kctl, unsigned int offset) { *dst_id = src_kctl->id; dst_id->index += offset; dst_id->numid += offset; return dst_id; } /* * Frequently used control callbacks/helpers */ int snd_ctl_boolean_mono_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); int snd_ctl_boolean_stereo_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); int snd_ctl_enum_info(struct snd_ctl_elem_info *info, unsigned int channels, unsigned int items, const char *const names[]); /* * virtual master control */ struct snd_kcontrol *snd_ctl_make_virtual_master(char *name, const unsigned int *tlv); int _snd_ctl_add_follower(struct snd_kcontrol *master, struct snd_kcontrol *follower, unsigned int flags); /* optional flags for follower */ #define SND_CTL_FOLLOWER_NEED_UPDATE (1 << 0) /** * snd_ctl_add_follower - Add a virtual follower control * @master: vmaster element * @follower: follower element to add * * Add a virtual follower control to the given master element created via * snd_ctl_create_virtual_master() beforehand. * * All followers must be the same type (returning the same information * via info callback). The function doesn't check it, so it's your * responsibility. * * Also, some additional limitations: * at most two channels, * logarithmic volume control (dB level) thus no linear volume, * master can only attenuate the volume without gain * * Return: Zero if successful or a negative error code. */ static inline int snd_ctl_add_follower(struct snd_kcontrol *master, struct snd_kcontrol *follower) { return _snd_ctl_add_follower(master, follower, 0); } int snd_ctl_add_followers(struct snd_card *card, struct snd_kcontrol *master, const char * const *list); /** * snd_ctl_add_follower_uncached - Add a virtual follower control * @master: vmaster element * @follower: follower element to add * * Add a virtual follower control to the given master. * Unlike snd_ctl_add_follower(), the element added via this function * is supposed to have volatile values, and get callback is called * at each time queried from the master. * * When the control peeks the hardware values directly and the value * can be changed by other means than the put callback of the element, * this function should be used to keep the value always up-to-date. * * Return: Zero if successful or a negative error code. */ static inline int snd_ctl_add_follower_uncached(struct snd_kcontrol *master, struct snd_kcontrol *follower) { return _snd_ctl_add_follower(master, follower, SND_CTL_FOLLOWER_NEED_UPDATE); } int snd_ctl_add_vmaster_hook(struct snd_kcontrol *kctl, void (*hook)(void *private_data, int), void *private_data); void snd_ctl_sync_vmaster(struct snd_kcontrol *kctl, bool hook_only); #define snd_ctl_sync_vmaster_hook(kctl) snd_ctl_sync_vmaster(kctl, true) int snd_ctl_apply_vmaster_followers(struct snd_kcontrol *kctl, int (*func)(struct snd_kcontrol *vfollower, struct snd_kcontrol *follower, void *arg), void *arg); /* * Control LED trigger layer */ #define SND_CTL_LAYER_MODULE_LED "snd-ctl-led" #if IS_MODULE(CONFIG_SND_CTL_LED) static inline int snd_ctl_led_request(void) { return snd_ctl_request_layer(SND_CTL_LAYER_MODULE_LED); } #else static inline int snd_ctl_led_request(void) { return 0; } #endif /* * Helper functions for jack-detection controls */ struct snd_kcontrol * snd_kctl_jack_new(const char *name, struct snd_card *card); void snd_kctl_jack_report(struct snd_card *card, struct snd_kcontrol *kctl, bool status); #endif /* __SOUND_CONTROL_H */ |
| 6 4 2 5 1 1 4 4 4 1 1 2 1 1 2 4 4 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 | // SPDX-License-Identifier: GPL-2.0+ /* * REINER SCT cyberJack pinpad/e-com USB Chipcard Reader Driver * * Copyright (C) 2001 REINER SCT * Author: Matthias Bruestle * * Contact: support@reiner-sct.com (see MAINTAINERS) * * This program is largely derived from work by the linux-usb group * and associated source files. Please see the usb/serial files for * individual credits and copyrights. * * Thanks to Greg Kroah-Hartman (greg@kroah.com) for his help and * patience. * * In case of problems, please write to the contact e-mail address * mentioned above. * * Please note that later models of the cyberjack reader family are * supported by a libusb-based userspace device driver. * * Homepage: http://www.reiner-sct.de/support/treiber_cyberjack.php#linux */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/usb.h> #include <linux/usb/serial.h> #define CYBERJACK_LOCAL_BUF_SIZE 32 #define DRIVER_AUTHOR "Matthias Bruestle" #define DRIVER_DESC "REINER SCT cyberJack pinpad/e-com USB Chipcard Reader Driver" #define CYBERJACK_VENDOR_ID 0x0C4B #define CYBERJACK_PRODUCT_ID 0x0100 /* Function prototypes */ static int cyberjack_port_probe(struct usb_serial_port *port); static void cyberjack_port_remove(struct usb_serial_port *port); static int cyberjack_open(struct tty_struct *tty, struct usb_serial_port *port); static void cyberjack_close(struct usb_serial_port *port); static int cyberjack_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count); static unsigned int cyberjack_write_room(struct tty_struct *tty); static void cyberjack_read_int_callback(struct urb *urb); static void cyberjack_read_bulk_callback(struct urb *urb); static void cyberjack_write_bulk_callback(struct urb *urb); static const struct usb_device_id id_table[] = { { USB_DEVICE(CYBERJACK_VENDOR_ID, CYBERJACK_PRODUCT_ID) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); static struct usb_serial_driver cyberjack_device = { .driver = { .name = "cyberjack", }, .description = "Reiner SCT Cyberjack USB card reader", .id_table = id_table, .num_ports = 1, .num_bulk_out = 1, .port_probe = cyberjack_port_probe, .port_remove = cyberjack_port_remove, .open = cyberjack_open, .close = cyberjack_close, .write = cyberjack_write, .write_room = cyberjack_write_room, .read_int_callback = cyberjack_read_int_callback, .read_bulk_callback = cyberjack_read_bulk_callback, .write_bulk_callback = cyberjack_write_bulk_callback, }; static struct usb_serial_driver * const serial_drivers[] = { &cyberjack_device, NULL }; struct cyberjack_private { spinlock_t lock; /* Lock for SMP */ short rdtodo; /* Bytes still to read */ unsigned char wrbuf[5*64]; /* Buffer for collecting data to write */ short wrfilled; /* Overall data size we already got */ short wrsent; /* Data already sent */ }; static int cyberjack_port_probe(struct usb_serial_port *port) { struct cyberjack_private *priv; int result; priv = kmalloc_obj(struct cyberjack_private); if (!priv) return -ENOMEM; spin_lock_init(&priv->lock); priv->rdtodo = 0; priv->wrfilled = 0; priv->wrsent = 0; usb_set_serial_port_data(port, priv); result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); if (result) dev_err(&port->dev, "usb_submit_urb(read int) failed\n"); return 0; } static void cyberjack_port_remove(struct usb_serial_port *port) { struct cyberjack_private *priv; usb_kill_urb(port->interrupt_in_urb); priv = usb_get_serial_port_data(port); kfree(priv); } static int cyberjack_open(struct tty_struct *tty, struct usb_serial_port *port) { struct cyberjack_private *priv; unsigned long flags; dev_dbg(&port->dev, "%s - usb_clear_halt\n", __func__); usb_clear_halt(port->serial->dev, port->write_urb->pipe); priv = usb_get_serial_port_data(port); spin_lock_irqsave(&priv->lock, flags); priv->rdtodo = 0; priv->wrfilled = 0; priv->wrsent = 0; spin_unlock_irqrestore(&priv->lock, flags); return 0; } static void cyberjack_close(struct usb_serial_port *port) { usb_kill_urb(port->write_urb); usb_kill_urb(port->read_urb); } static int cyberjack_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count) { struct device *dev = &port->dev; struct cyberjack_private *priv = usb_get_serial_port_data(port); unsigned long flags; int result; int wrexpected; if (count == 0) { dev_dbg(dev, "%s - write request of 0 bytes\n", __func__); return 0; } if (!test_and_clear_bit(0, &port->write_urbs_free)) { dev_dbg(dev, "%s - already writing\n", __func__); return 0; } spin_lock_irqsave(&priv->lock, flags); if (count+priv->wrfilled > sizeof(priv->wrbuf)) { /* To much data for buffer. Reset buffer. */ priv->wrfilled = 0; spin_unlock_irqrestore(&priv->lock, flags); set_bit(0, &port->write_urbs_free); return 0; } /* Copy data */ memcpy(priv->wrbuf + priv->wrfilled, buf, count); usb_serial_debug_data(dev, __func__, count, priv->wrbuf + priv->wrfilled); priv->wrfilled += count; if (priv->wrfilled >= 3) { wrexpected = ((int)priv->wrbuf[2]<<8)+priv->wrbuf[1]+3; dev_dbg(dev, "%s - expected data: %d\n", __func__, wrexpected); } else wrexpected = sizeof(priv->wrbuf); if (priv->wrfilled >= wrexpected) { /* We have enough data to begin transmission */ int length; dev_dbg(dev, "%s - transmitting data (frame 1)\n", __func__); length = (wrexpected > port->bulk_out_size) ? port->bulk_out_size : wrexpected; memcpy(port->write_urb->transfer_buffer, priv->wrbuf, length); priv->wrsent = length; /* set up our urb */ port->write_urb->transfer_buffer_length = length; /* send the data out the bulk port */ result = usb_submit_urb(port->write_urb, GFP_ATOMIC); if (result) { dev_err(&port->dev, "%s - failed submitting write urb, error %d\n", __func__, result); /* Throw away data. No better idea what to do with it. */ priv->wrfilled = 0; priv->wrsent = 0; spin_unlock_irqrestore(&priv->lock, flags); set_bit(0, &port->write_urbs_free); return 0; } dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent); dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled); if (priv->wrsent >= priv->wrfilled) { dev_dbg(dev, "%s - buffer cleaned\n", __func__); memset(priv->wrbuf, 0, sizeof(priv->wrbuf)); priv->wrfilled = 0; priv->wrsent = 0; } } spin_unlock_irqrestore(&priv->lock, flags); return count; } static unsigned int cyberjack_write_room(struct tty_struct *tty) { /* FIXME: .... */ return CYBERJACK_LOCAL_BUF_SIZE; } static void cyberjack_read_int_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct cyberjack_private *priv = usb_get_serial_port_data(port); struct device *dev = &port->dev; unsigned char *data = urb->transfer_buffer; int status = urb->status; unsigned long flags; int result; /* the urb might have been killed. */ if (status) return; usb_serial_debug_data(dev, __func__, urb->actual_length, data); /* React only to interrupts signaling a bulk_in transfer */ if (urb->actual_length == 4 && data[0] == 0x01) { short old_rdtodo; /* This is a announcement of coming bulk_ins. */ unsigned short size = ((unsigned short)data[3]<<8)+data[2]+3; spin_lock_irqsave(&priv->lock, flags); old_rdtodo = priv->rdtodo; if (old_rdtodo > SHRT_MAX - size) { dev_dbg(dev, "Too many bulk_in urbs to do.\n"); spin_unlock_irqrestore(&priv->lock, flags); goto resubmit; } /* "+=" is probably more fault tolerant than "=" */ priv->rdtodo += size; dev_dbg(dev, "%s - rdtodo: %d\n", __func__, priv->rdtodo); spin_unlock_irqrestore(&priv->lock, flags); if (!old_rdtodo) { result = usb_submit_urb(port->read_urb, GFP_ATOMIC); if (result) dev_err(dev, "%s - failed resubmitting read urb, error %d\n", __func__, result); dev_dbg(dev, "%s - usb_submit_urb(read urb)\n", __func__); } } resubmit: result = usb_submit_urb(port->interrupt_in_urb, GFP_ATOMIC); if (result) dev_err(&port->dev, "usb_submit_urb(read int) failed\n"); dev_dbg(dev, "%s - usb_submit_urb(int urb)\n", __func__); } static void cyberjack_read_bulk_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct cyberjack_private *priv = usb_get_serial_port_data(port); struct device *dev = &port->dev; unsigned char *data = urb->transfer_buffer; unsigned long flags; short todo; int result; int status = urb->status; usb_serial_debug_data(dev, __func__, urb->actual_length, data); if (status) { dev_dbg(dev, "%s - nonzero read bulk status received: %d\n", __func__, status); return; } if (urb->actual_length) { tty_insert_flip_string(&port->port, data, urb->actual_length); tty_flip_buffer_push(&port->port); } spin_lock_irqsave(&priv->lock, flags); /* Reduce urbs to do by one. */ priv->rdtodo -= urb->actual_length; /* Just to be sure */ if (priv->rdtodo < 0) priv->rdtodo = 0; todo = priv->rdtodo; spin_unlock_irqrestore(&priv->lock, flags); dev_dbg(dev, "%s - rdtodo: %d\n", __func__, todo); /* Continue to read if we have still urbs to do. */ if (todo /* || (urb->actual_length==port->bulk_in_endpointAddress)*/) { result = usb_submit_urb(port->read_urb, GFP_ATOMIC); if (result) dev_err(dev, "%s - failed resubmitting read urb, error %d\n", __func__, result); dev_dbg(dev, "%s - usb_submit_urb(read urb)\n", __func__); } } static void cyberjack_write_bulk_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct cyberjack_private *priv = usb_get_serial_port_data(port); struct device *dev = &port->dev; int status = urb->status; unsigned long flags; bool resubmitted = false; if (status) { dev_dbg(dev, "%s - nonzero write bulk status received: %d\n", __func__, status); set_bit(0, &port->write_urbs_free); return; } spin_lock_irqsave(&priv->lock, flags); /* only do something if we have more data to send */ if (priv->wrfilled) { int length, blksize, result; dev_dbg(dev, "%s - transmitting data (frame n)\n", __func__); length = ((priv->wrfilled - priv->wrsent) > port->bulk_out_size) ? port->bulk_out_size : (priv->wrfilled - priv->wrsent); memcpy(port->write_urb->transfer_buffer, priv->wrbuf + priv->wrsent, length); priv->wrsent += length; /* set up our urb */ port->write_urb->transfer_buffer_length = length; /* send the data out the bulk port */ result = usb_submit_urb(port->write_urb, GFP_ATOMIC); if (result) { dev_err(dev, "%s - failed submitting write urb, error %d\n", __func__, result); /* Throw away data. No better idea what to do with it. */ priv->wrfilled = 0; priv->wrsent = 0; goto exit; } resubmitted = true; dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent); dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled); blksize = ((int)priv->wrbuf[2]<<8)+priv->wrbuf[1]+3; if (priv->wrsent >= priv->wrfilled || priv->wrsent >= blksize) { dev_dbg(dev, "%s - buffer cleaned\n", __func__); memset(priv->wrbuf, 0, sizeof(priv->wrbuf)); priv->wrfilled = 0; priv->wrsent = 0; } } exit: spin_unlock_irqrestore(&priv->lock, flags); if (!resubmitted) set_bit(0, &port->write_urbs_free); usb_serial_port_softint(port); } module_usb_serial_driver(serial_drivers, id_table); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 24 24 13 9 8 12 2 6 24 13 13 13 24 13 24 24 24 13 13 2 24 6 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 | /* * JFFS2 -- Journalling Flash File System, Version 2. * * Copyright © 2001-2007 Red Hat, Inc. * Copyright © 2004-2010 David Woodhouse <dwmw2@infradead.org> * * Created by David Woodhouse <dwmw2@infradead.org> * * For licensing information, see the file 'LICENCE' in this directory. * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mtd/mtd.h> #include <linux/mm.h> /* kvfree() */ #include "nodelist.h" static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *, struct jffs2_inode_cache *, struct jffs2_full_dirent **); static inline struct jffs2_inode_cache * first_inode_chain(int *i, struct jffs2_sb_info *c) { for (; *i < c->inocache_hashsize; (*i)++) { if (c->inocache_list[*i]) return c->inocache_list[*i]; } return NULL; } static inline struct jffs2_inode_cache * next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c) { /* More in this chain? */ if (ic->next) return ic->next; (*i)++; return first_inode_chain(i, c); } #define for_each_inode(i, c, ic) \ for (i = 0, ic = first_inode_chain(&i, (c)); \ ic; \ ic = next_inode(&i, ic, (c))) static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic, int *dir_hardlinks) { struct jffs2_full_dirent *fd; dbg_fsbuild("building directory inode #%u\n", ic->ino); /* For each child, increase nlink */ for(fd = ic->scan_dents; fd; fd = fd->next) { struct jffs2_inode_cache *child_ic; if (!fd->ino) continue; /* we can get high latency here with huge directories */ child_ic = jffs2_get_ino_cache(c, fd->ino); if (!child_ic) { dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n", fd->name, fd->ino, ic->ino); jffs2_mark_node_obsolete(c, fd->raw); /* Clear the ic/raw union so it doesn't cause problems later. */ fd->ic = NULL; continue; } /* From this point, fd->raw is no longer used so we can set fd->ic */ fd->ic = child_ic; child_ic->pino_nlink++; /* If we appear (at this stage) to have hard-linked directories, * set a flag to trigger a scan later */ if (fd->type == DT_DIR) { child_ic->flags |= INO_FLAGS_IS_DIR; if (child_ic->pino_nlink > 1) *dir_hardlinks = 1; } dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino); /* Can't free scan_dents so far. We might need them in pass 2 */ } } /* Scan plan: - Scan physical nodes. Build map of inodes/dirents. Allocate inocaches as we go - Scan directory tree from top down, setting nlink in inocaches - Scan inocaches for inodes with nlink==0 */ static int jffs2_build_filesystem(struct jffs2_sb_info *c) { int ret, i, dir_hardlinks = 0; struct jffs2_inode_cache *ic; struct jffs2_full_dirent *fd; struct jffs2_full_dirent *dead_fds = NULL; dbg_fsbuild("build FS data structures\n"); /* First, scan the medium and build all the inode caches with lists of physical nodes */ c->flags |= JFFS2_SB_FLAG_SCANNING; ret = jffs2_scan_medium(c); c->flags &= ~JFFS2_SB_FLAG_SCANNING; if (ret) goto exit; dbg_fsbuild("scanned flash completely\n"); jffs2_dbg_dump_block_lists_nolock(c); dbg_fsbuild("pass 1 starting\n"); c->flags |= JFFS2_SB_FLAG_BUILDING; /* Now scan the directory tree, increasing nlink according to every dirent found. */ for_each_inode(i, c, ic) { if (ic->scan_dents) { jffs2_build_inode_pass1(c, ic, &dir_hardlinks); cond_resched(); } } dbg_fsbuild("pass 1 complete\n"); /* Next, scan for inodes with nlink == 0 and remove them. If they were directories, then decrement the nlink of their children too, and repeat the scan. As that's going to be a fairly uncommon occurrence, it's not so evil to do it this way. Recursion bad. */ dbg_fsbuild("pass 2 starting\n"); for_each_inode(i, c, ic) { if (ic->pino_nlink) continue; jffs2_build_remove_unlinked_inode(c, ic, &dead_fds); cond_resched(); } dbg_fsbuild("pass 2a starting\n"); while (dead_fds) { fd = dead_fds; dead_fds = fd->next; ic = jffs2_get_ino_cache(c, fd->ino); if (ic) jffs2_build_remove_unlinked_inode(c, ic, &dead_fds); jffs2_free_full_dirent(fd); } dbg_fsbuild("pass 2a complete\n"); if (dir_hardlinks) { /* If we detected directory hardlinks earlier, *hopefully* * they are gone now because some of the links were from * dead directories which still had some old dirents lying * around and not yet garbage-collected, but which have * been discarded above. So clear the pino_nlink field * in each directory, so that the final scan below can * print appropriate warnings. */ for_each_inode(i, c, ic) { if (ic->flags & INO_FLAGS_IS_DIR) ic->pino_nlink = 0; } } dbg_fsbuild("freeing temporary data structures\n"); /* Finally, we can scan again and free the dirent structs */ for_each_inode(i, c, ic) { while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; /* We do use the pino_nlink field to count nlink of * directories during fs build, so set it to the * parent ino# now. Now that there's hopefully only * one. */ if (fd->type == DT_DIR) { if (!fd->ic) { /* We'll have complained about it and marked the coresponding raw node obsolete already. Just skip it. */ continue; } /* We *have* to have set this in jffs2_build_inode_pass1() */ BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR)); /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks * is set. Otherwise, we know this should never trigger anyway, so * we don't do the check. And ic->pino_nlink still contains the nlink * value (which is 1). */ if (dir_hardlinks && fd->ic->pino_nlink) { JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n", fd->name, fd->ino, ic->ino, fd->ic->pino_nlink); /* Should we unlink it from its previous parent? */ } /* For directories, ic->pino_nlink holds that parent inode # */ fd->ic->pino_nlink = ic->ino; } jffs2_free_full_dirent(fd); } ic->scan_dents = NULL; cond_resched(); } ret = jffs2_build_xattr_subsystem(c); if (ret) goto exit; c->flags &= ~JFFS2_SB_FLAG_BUILDING; dbg_fsbuild("FS build complete\n"); /* Rotate the lists by some number to ensure wear levelling */ jffs2_rotate_lists(c); ret = 0; exit: if (ret) { for_each_inode(i, c, ic) { while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; jffs2_free_full_dirent(fd); } } jffs2_clear_xattr_subsystem(c); } return ret; } static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic, struct jffs2_full_dirent **dead_fds) { struct jffs2_raw_node_ref *raw; struct jffs2_full_dirent *fd; dbg_fsbuild("removing ino #%u with nlink == zero.\n", ic->ino); raw = ic->nodes; while (raw != (void *)ic) { struct jffs2_raw_node_ref *next = raw->next_in_ino; dbg_fsbuild("obsoleting node at 0x%08x\n", ref_offset(raw)); jffs2_mark_node_obsolete(c, raw); raw = next; } if (ic->scan_dents) { int whinged = 0; dbg_fsbuild("inode #%u was a directory which may have children...\n", ic->ino); while(ic->scan_dents) { struct jffs2_inode_cache *child_ic; fd = ic->scan_dents; ic->scan_dents = fd->next; if (!fd->ino) { /* It's a deletion dirent. Ignore it */ dbg_fsbuild("child \"%s\" is a deletion dirent, skipping...\n", fd->name); jffs2_free_full_dirent(fd); continue; } if (!whinged) whinged = 1; dbg_fsbuild("removing child \"%s\", ino #%u\n", fd->name, fd->ino); child_ic = jffs2_get_ino_cache(c, fd->ino); if (!child_ic) { dbg_fsbuild("cannot remove child \"%s\", ino #%u, because it doesn't exist\n", fd->name, fd->ino); jffs2_free_full_dirent(fd); continue; } /* Reduce nlink of the child. If it's now zero, stick it on the dead_fds list to be cleaned up later. Else just free the fd */ child_ic->pino_nlink--; if (!child_ic->pino_nlink) { dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n", fd->ino, fd->name); fd->next = *dead_fds; *dead_fds = fd; } else { dbg_fsbuild("inode #%u (\"%s\") has now got nlink %d. Ignoring.\n", fd->ino, fd->name, child_ic->pino_nlink); jffs2_free_full_dirent(fd); } } } /* We don't delete the inocache from the hash list and free it yet. The erase code will do that, when all the nodes are completely gone. */ } static void jffs2_calc_trigger_levels(struct jffs2_sb_info *c) { uint32_t size; /* Deletion should almost _always_ be allowed. We're fairly buggered once we stop allowing people to delete stuff because there's not enough free space... */ c->resv_blocks_deletion = 2; /* Be conservative about how much space we need before we allow writes. On top of that which is required for deletia, require an extra 2% of the medium to be available, for overhead caused by nodes being split across blocks, etc. */ size = c->flash_size / 50; /* 2% of flash size */ size += c->nr_blocks * 100; /* And 100 bytes per eraseblock */ size += c->sector_size - 1; /* ... and round up */ c->resv_blocks_write = c->resv_blocks_deletion + (size / c->sector_size); /* When do we let the GC thread run in the background */ c->resv_blocks_gctrigger = c->resv_blocks_write + 1; /* When do we allow garbage collection to merge nodes to make long-term progress at the expense of short-term space exhaustion? */ c->resv_blocks_gcmerge = c->resv_blocks_deletion + 1; /* When do we allow garbage collection to eat from bad blocks rather than actually making progress? */ c->resv_blocks_gcbad = 0;//c->resv_blocks_deletion + 2; /* What number of 'very dirty' eraseblocks do we allow before we trigger the GC thread even if we don't _need_ the space. When we can't mark nodes obsolete on the medium, the old dirty nodes cause performance problems because we have to inspect and discard them. */ c->vdirty_blocks_gctrigger = c->resv_blocks_gctrigger; if (jffs2_can_mark_obsolete(c)) c->vdirty_blocks_gctrigger *= 10; /* If there's less than this amount of dirty space, don't bother trying to GC to make more space. It'll be a fruitless task */ c->nospc_dirty_size = c->sector_size + (c->flash_size / 100); dbg_fsbuild("trigger levels (size %d KiB, block size %d KiB, %d blocks)\n", c->flash_size / 1024, c->sector_size / 1024, c->nr_blocks); dbg_fsbuild("Blocks required to allow deletion: %d (%d KiB)\n", c->resv_blocks_deletion, c->resv_blocks_deletion*c->sector_size/1024); dbg_fsbuild("Blocks required to allow writes: %d (%d KiB)\n", c->resv_blocks_write, c->resv_blocks_write*c->sector_size/1024); dbg_fsbuild("Blocks required to quiesce GC thread: %d (%d KiB)\n", c->resv_blocks_gctrigger, c->resv_blocks_gctrigger*c->sector_size/1024); dbg_fsbuild("Blocks required to allow GC merges: %d (%d KiB)\n", c->resv_blocks_gcmerge, c->resv_blocks_gcmerge*c->sector_size/1024); dbg_fsbuild("Blocks required to GC bad blocks: %d (%d KiB)\n", c->resv_blocks_gcbad, c->resv_blocks_gcbad*c->sector_size/1024); dbg_fsbuild("Amount of dirty space required to GC: %d bytes\n", c->nospc_dirty_size); dbg_fsbuild("Very dirty blocks before GC triggered: %d\n", c->vdirty_blocks_gctrigger); } int jffs2_do_mount_fs(struct jffs2_sb_info *c) { int ret; int i; int size; c->free_size = c->flash_size; c->nr_blocks = c->flash_size / c->sector_size; size = sizeof(struct jffs2_eraseblock) * c->nr_blocks; #ifndef __ECOS if (jffs2_blocks_use_vmalloc(c)) c->blocks = vzalloc(size); else #endif c->blocks = kzalloc(size, GFP_KERNEL); if (!c->blocks) return -ENOMEM; for (i=0; i<c->nr_blocks; i++) { INIT_LIST_HEAD(&c->blocks[i].list); c->blocks[i].offset = i * c->sector_size; c->blocks[i].free_size = c->sector_size; } INIT_LIST_HEAD(&c->clean_list); INIT_LIST_HEAD(&c->very_dirty_list); INIT_LIST_HEAD(&c->dirty_list); INIT_LIST_HEAD(&c->erasable_list); INIT_LIST_HEAD(&c->erasing_list); INIT_LIST_HEAD(&c->erase_checking_list); INIT_LIST_HEAD(&c->erase_pending_list); INIT_LIST_HEAD(&c->erasable_pending_wbuf_list); INIT_LIST_HEAD(&c->erase_complete_list); INIT_LIST_HEAD(&c->free_list); INIT_LIST_HEAD(&c->bad_list); INIT_LIST_HEAD(&c->bad_used_list); c->highest_ino = 1; c->summary = NULL; ret = jffs2_sum_init(c); if (ret) goto out_free; if (jffs2_build_filesystem(c)) { dbg_fsbuild("build_fs failed\n"); jffs2_free_ino_caches(c); jffs2_free_raw_node_refs(c); ret = -EIO; goto out_sum_exit; } jffs2_calc_trigger_levels(c); return 0; out_sum_exit: jffs2_sum_exit(c); out_free: kvfree(c->blocks); return ret; } |
| 4 1 22 18 9 27 1 1 1 4 4 22 2 21 27 2 23 2 3 3 2 14 1 2 1 9 2 27 4 23 2 9 1 8 2 1 4 2 3 3 2 27 27 27 27 27 27 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Neil Brown <neilb@cse.unsw.edu.au> * J. Bruce Fields <bfields@umich.edu> * Andy Adamson <andros@umich.edu> * Dug Song <dugsong@monkey.org> * * RPCSEC_GSS server authentication. * This implements RPCSEC_GSS as defined in rfc2203 (rpcsec_gss) and rfc2078 * (gssapi) * * The RPCSEC_GSS involves three stages: * 1/ context creation * 2/ data exchange * 3/ context destruction * * Context creation is handled largely by upcalls to user-space. * In particular, GSS_Accept_sec_context is handled by an upcall * Data exchange is handled entirely within the kernel * In particular, GSS_GetMIC, GSS_VerifyMIC, GSS_Seal, GSS_Unseal are in-kernel. * Context destruction is handled in-kernel * GSS_Delete_sec_context is in-kernel * * Context creation is initiated by a RPCSEC_GSS_INIT request arriving. * The context handle and gss_token are used as a key into the rpcsec_init cache. * The content of this cache includes some of the outputs of GSS_Accept_sec_context, * being major_status, minor_status, context_handle, reply_token. * These are sent back to the client. * Sequence window management is handled by the kernel. The window size if currently * a compile time constant. * * When user-space is happy that a context is established, it places an entry * in the rpcsec_context cache. The key for this cache is the context_handle. * The content includes: * uid/gidlist - for determining access rights * mechanism type * mechanism specific information, such as a key * */ #include <linux/slab.h> #include <linux/types.h> #include <linux/module.h> #include <linux/pagemap.h> #include <linux/user_namespace.h> #include <linux/sunrpc/auth_gss.h> #include <linux/sunrpc/gss_err.h> #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/gss_krb5.h> #include <trace/events/rpcgss.h> #include "gss_rpc_upcall.h" /* * Unfortunately there isn't a maximum checksum size exported via the * GSS API. Manufacture one based on GSS mechanisms supported by this * implementation. */ #define GSS_MAX_CKSUMSIZE (GSS_KRB5_TOK_HDR_LEN + GSS_KRB5_MAX_CKSUM_LEN) /* * This value may be increased in the future to accommodate other * usage of the scratch buffer. */ #define GSS_SCRATCH_SIZE GSS_MAX_CKSUMSIZE struct gss_svc_data { /* decoded gss client cred: */ struct rpc_gss_wire_cred clcred; u32 gsd_databody_offset; struct rsc *rsci; /* for temporary results */ __be32 gsd_seq_num; u8 gsd_scratch[GSS_SCRATCH_SIZE]; }; /* The rpcsec_init cache is used for mapping RPCSEC_GSS_{,CONT_}INIT requests * into replies. * * Key is context handle (\x if empty) and gss_token. * Content is major_status minor_status (integers) context_handle, reply_token. * */ static int netobj_equal(struct xdr_netobj *a, struct xdr_netobj *b) { return a->len == b->len && 0 == memcmp(a->data, b->data, a->len); } #define RSI_HASHBITS 6 #define RSI_HASHMAX (1<<RSI_HASHBITS) struct rsi { struct cache_head h; struct xdr_netobj in_handle, in_token; struct xdr_netobj out_handle, out_token; int major_status, minor_status; struct rcu_head rcu_head; }; static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old); static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item); static void rsi_free(struct rsi *rsii) { kfree(rsii->in_handle.data); kfree(rsii->in_token.data); kfree(rsii->out_handle.data); kfree(rsii->out_token.data); } static void rsi_free_rcu(struct rcu_head *head) { struct rsi *rsii = container_of(head, struct rsi, rcu_head); rsi_free(rsii); kfree(rsii); } static void rsi_put(struct kref *ref) { struct rsi *rsii = container_of(ref, struct rsi, h.ref); call_rcu(&rsii->rcu_head, rsi_free_rcu); } static inline int rsi_hash(struct rsi *item) { return hash_mem(item->in_handle.data, item->in_handle.len, RSI_HASHBITS) ^ hash_mem(item->in_token.data, item->in_token.len, RSI_HASHBITS); } static int rsi_match(struct cache_head *a, struct cache_head *b) { struct rsi *item = container_of(a, struct rsi, h); struct rsi *tmp = container_of(b, struct rsi, h); return netobj_equal(&item->in_handle, &tmp->in_handle) && netobj_equal(&item->in_token, &tmp->in_token); } static int dup_to_netobj(struct xdr_netobj *dst, char *src, int len) { dst->len = len; dst->data = (len ? kmemdup(src, len, GFP_KERNEL) : NULL); if (len && !dst->data) return -ENOMEM; return 0; } static inline int dup_netobj(struct xdr_netobj *dst, struct xdr_netobj *src) { return dup_to_netobj(dst, src->data, src->len); } static void rsi_init(struct cache_head *cnew, struct cache_head *citem) { struct rsi *new = container_of(cnew, struct rsi, h); struct rsi *item = container_of(citem, struct rsi, h); new->out_handle.data = NULL; new->out_handle.len = 0; new->out_token.data = NULL; new->out_token.len = 0; new->in_handle.len = item->in_handle.len; item->in_handle.len = 0; new->in_token.len = item->in_token.len; item->in_token.len = 0; new->in_handle.data = item->in_handle.data; item->in_handle.data = NULL; new->in_token.data = item->in_token.data; item->in_token.data = NULL; } static void update_rsi(struct cache_head *cnew, struct cache_head *citem) { struct rsi *new = container_of(cnew, struct rsi, h); struct rsi *item = container_of(citem, struct rsi, h); BUG_ON(new->out_handle.data || new->out_token.data); new->out_handle.len = item->out_handle.len; item->out_handle.len = 0; new->out_token.len = item->out_token.len; item->out_token.len = 0; new->out_handle.data = item->out_handle.data; item->out_handle.data = NULL; new->out_token.data = item->out_token.data; item->out_token.data = NULL; new->major_status = item->major_status; new->minor_status = item->minor_status; } static struct cache_head *rsi_alloc(void) { struct rsi *rsii = kmalloc_obj(*rsii); if (rsii) return &rsii->h; else return NULL; } static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_upcall_warn(cd, h); } static void rsi_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { struct rsi *rsii = container_of(h, struct rsi, h); qword_addhex(bpp, blen, rsii->in_handle.data, rsii->in_handle.len); qword_addhex(bpp, blen, rsii->in_token.data, rsii->in_token.len); (*bpp)[-1] = '\n'; WARN_ONCE(*blen < 0, "RPCSEC/GSS credential too large - please use gssproxy\n"); } static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) { /* context token expiry major minor context token */ char *buf = mesg; char *ep; int len; struct rsi rsii, *rsip = NULL; time64_t expiry; int status = -EINVAL; memset(&rsii, 0, sizeof(rsii)); /* handle */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.in_handle, buf, len)) goto out; /* token */ len = qword_get(&mesg, buf, mlen); status = -EINVAL; if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.in_token, buf, len)) goto out; rsip = rsi_lookup(cd, &rsii); if (!rsip) goto out; rsii.h.flags = 0; /* expiry */ status = get_expiry(&mesg, &expiry); if (status) goto out; status = -EINVAL; /* major/minor */ len = qword_get(&mesg, buf, mlen); if (len <= 0) goto out; rsii.major_status = simple_strtoul(buf, &ep, 10); if (*ep) goto out; len = qword_get(&mesg, buf, mlen); if (len <= 0) goto out; rsii.minor_status = simple_strtoul(buf, &ep, 10); if (*ep) goto out; /* out_handle */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.out_handle, buf, len)) goto out; /* out_token */ len = qword_get(&mesg, buf, mlen); status = -EINVAL; if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsii.out_token, buf, len)) goto out; rsii.h.expiry_time = expiry; rsip = rsi_update(cd, &rsii, rsip); status = 0; out: rsi_free(&rsii); if (rsip) cache_put(&rsip->h, cd); else status = -ENOMEM; return status; } static const struct cache_detail rsi_cache_template = { .owner = THIS_MODULE, .hash_size = RSI_HASHMAX, .name = "auth.rpcsec.init", .cache_put = rsi_put, .cache_upcall = rsi_upcall, .cache_request = rsi_request, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, .update = update_rsi, .alloc = rsi_alloc, }; static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item) { struct cache_head *ch; int hash = rsi_hash(item); ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash); if (ch) return container_of(ch, struct rsi, h); else return NULL; } static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old) { struct cache_head *ch; int hash = rsi_hash(new); ch = sunrpc_cache_update(cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct rsi, h); else return NULL; } /* * The rpcsec_context cache is used to store a context that is * used in data exchange. * The key is a context handle. The content is: * uid, gidlist, mechanism, service-set, mech-specific-data */ #define RSC_HASHBITS 10 #define RSC_HASHMAX (1<<RSC_HASHBITS) #define GSS_SEQ_WIN 128 struct gss_svc_seq_data { /* highest seq number seen so far: */ u32 sd_max; /* for i such that sd_max-GSS_SEQ_WIN < i <= sd_max, the i-th bit of * sd_win is nonzero iff sequence number i has been seen already: */ unsigned long sd_win[GSS_SEQ_WIN/BITS_PER_LONG]; spinlock_t sd_lock; }; struct rsc { struct cache_head h; struct xdr_netobj handle; struct svc_cred cred; struct gss_svc_seq_data seqdata; struct gss_ctx *mechctx; struct rcu_head rcu_head; }; static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old); static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item); static void rsc_free(struct rsc *rsci) { kfree(rsci->handle.data); if (rsci->mechctx) gss_delete_sec_context(&rsci->mechctx); free_svc_cred(&rsci->cred); } static void rsc_free_rcu(struct rcu_head *head) { struct rsc *rsci = container_of(head, struct rsc, rcu_head); kfree(rsci->handle.data); kfree(rsci); } static void rsc_put(struct kref *ref) { struct rsc *rsci = container_of(ref, struct rsc, h.ref); if (rsci->mechctx) gss_delete_sec_context(&rsci->mechctx); free_svc_cred(&rsci->cred); call_rcu(&rsci->rcu_head, rsc_free_rcu); } static inline int rsc_hash(struct rsc *rsci) { return hash_mem(rsci->handle.data, rsci->handle.len, RSC_HASHBITS); } static int rsc_match(struct cache_head *a, struct cache_head *b) { struct rsc *new = container_of(a, struct rsc, h); struct rsc *tmp = container_of(b, struct rsc, h); return netobj_equal(&new->handle, &tmp->handle); } static void rsc_init(struct cache_head *cnew, struct cache_head *ctmp) { struct rsc *new = container_of(cnew, struct rsc, h); struct rsc *tmp = container_of(ctmp, struct rsc, h); new->handle.len = tmp->handle.len; tmp->handle.len = 0; new->handle.data = tmp->handle.data; tmp->handle.data = NULL; new->mechctx = NULL; init_svc_cred(&new->cred); } static void update_rsc(struct cache_head *cnew, struct cache_head *ctmp) { struct rsc *new = container_of(cnew, struct rsc, h); struct rsc *tmp = container_of(ctmp, struct rsc, h); new->mechctx = tmp->mechctx; tmp->mechctx = NULL; memset(&new->seqdata, 0, sizeof(new->seqdata)); spin_lock_init(&new->seqdata.sd_lock); new->cred = tmp->cred; init_svc_cred(&tmp->cred); } static struct cache_head * rsc_alloc(void) { struct rsc *rsci = kmalloc_obj(*rsci); if (rsci) return &rsci->h; else return NULL; } static int rsc_upcall(struct cache_detail *cd, struct cache_head *h) { return -EINVAL; } static int rsc_parse(struct cache_detail *cd, char *mesg, int mlen) { /* contexthandle expiry [ uid gid N <n gids> mechname ...mechdata... ] */ char *buf = mesg; int id; int len, rv; struct rsc rsci, *rscp = NULL; time64_t expiry; int status = -EINVAL; struct gss_api_mech *gm = NULL; memset(&rsci, 0, sizeof(rsci)); /* context handle */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = -ENOMEM; if (dup_to_netobj(&rsci.handle, buf, len)) goto out; rsci.h.flags = 0; /* expiry */ status = get_expiry(&mesg, &expiry); if (status) goto out; status = -EINVAL; rscp = rsc_lookup(cd, &rsci); if (!rscp) goto out; /* uid, or NEGATIVE */ rv = get_int(&mesg, &id); if (rv == -EINVAL) goto out; if (rv == -ENOENT) set_bit(CACHE_NEGATIVE, &rsci.h.flags); else { int N, i; /* * NOTE: we skip uid_valid()/gid_valid() checks here: * instead, * -1 id's are later mapped to the * (export-specific) anonymous id by nfsd_setuser. * * (But supplementary gid's get no such special * treatment so are checked for validity here.) */ /* uid */ rsci.cred.cr_uid = make_kuid(current_user_ns(), id); /* gid */ if (get_int(&mesg, &id)) goto out; rsci.cred.cr_gid = make_kgid(current_user_ns(), id); /* number of additional gid's */ if (get_int(&mesg, &N)) goto out; if (N < 0 || N > NGROUPS_MAX) goto out; status = -ENOMEM; rsci.cred.cr_group_info = groups_alloc(N); if (rsci.cred.cr_group_info == NULL) goto out; /* gid's */ status = -EINVAL; for (i=0; i<N; i++) { kgid_t kgid; if (get_int(&mesg, &id)) goto out; kgid = make_kgid(current_user_ns(), id); if (!gid_valid(kgid)) goto out; rsci.cred.cr_group_info->gid[i] = kgid; } groups_sort(rsci.cred.cr_group_info); /* mech name */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; gm = rsci.cred.cr_gss_mech = gss_mech_get_by_name(buf); status = -EOPNOTSUPP; if (!gm) goto out; status = -EINVAL; /* mech-specific data: */ len = qword_get(&mesg, buf, mlen); if (len < 0) goto out; status = gss_import_sec_context(buf, len, gm, &rsci.mechctx, NULL, GFP_KERNEL); if (status) goto out; /* get client name */ len = qword_get(&mesg, buf, mlen); if (len > 0) { rsci.cred.cr_principal = kstrdup(buf, GFP_KERNEL); if (!rsci.cred.cr_principal) { status = -ENOMEM; goto out; } } } rsci.h.expiry_time = expiry; rscp = rsc_update(cd, &rsci, rscp); status = 0; out: rsc_free(&rsci); if (rscp) cache_put(&rscp->h, cd); else status = -ENOMEM; return status; } static const struct cache_detail rsc_cache_template = { .owner = THIS_MODULE, .hash_size = RSC_HASHMAX, .name = "auth.rpcsec.context", .cache_put = rsc_put, .cache_upcall = rsc_upcall, .cache_parse = rsc_parse, .match = rsc_match, .init = rsc_init, .update = update_rsc, .alloc = rsc_alloc, }; static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item) { struct cache_head *ch; int hash = rsc_hash(item); ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash); if (ch) return container_of(ch, struct rsc, h); else return NULL; } static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old) { struct cache_head *ch; int hash = rsc_hash(new); ch = sunrpc_cache_update(cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct rsc, h); else return NULL; } static struct rsc * gss_svc_searchbyctx(struct cache_detail *cd, struct xdr_netobj *handle) { struct rsc rsci; struct rsc *found; memset(&rsci, 0, sizeof(rsci)); if (dup_to_netobj(&rsci.handle, handle->data, handle->len)) return NULL; found = rsc_lookup(cd, &rsci); rsc_free(&rsci); if (!found) return NULL; if (cache_check(cd, &found->h, NULL)) return NULL; return found; } /** * gss_check_seq_num - GSS sequence number window check * @rqstp: RPC Call to use when reporting errors * @rsci: cached GSS context state (updated on return) * @seq_num: sequence number to check * * Implements sequence number algorithm as specified in * RFC 2203, Section 5.3.3.1. "Context Management". * * Return values: * %true: @rqstp's GSS sequence number is inside the window * %false: @rqstp's GSS sequence number is outside the window */ static bool gss_check_seq_num(const struct svc_rqst *rqstp, struct rsc *rsci, u32 seq_num) { struct gss_svc_seq_data *sd = &rsci->seqdata; bool result = false; spin_lock(&sd->sd_lock); if (seq_num > sd->sd_max) { if (seq_num >= sd->sd_max + GSS_SEQ_WIN) { memset(sd->sd_win, 0, sizeof(sd->sd_win)); sd->sd_max = seq_num; } else while (sd->sd_max < seq_num) { sd->sd_max++; __clear_bit(sd->sd_max % GSS_SEQ_WIN, sd->sd_win); } __set_bit(seq_num % GSS_SEQ_WIN, sd->sd_win); goto ok; } else if (seq_num + GSS_SEQ_WIN <= sd->sd_max) { goto toolow; } if (__test_and_set_bit(seq_num % GSS_SEQ_WIN, sd->sd_win)) goto alreadyseen; ok: result = true; out: spin_unlock(&sd->sd_lock); return result; toolow: trace_rpcgss_svc_seqno_low(rqstp, seq_num, sd->sd_max - GSS_SEQ_WIN, sd->sd_max); goto out; alreadyseen: trace_rpcgss_svc_seqno_seen(rqstp, seq_num); goto out; } /* * Decode and verify a Call's verifier field. For RPC_AUTH_GSS Calls, * the body of this field contains a variable length checksum. * * GSS-specific auth_stat values are mandated by RFC 2203 Section * 5.3.3.3. */ static int svcauth_gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, __be32 *rpcstart, struct rpc_gss_wire_cred *gc) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct gss_ctx *ctx_id = rsci->mechctx; u32 flavor, maj_stat; struct xdr_buf rpchdr; struct xdr_netobj checksum; struct kvec iov; /* * Compute the checksum of the incoming Call from the * XID field to credential field: */ iov.iov_base = rpcstart; iov.iov_len = (u8 *)xdr->p - (u8 *)rpcstart; xdr_buf_from_iov(&iov, &rpchdr); /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, (void **)&checksum.data, &checksum.len) < 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (flavor != RPC_AUTH_GSS || checksum.len < XDR_UNIT) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (rqstp->rq_deferred) return SVC_OK; maj_stat = gss_verify_mic(ctx_id, &rpchdr, &checksum); if (maj_stat != GSS_S_COMPLETE) { trace_rpcgss_svc_mic(rqstp, maj_stat); rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; return SVC_DENIED; } if (gc->gc_seq > MAXSEQ) { trace_rpcgss_svc_seqno_large(rqstp, gc->gc_seq); rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; return SVC_DENIED; } if (!gss_check_seq_num(rqstp, rsci, gc->gc_seq)) return SVC_DROP; return SVC_OK; } /* * Construct and encode a Reply's verifier field. The verifier's body * field contains a variable-length checksum of the GSS sequence * number. */ static bool svcauth_gss_encode_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq) { struct gss_svc_data *gsd = rqstp->rq_auth_data; u32 maj_stat; struct xdr_buf verf_data; struct xdr_netobj checksum; struct kvec iov; gsd->gsd_seq_num = cpu_to_be32(seq); iov.iov_base = &gsd->gsd_seq_num; iov.iov_len = XDR_UNIT; xdr_buf_from_iov(&iov, &verf_data); checksum.data = gsd->gsd_scratch; maj_stat = gss_get_mic(ctx_id, &verf_data, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; return xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_GSS, checksum.data, checksum.len) > 0; bad_mic: trace_rpcgss_svc_get_mic(rqstp, maj_stat); return false; } struct gss_domain { struct auth_domain h; u32 pseudoflavor; }; static struct auth_domain * find_gss_auth_domain(struct gss_ctx *ctx, u32 svc) { char *name; name = gss_service_to_auth_domain_name(ctx->mech_type, svc); if (!name) return NULL; return auth_domain_find(name); } static struct auth_ops svcauthops_gss; u32 svcauth_gss_flavor(struct auth_domain *dom) { struct gss_domain *gd = container_of(dom, struct gss_domain, h); return gd->pseudoflavor; } EXPORT_SYMBOL_GPL(svcauth_gss_flavor); struct auth_domain * svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name) { struct gss_domain *new; struct auth_domain *test; int stat = -ENOMEM; new = kmalloc_obj(*new); if (!new) goto out; kref_init(&new->h.ref); new->h.name = kstrdup(name, GFP_KERNEL); if (!new->h.name) goto out_free_dom; new->h.flavour = &svcauthops_gss; new->pseudoflavor = pseudoflavor; test = auth_domain_lookup(name, &new->h); if (test != &new->h) { pr_warn("svc: duplicate registration of gss pseudo flavour %s.\n", name); stat = -EADDRINUSE; auth_domain_put(test); goto out_free_name; } return test; out_free_name: kfree(new->h.name); out_free_dom: kfree(new); out: return ERR_PTR(stat); } EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor); /* * RFC 2203, Section 5.3.2.2 * * struct rpc_gss_integ_data { * opaque databody_integ<>; * opaque checksum<>; * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; */ static noinline_for_stack int svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) { struct gss_svc_data *gsd = rqstp->rq_auth_data; struct xdr_stream *xdr = &rqstp->rq_arg_stream; u32 len, offset, seq_num, maj_stat; struct xdr_buf *buf = xdr->buf; struct xdr_buf databody_integ; struct xdr_netobj checksum; /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) return 0; if (xdr_stream_decode_u32(xdr, &len) < 0) goto unwrap_failed; if (len & 3) goto unwrap_failed; offset = xdr_stream_pos(xdr); if (xdr_buf_subsegment(buf, &databody_integ, offset, len)) goto unwrap_failed; /* * The xdr_stream now points to the @seq_num field. The next * XDR data item is the @arg field, which contains the clear * text RPC program payload. The checksum, which follows the * @arg field, is located and decoded without updating the * xdr_stream. */ offset += len; if (xdr_decode_word(buf, offset, &checksum.len)) goto unwrap_failed; if (checksum.len > sizeof(gsd->gsd_scratch)) goto unwrap_failed; checksum.data = gsd->gsd_scratch; if (read_bytes_from_xdr_buf(buf, offset + XDR_UNIT, checksum.data, checksum.len)) goto unwrap_failed; maj_stat = gss_verify_mic(ctx, &databody_integ, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; /* The received seqno is protected by the checksum. */ if (xdr_stream_decode_u32(xdr, &seq_num) < 0) goto unwrap_failed; if (seq_num != seq) goto bad_seqno; xdr_truncate_decode(xdr, XDR_UNIT + checksum.len); return 0; unwrap_failed: trace_rpcgss_svc_unwrap_failed(rqstp); return -EINVAL; bad_seqno: trace_rpcgss_svc_seqno_bad(rqstp, seq, seq_num); return -EINVAL; bad_mic: trace_rpcgss_svc_mic(rqstp, maj_stat); return -EINVAL; } /* * RFC 2203, Section 5.3.2.3 * * struct rpc_gss_priv_data { * opaque databody_priv<> * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; */ static noinline_for_stack int svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; u32 len, maj_stat, seq_num, offset; struct xdr_buf *buf = xdr->buf; unsigned int saved_len; if (xdr_stream_decode_u32(xdr, &len) < 0) goto unwrap_failed; if (rqstp->rq_deferred) { /* Already decrypted last time through! The sequence number * check at out_seq is unnecessary but harmless: */ goto out_seq; } if (len > xdr_stream_remaining(xdr)) goto unwrap_failed; if (len <= GSS_KRB5_TOK_HDR_LEN) goto unwrap_failed; offset = xdr_stream_pos(xdr); saved_len = buf->len; maj_stat = gss_unwrap(ctx, offset, offset + len, buf); if (maj_stat != GSS_S_COMPLETE) goto bad_unwrap; xdr->nwords -= XDR_QUADLEN(saved_len - buf->len); out_seq: /* gss_unwrap() decrypted the sequence number. */ if (xdr_stream_decode_u32(xdr, &seq_num) < 0) goto unwrap_failed; if (seq_num != seq) goto bad_seqno; return 0; unwrap_failed: trace_rpcgss_svc_unwrap_failed(rqstp); return -EINVAL; bad_seqno: trace_rpcgss_svc_seqno_bad(rqstp, seq, seq_num); return -EINVAL; bad_unwrap: trace_rpcgss_svc_unwrap(rqstp, maj_stat); return -EINVAL; } static enum svc_auth_status svcauth_gss_set_client(struct svc_rqst *rqstp) { struct gss_svc_data *svcdata = rqstp->rq_auth_data; struct rsc *rsci = svcdata->rsci; struct rpc_gss_wire_cred *gc = &svcdata->clcred; int stat; rqstp->rq_auth_stat = rpc_autherr_badcred; /* * A gss export can be specified either by: * export *(sec=krb5,rw) * or by * export gss/krb5(rw) * The latter is deprecated; but for backwards compatibility reasons * the nfsd code will still fall back on trying it if the former * doesn't work; so we try to make both available to nfsd, below. */ rqstp->rq_gssclient = find_gss_auth_domain(rsci->mechctx, gc->gc_svc); if (rqstp->rq_gssclient == NULL) return SVC_DENIED; stat = svcauth_unix_set_client(rqstp); if (stat == SVC_DROP || stat == SVC_CLOSE) return stat; rqstp->rq_auth_stat = rpc_auth_ok; return SVC_OK; } static bool svcauth_gss_proc_init_verf(struct cache_detail *cd, struct svc_rqst *rqstp, struct xdr_netobj *out_handle, int *major_status, u32 seq_num) { struct xdr_stream *xdr = &rqstp->rq_res_stream; struct rsc *rsci; bool rc; if (*major_status != GSS_S_COMPLETE) goto null_verifier; rsci = gss_svc_searchbyctx(cd, out_handle); if (rsci == NULL) { *major_status = GSS_S_NO_CONTEXT; goto null_verifier; } rc = svcauth_gss_encode_verf(rqstp, rsci->mechctx, seq_num); cache_put(&rsci->h, cd); return rc; null_verifier: return xdr_stream_encode_opaque_auth(xdr, RPC_AUTH_NULL, NULL, 0) > 0; } static void gss_free_in_token_pages(struct gssp_in_token *in_token) { int i; i = 0; while (in_token->pages[i]) put_page(in_token->pages[i++]); kfree(in_token->pages); in_token->pages = NULL; } static int gss_read_proxy_verf(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc, struct xdr_netobj *in_handle, struct gssp_in_token *in_token) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; unsigned int length, pgto_offs, pgfrom_offs; int pages, i, pgto, pgfrom; size_t to_offs, from_offs; u32 inlen; if (dup_netobj(in_handle, &gc->gc_ctx)) return SVC_CLOSE; /* * RFC 2203 Section 5.2.2 * * struct rpc_gss_init_arg { * opaque gss_token<>; * }; */ if (xdr_stream_decode_u32(xdr, &inlen) < 0) goto out_denied_free; if (inlen > xdr_stream_remaining(xdr)) goto out_denied_free; pages = DIV_ROUND_UP(inlen, PAGE_SIZE); in_token->pages = kzalloc_objs(struct page *, pages + 1); if (!in_token->pages) goto out_denied_free; in_token->page_base = 0; in_token->page_len = inlen; for (i = 0; i < pages; i++) { in_token->pages[i] = alloc_page(GFP_KERNEL); if (!in_token->pages[i]) { gss_free_in_token_pages(in_token); goto out_denied_free; } } length = min_t(unsigned int, inlen, (char *)xdr->end - (char *)xdr->p); if (length) memcpy(page_address(in_token->pages[0]), xdr->p, length); inlen -= length; to_offs = length; from_offs = rqstp->rq_arg.page_base; while (inlen) { pgto = to_offs >> PAGE_SHIFT; pgfrom = from_offs >> PAGE_SHIFT; pgto_offs = to_offs & ~PAGE_MASK; pgfrom_offs = from_offs & ~PAGE_MASK; length = min_t(unsigned int, inlen, min_t(unsigned int, PAGE_SIZE - pgto_offs, PAGE_SIZE - pgfrom_offs)); memcpy(page_address(in_token->pages[pgto]) + pgto_offs, page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs, length); to_offs += length; from_offs += length; inlen -= length; } return 0; out_denied_free: kfree(in_handle->data); return SVC_DENIED; } /* * RFC 2203, Section 5.2.3.1. * * struct rpc_gss_init_res { * opaque handle<>; * unsigned int gss_major; * unsigned int gss_minor; * unsigned int seq_window; * opaque gss_token<>; * }; */ static bool svcxdr_encode_gss_init_res(struct xdr_stream *xdr, struct xdr_netobj *handle, struct xdr_netobj *gss_token, unsigned int major_status, unsigned int minor_status, u32 seq_num) { if (xdr_stream_encode_opaque(xdr, handle->data, handle->len) < 0) return false; if (xdr_stream_encode_u32(xdr, major_status) < 0) return false; if (xdr_stream_encode_u32(xdr, minor_status) < 0) return false; if (xdr_stream_encode_u32(xdr, seq_num) < 0) return false; if (xdr_stream_encode_opaque(xdr, gss_token->data, gss_token->len) < 0) return false; return true; } /* * Having read the cred already and found we're in the context * initiation case, read the verifier and initiate (or check the results * of) upcalls to userspace for help with context initiation. If * the upcall results are available, write the verifier and result. * Otherwise, drop the request pending an answer to the upcall. */ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct rsi *rsip, rsikey; __be32 *p; u32 len; int ret; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); memset(&rsikey, 0, sizeof(rsikey)); if (dup_netobj(&rsikey.in_handle, &gc->gc_ctx)) return SVC_CLOSE; /* * RFC 2203 Section 5.2.2 * * struct rpc_gss_init_arg { * opaque gss_token<>; * }; */ if (xdr_stream_decode_u32(xdr, &len) < 0) { kfree(rsikey.in_handle.data); return SVC_DENIED; } p = xdr_inline_decode(xdr, len); if (!p) { kfree(rsikey.in_handle.data); return SVC_DENIED; } rsikey.in_token.data = kmalloc(len, GFP_KERNEL); if (ZERO_OR_NULL_PTR(rsikey.in_token.data)) { kfree(rsikey.in_handle.data); return SVC_CLOSE; } memcpy(rsikey.in_token.data, p, len); rsikey.in_token.len = len; /* Perform upcall, or find upcall result: */ rsip = rsi_lookup(sn->rsi_cache, &rsikey); rsi_free(&rsikey); if (!rsip) return SVC_CLOSE; if (cache_check(sn->rsi_cache, &rsip->h, &rqstp->rq_chandle) < 0) /* No upcall result: */ return SVC_CLOSE; ret = SVC_CLOSE; if (!svcauth_gss_proc_init_verf(sn->rsc_cache, rqstp, &rsip->out_handle, &rsip->major_status, GSS_SEQ_WIN)) goto out; if (!svcxdr_set_accept_stat(rqstp)) goto out; if (!svcxdr_encode_gss_init_res(&rqstp->rq_res_stream, &rsip->out_handle, &rsip->out_token, rsip->major_status, rsip->minor_status, GSS_SEQ_WIN)) goto out; ret = SVC_COMPLETE; out: cache_put(&rsip->h, sn->rsi_cache); return ret; } static int gss_proxy_save_rsc(struct cache_detail *cd, struct gssp_upcall_data *ud, uint64_t *handle) { struct rsc rsci, *rscp = NULL; static atomic64_t ctxhctr; long long ctxh; struct gss_api_mech *gm = NULL; time64_t expiry; int status; memset(&rsci, 0, sizeof(rsci)); /* context handle */ status = -ENOMEM; /* the handle needs to be just a unique id, * use a static counter */ ctxh = atomic64_inc_return(&ctxhctr); /* make a copy for the caller */ *handle = ctxh; /* make a copy for the rsc cache */ if (dup_to_netobj(&rsci.handle, (char *)handle, sizeof(uint64_t))) goto out; rscp = rsc_lookup(cd, &rsci); if (!rscp) goto out; /* creds */ if (!ud->found_creds) { /* userspace seem buggy, we should always get at least a * mapping to nobody */ goto out; } else { struct timespec64 boot; /* steal creds */ rsci.cred = ud->creds; memset(&ud->creds, 0, sizeof(struct svc_cred)); status = -EOPNOTSUPP; /* get mech handle from OID */ gm = gss_mech_get_by_OID(&ud->mech_oid); if (!gm) goto out; rsci.cred.cr_gss_mech = gm; status = -EINVAL; /* mech-specific data: */ status = gss_import_sec_context(ud->out_handle.data, ud->out_handle.len, gm, &rsci.mechctx, &expiry, GFP_KERNEL); if (status) goto out; getboottime64(&boot); expiry -= boot.tv_sec; } rsci.h.expiry_time = expiry; rscp = rsc_update(cd, &rsci, rscp); status = 0; out: rsc_free(&rsci); if (rscp) cache_put(&rscp->h, cd); else status = -ENOMEM; return status; } static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc) { struct xdr_netobj cli_handle; struct gssp_upcall_data ud; uint64_t handle; int status; int ret; struct net *net = SVC_NET(rqstp); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); memset(&ud, 0, sizeof(ud)); ret = gss_read_proxy_verf(rqstp, gc, &ud.in_handle, &ud.in_token); if (ret) return ret; ret = SVC_CLOSE; /* Perform synchronous upcall to gss-proxy */ status = gssp_accept_sec_context_upcall(net, &ud); if (status) goto out; trace_rpcgss_svc_accept_upcall(rqstp, ud.major_status, ud.minor_status); switch (ud.major_status) { case GSS_S_CONTINUE_NEEDED: cli_handle = ud.out_handle; break; case GSS_S_COMPLETE: status = gss_proxy_save_rsc(sn->rsc_cache, &ud, &handle); if (status) goto out; cli_handle.data = (u8 *)&handle; cli_handle.len = sizeof(handle); break; default: goto out; } if (!svcauth_gss_proc_init_verf(sn->rsc_cache, rqstp, &cli_handle, &ud.major_status, GSS_SEQ_WIN)) goto out; if (!svcxdr_set_accept_stat(rqstp)) goto out; if (!svcxdr_encode_gss_init_res(&rqstp->rq_res_stream, &cli_handle, &ud.out_token, ud.major_status, ud.minor_status, GSS_SEQ_WIN)) goto out; ret = SVC_COMPLETE; out: gss_free_in_token_pages(&ud.in_token); gssp_free_upcall_data(&ud); return ret; } /* * Try to set the sn->use_gss_proxy variable to a new value. We only allow * it to be changed if it's currently undefined (-1). If it's any other value * then return -EBUSY unless the type wouldn't have changed anyway. */ static int set_gss_proxy(struct net *net, int type) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int ret; WARN_ON_ONCE(type != 0 && type != 1); ret = cmpxchg(&sn->use_gss_proxy, -1, type); if (ret != -1 && ret != type) return -EBUSY; return 0; } static bool use_gss_proxy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); /* If use_gss_proxy is still undefined, then try to disable it */ if (sn->use_gss_proxy == -1) set_gss_proxy(net, 0); return sn->use_gss_proxy; } static noinline_for_stack int svcauth_gss_proc_init(struct svc_rqst *rqstp, struct rpc_gss_wire_cred *gc) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; u32 flavor, len; void *body; /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, &body, &len) < 0) return SVC_GARBAGE; if (flavor != RPC_AUTH_NULL || len != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (gc->gc_proc == RPC_GSS_PROC_INIT && gc->gc_ctx.len != 0) { rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } if (!use_gss_proxy(SVC_NET(rqstp))) return svcauth_gss_legacy_init(rqstp, gc); return svcauth_gss_proxy_init(rqstp, gc); } #ifdef CONFIG_PROC_FS static ssize_t write_gssp(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct net *net = pde_data(file_inode(file)); char tbuf[20]; unsigned long i; int res; if (*ppos || count > sizeof(tbuf)-1) return -EINVAL; if (copy_from_user(tbuf, buf, count)) return -EFAULT; tbuf[count] = 0; res = kstrtoul(tbuf, 0, &i); if (res) return res; if (i != 1) return -EINVAL; res = set_gssp_clnt(net); if (res) return res; res = set_gss_proxy(net, 1); if (res) return res; return count; } static ssize_t read_gssp(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct net *net = pde_data(file_inode(file)); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); unsigned long p = *ppos; char tbuf[10]; size_t len; snprintf(tbuf, sizeof(tbuf), "%d\n", sn->use_gss_proxy); len = strlen(tbuf); if (p >= len) return 0; len -= p; if (len > count) len = count; if (copy_to_user(buf, (void *)(tbuf+p), len)) return -EFAULT; *ppos += len; return len; } static const struct proc_ops use_gss_proxy_proc_ops = { .proc_open = nonseekable_open, .proc_write = write_gssp, .proc_read = read_gssp, }; static int create_use_gss_proxy_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct proc_dir_entry **p = &sn->use_gssp_proc; sn->use_gss_proxy = -1; *p = proc_create_data("use-gss-proxy", S_IFREG | 0600, sn->proc_net_rpc, &use_gss_proxy_proc_ops, net); if (!*p) return -ENOMEM; return 0; } static void destroy_use_gss_proxy_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); if (sn->use_gssp_proc) { remove_proc_entry("use-gss-proxy", sn->proc_net_rpc); clear_gssp_clnt(sn); } } static ssize_t read_gss_krb5_enctypes(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct rpcsec_gss_oid oid = { .len = 9, .data = "\x2a\x86\x48\x86\xf7\x12\x01\x02\x02", }; struct gss_api_mech *mech; ssize_t ret; mech = gss_mech_get_by_OID(&oid); if (!mech) return 0; if (!mech->gm_upcall_enctypes) { gss_mech_put(mech); return 0; } ret = simple_read_from_buffer(buf, count, ppos, mech->gm_upcall_enctypes, strlen(mech->gm_upcall_enctypes)); gss_mech_put(mech); return ret; } static const struct proc_ops gss_krb5_enctypes_proc_ops = { .proc_open = nonseekable_open, .proc_read = read_gss_krb5_enctypes, }; static int create_krb5_enctypes_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); sn->gss_krb5_enctypes = proc_create_data("gss_krb5_enctypes", S_IFREG | 0444, sn->proc_net_rpc, &gss_krb5_enctypes_proc_ops, net); return sn->gss_krb5_enctypes ? 0 : -ENOMEM; } static void destroy_krb5_enctypes_proc_entry(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); if (sn->gss_krb5_enctypes) remove_proc_entry("gss_krb5_enctypes", sn->proc_net_rpc); } #else /* CONFIG_PROC_FS */ static int create_use_gss_proxy_proc_entry(struct net *net) { return 0; } static void destroy_use_gss_proxy_proc_entry(struct net *net) {} static int create_krb5_enctypes_proc_entry(struct net *net) { return 0; } static void destroy_krb5_enctypes_proc_entry(struct net *net) {} #endif /* CONFIG_PROC_FS */ /* * The Call's credential body should contain a struct rpc_gss_cred_t. * * RFC 2203 Section 5 * * struct rpc_gss_cred_t { * union switch (unsigned int version) { * case RPCSEC_GSS_VERS_1: * struct { * rpc_gss_proc_t gss_proc; * unsigned int seq_num; * rpc_gss_service_t service; * opaque handle<>; * } rpc_gss_cred_vers_1_t; * } * }; */ static bool svcauth_gss_decode_credbody(struct xdr_stream *xdr, struct rpc_gss_wire_cred *gc, __be32 **rpcstart) { ssize_t handle_len; u32 body_len; __be32 *p; /* Early-return paths leave deterministic state, not stale residue. */ memset(gc, 0, sizeof(*gc)); p = xdr_inline_decode(xdr, XDR_UNIT); if (!p) return false; /* * start of rpc packet is 7 u32's back from here: * xid direction rpcversion prog vers proc flavour */ *rpcstart = p - 7; body_len = be32_to_cpup(p); if (body_len > RPC_MAX_AUTH_SIZE) return false; /* struct rpc_gss_cred_t */ if (xdr_stream_decode_u32(xdr, &gc->gc_v) < 0) return false; if (xdr_stream_decode_u32(xdr, &gc->gc_proc) < 0) return false; if (xdr_stream_decode_u32(xdr, &gc->gc_seq) < 0) return false; if (xdr_stream_decode_u32(xdr, &gc->gc_svc) < 0) return false; handle_len = xdr_stream_decode_opaque_inline(xdr, (void **)&gc->gc_ctx.data, body_len); if (handle_len < 0) return false; if (body_len != XDR_UNIT * 5 + xdr_align_size(handle_len)) return false; gc->gc_ctx.len = handle_len; return true; } /** * svcauth_gss_accept - Decode and validate incoming RPC_AUTH_GSS credential * @rqstp: RPC transaction * * Return values: * %SVC_OK: Success * %SVC_COMPLETE: GSS context lifetime event * %SVC_DENIED: Credential or verifier is not valid * %SVC_GARBAGE: Failed to decode credential or verifier * %SVC_CLOSE: Temporary failure * * The rqstp->rq_auth_stat field is also set (see RFCs 2203 and 5531). */ static enum svc_auth_status svcauth_gss_accept(struct svc_rqst *rqstp) { struct gss_svc_data *svcdata = rqstp->rq_auth_data; __be32 *rpcstart; struct rpc_gss_wire_cred *gc; struct rsc *rsci = NULL; int ret; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); rqstp->rq_auth_stat = rpc_autherr_failed; if (!svcdata) svcdata = kmalloc_obj(*svcdata); if (!svcdata) goto auth_err; rqstp->rq_auth_data = svcdata; svcdata->gsd_databody_offset = 0; svcdata->rsci = NULL; gc = &svcdata->clcred; rqstp->rq_auth_stat = rpc_autherr_badcred; if (!svcauth_gss_decode_credbody(&rqstp->rq_arg_stream, gc, &rpcstart)) goto auth_err; if (gc->gc_v != RPC_GSS_VERSION) goto auth_err; switch (gc->gc_proc) { case RPC_GSS_PROC_INIT: case RPC_GSS_PROC_CONTINUE_INIT: if (rqstp->rq_proc != 0) goto auth_err; return svcauth_gss_proc_init(rqstp, gc); case RPC_GSS_PROC_DESTROY: if (rqstp->rq_proc != 0) goto auth_err; fallthrough; case RPC_GSS_PROC_DATA: rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; rsci = gss_svc_searchbyctx(sn->rsc_cache, &gc->gc_ctx); if (!rsci) goto auth_err; switch (svcauth_gss_verify_header(rqstp, rsci, rpcstart, gc)) { case SVC_OK: break; case SVC_DENIED: goto auth_err; case SVC_DROP: goto drop; } break; default: if (rqstp->rq_proc != 0) goto auth_err; rqstp->rq_auth_stat = rpc_autherr_rejectedcred; goto auth_err; } /* now act upon the command: */ switch (gc->gc_proc) { case RPC_GSS_PROC_DESTROY: if (!svcauth_gss_encode_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; if (!svcxdr_set_accept_stat(rqstp)) goto auth_err; /* Delete the entry from the cache_list and call cache_put */ sunrpc_cache_unhash(sn->rsc_cache, &rsci->h); goto complete; case RPC_GSS_PROC_DATA: rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; if (!svcauth_gss_encode_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; if (!svcxdr_set_accept_stat(rqstp)) goto auth_err; svcdata->gsd_databody_offset = xdr_stream_pos(&rqstp->rq_res_stream); rqstp->rq_cred = rsci->cred; get_group_info(rsci->cred.cr_group_info); rqstp->rq_auth_stat = rpc_autherr_badcred; switch (gc->gc_svc) { case RPC_GSS_SVC_NONE: break; case RPC_GSS_SVC_INTEGRITY: /* placeholders for body length and seq. number: */ xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2); if (svcauth_gss_unwrap_integ(rqstp, gc->gc_seq, rsci->mechctx)) goto garbage_args; svcxdr_set_auth_slack(rqstp, RPC_MAX_AUTH_SIZE); break; case RPC_GSS_SVC_PRIVACY: /* placeholders for body length and seq. number: */ xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2); if (svcauth_gss_unwrap_priv(rqstp, gc->gc_seq, rsci->mechctx)) goto garbage_args; svcxdr_set_auth_slack(rqstp, RPC_MAX_AUTH_SIZE * 2); break; default: goto auth_err; } svcdata->rsci = rsci; cache_get(&rsci->h); rqstp->rq_cred.cr_flavor = gss_svc_to_pseudoflavor( rsci->mechctx->mech_type, GSS_C_QOP_DEFAULT, gc->gc_svc); ret = SVC_OK; trace_rpcgss_svc_authenticate(rqstp, gc); goto out; } garbage_args: ret = SVC_GARBAGE; goto out; auth_err: xdr_truncate_encode(&rqstp->rq_res_stream, XDR_UNIT * 2); ret = SVC_DENIED; goto out; complete: ret = SVC_COMPLETE; goto out; drop: ret = SVC_CLOSE; out: if (rsci) cache_put(&rsci->h, sn->rsc_cache); return ret; } static u32 svcauth_gss_prepare_to_wrap(struct svc_rqst *rqstp, struct gss_svc_data *gsd) { u32 offset; /* Release can be called twice, but we only wrap once. */ offset = gsd->gsd_databody_offset; gsd->gsd_databody_offset = 0; /* AUTH_ERROR replies are not wrapped. */ if (rqstp->rq_auth_stat != rpc_auth_ok) return 0; /* Also don't wrap if the accept_stat is nonzero: */ if (*rqstp->rq_accept_statp != rpc_success) return 0; return offset; } /* * RFC 2203, Section 5.3.2.2 * * struct rpc_gss_integ_data { * opaque databody_integ<>; * opaque checksum<>; * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; * * The RPC Reply message has already been XDR-encoded. rq_res_stream * is now positioned so that the checksum can be written just past * the RPC Reply message. */ static int svcauth_gss_wrap_integ(struct svc_rqst *rqstp) { struct gss_svc_data *gsd = rqstp->rq_auth_data; struct xdr_stream *xdr = &rqstp->rq_res_stream; struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *buf = xdr->buf; struct xdr_buf databody_integ; struct xdr_netobj checksum; u32 offset, maj_stat; offset = svcauth_gss_prepare_to_wrap(rqstp, gsd); if (!offset) goto out; if (xdr_buf_subsegment(buf, &databody_integ, offset + XDR_UNIT, buf->len - offset - XDR_UNIT)) goto wrap_failed; /* Buffer space for these has already been reserved in * svcauth_gss_accept(). */ if (xdr_encode_word(buf, offset, databody_integ.len)) goto wrap_failed; if (xdr_encode_word(buf, offset + XDR_UNIT, gc->gc_seq)) goto wrap_failed; checksum.data = gsd->gsd_scratch; maj_stat = gss_get_mic(gsd->rsci->mechctx, &databody_integ, &checksum); if (maj_stat != GSS_S_COMPLETE) goto bad_mic; if (xdr_stream_encode_opaque(xdr, checksum.data, checksum.len) < 0) goto wrap_failed; xdr_commit_encode(xdr); out: return 0; bad_mic: trace_rpcgss_svc_get_mic(rqstp, maj_stat); return -EINVAL; wrap_failed: trace_rpcgss_svc_wrap_failed(rqstp); return -EINVAL; } /* * RFC 2203, Section 5.3.2.3 * * struct rpc_gss_priv_data { * opaque databody_priv<> * }; * * struct rpc_gss_data_t { * unsigned int seq_num; * proc_req_arg_t arg; * }; * * gss_wrap() expands the size of the RPC message payload in the * response buffer. The main purpose of svcauth_gss_wrap_priv() * is to ensure there is adequate space in the response buffer to * avoid overflow during the wrap. */ static int svcauth_gss_wrap_priv(struct svc_rqst *rqstp) { struct gss_svc_data *gsd = rqstp->rq_auth_data; struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *buf = &rqstp->rq_res; struct kvec *head = buf->head; struct kvec *tail = buf->tail; u32 offset, pad, maj_stat; __be32 *p; offset = svcauth_gss_prepare_to_wrap(rqstp, gsd); if (!offset) return 0; /* * Buffer space for this field has already been reserved * in svcauth_gss_accept(). Note that the GSS sequence * number is encrypted along with the RPC reply payload. */ if (xdr_encode_word(buf, offset + XDR_UNIT, gc->gc_seq)) goto wrap_failed; /* * If there is currently tail data, make sure there is * room for the head, tail, and 2 * RPC_MAX_AUTH_SIZE in * the page, and move the current tail data such that * there is RPC_MAX_AUTH_SIZE slack space available in * both the head and tail. */ if (tail->iov_base) { if (tail->iov_base >= head->iov_base + PAGE_SIZE) goto wrap_failed; if (tail->iov_base < head->iov_base) goto wrap_failed; if (tail->iov_len + head->iov_len + 2 * RPC_MAX_AUTH_SIZE > PAGE_SIZE) goto wrap_failed; memmove(tail->iov_base + RPC_MAX_AUTH_SIZE, tail->iov_base, tail->iov_len); tail->iov_base += RPC_MAX_AUTH_SIZE; } /* * If there is no current tail data, make sure there is * room for the head data, and 2 * RPC_MAX_AUTH_SIZE in the * allotted page, and set up tail information such that there * is RPC_MAX_AUTH_SIZE slack space available in both the * head and tail. */ if (!tail->iov_base) { if (head->iov_len + 2 * RPC_MAX_AUTH_SIZE > PAGE_SIZE) goto wrap_failed; tail->iov_base = head->iov_base + head->iov_len + RPC_MAX_AUTH_SIZE; tail->iov_len = 0; } maj_stat = gss_wrap(gsd->rsci->mechctx, offset + XDR_UNIT, buf, buf->pages); if (maj_stat != GSS_S_COMPLETE) goto bad_wrap; /* Wrapping can change the size of databody_priv. */ if (xdr_encode_word(buf, offset, buf->len - offset - XDR_UNIT)) goto wrap_failed; pad = xdr_pad_size(buf->len - offset - XDR_UNIT); p = (__be32 *)(tail->iov_base + tail->iov_len); memset(p, 0, pad); tail->iov_len += pad; buf->len += pad; return 0; wrap_failed: trace_rpcgss_svc_wrap_failed(rqstp); return -EINVAL; bad_wrap: trace_rpcgss_svc_wrap(rqstp, maj_stat); return -ENOMEM; } /** * svcauth_gss_release - Wrap payload and release resources * @rqstp: RPC transaction context * * Return values: * %0: the Reply is ready to be sent * %-ENOMEM: failed to allocate memory * %-EINVAL: encoding error */ static int svcauth_gss_release(struct svc_rqst *rqstp) { struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); struct gss_svc_data *gsd = rqstp->rq_auth_data; struct rpc_gss_wire_cred *gc; int stat; if (!gsd) goto out; if (rqstp->rq_auth_stat != rpc_auth_ok) goto out; gc = &gsd->clcred; if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; switch (gc->gc_svc) { case RPC_GSS_SVC_NONE: break; case RPC_GSS_SVC_INTEGRITY: stat = svcauth_gss_wrap_integ(rqstp); if (stat) goto out_err; break; case RPC_GSS_SVC_PRIVACY: stat = svcauth_gss_wrap_priv(rqstp); if (stat) goto out_err; break; /* * For any other gc_svc value, svcauth_gss_accept() already set * the auth_error appropriately; just fall through: */ } out: stat = 0; out_err: if (rqstp->rq_client) auth_domain_put(rqstp->rq_client); rqstp->rq_client = NULL; if (rqstp->rq_gssclient) auth_domain_put(rqstp->rq_gssclient); rqstp->rq_gssclient = NULL; if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; if (gsd && gsd->rsci) { cache_put(&gsd->rsci->h, sn->rsc_cache); gsd->rsci = NULL; } return stat; } static void svcauth_gss_domain_release_rcu(struct rcu_head *head) { struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head); struct gss_domain *gd = container_of(dom, struct gss_domain, h); kfree(dom->name); kfree(gd); } static void svcauth_gss_domain_release(struct auth_domain *dom) { call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu); } static rpc_authflavor_t svcauth_gss_pseudoflavor(struct svc_rqst *rqstp) { return svcauth_gss_flavor(rqstp->rq_gssclient); } static struct auth_ops svcauthops_gss = { .name = "rpcsec_gss", .owner = THIS_MODULE, .flavour = RPC_AUTH_GSS, .accept = svcauth_gss_accept, .release = svcauth_gss_release, .domain_release = svcauth_gss_domain_release, .set_client = svcauth_gss_set_client, .pseudoflavor = svcauth_gss_pseudoflavor, }; static int rsi_cache_create_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&rsi_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->rsi_cache = cd; return 0; } static void rsi_cache_destroy_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->rsi_cache; sn->rsi_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } static int rsc_cache_create_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&rsc_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->rsc_cache = cd; return 0; } static void rsc_cache_destroy_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->rsc_cache; sn->rsc_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } int gss_svc_init_net(struct net *net) { int rv; rv = rsc_cache_create_net(net); if (rv) return rv; rv = rsi_cache_create_net(net); if (rv) goto out1; rv = create_use_gss_proxy_proc_entry(net); if (rv) goto out2; rv = create_krb5_enctypes_proc_entry(net); if (rv) goto out3; return 0; out3: destroy_use_gss_proxy_proc_entry(net); out2: rsi_cache_destroy_net(net); out1: rsc_cache_destroy_net(net); return rv; } void gss_svc_shutdown_net(struct net *net) { destroy_krb5_enctypes_proc_entry(net); destroy_use_gss_proxy_proc_entry(net); rsi_cache_destroy_net(net); rsc_cache_destroy_net(net); } int gss_svc_init(void) { return svc_auth_register(RPC_AUTH_GSS, &svcauthops_gss); } void gss_svc_shutdown(void) { svc_auth_unregister(RPC_AUTH_GSS); } |
| 2 72 72 3 2 2 1 35 1 1 46 1 46 46 2 4 40 38 2 40 42 42 42 5 5 5 2 3 5 5 1 1 26 1 26 21 7 6 26 14 4 12 15 5 8 3 14 14 13 1 1 8 4 1 50 50 45 4 2 1 48 70 1 69 69 4 1 4 1 2 1 61 62 1 44 20 62 32 30 89 1 2 1 62 1 1 20 1 4 78 1 63 15 15 1 47 125 125 2 123 49 76 76 4 4 2 2 3 281 18 37 47 11 47 2 2 1 1 2 1 1 1 3 1 4 2 1 1 1 1 2 3 1 2 1 2 1 1 2 2 1 1 4 1 89 2 1 7 2 1 3 17 34 280 281 165 50 23 23 23 9 22 3 23 3 3 6 6 6 1 6 9 9 1 2 6 6 123 1 37 85 57 32 2 54 1 45 40 111 111 86 25 62 47 24 86 1 93 93 1 93 93 54 93 93 93 93 1 1 91 91 41 50 50 4 4 4 2 3 3 3 43 43 1 32 32 32 1 32 32 24 15 19 6 16 2 9 6 145 145 2 10 145 136 138 138 42 42 42 42 42 5 5 46 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * History: * Started: Aug 9 by Lawrence Foard (entropy@world.std.com), * to allow user process control of SCSI devices. * Development Sponsored by Killy Corp. NY NY * * Original driver (sg.c): * Copyright (C) 1992 Lawrence Foard * Version 2 and 3 extensions to driver: * Copyright (C) 1998 - 2014 Douglas Gilbert */ static int sg_version_num = 30536; /* 2 digits for each component */ #define SG_VERSION_STR "3.5.36" /* * D. P. Gilbert (dgilbert@interlog.com), notes: * - scsi logging is available via SCSI_LOG_TIMEOUT macros. First * the kernel/module needs to be built with CONFIG_SCSI_LOGGING * (otherwise the macros compile to empty statements). * */ #include <linux/module.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/mtio.h> #include <linux/ioctl.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/moduleparam.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/blktrace_api.h> #include <linux/mutex.h> #include <linux/atomic.h> #include <linux/ratelimit.h> #include <linux/uio.h> #include <linux/cred.h> /* for sg_check_file_access() */ #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsi_tcq.h> #include <scsi/sg.h> #include "scsi_logging.h" #ifdef CONFIG_SCSI_PROC_FS #include <linux/proc_fs.h> static char *sg_version_date = "20140603"; static int sg_proc_init(void); #endif #define SG_ALLOW_DIO_DEF 0 #define SG_MAX_DEVS (1 << MINORBITS) /* SG_MAX_CDB_SIZE should be 260 (spc4r37 section 3.1.30) however the type * of sg_io_hdr::cmd_len can only represent 255. All SCSI commands greater * than 16 bytes are "variable length" whose length is a multiple of 4 */ #define SG_MAX_CDB_SIZE 252 #define SG_DEFAULT_TIMEOUT mult_frac(SG_DEFAULT_TIMEOUT_USER, HZ, USER_HZ) /* N.B. This variable is readable and writeable via * /proc/scsi/sg/def_reserved_size . Each time sg_open() is called a buffer * of this size (or less if there is not enough memory) will be reserved * for use by this file descriptor. */ /* picks up init parameter */ static int def_reserved_size = SG_DEF_RESERVED_SIZE; static int sg_allow_dio = SG_ALLOW_DIO_DEF; static int scatter_elem_sz = SG_SCATTER_SZ; static int scatter_elem_sz_prev = SG_SCATTER_SZ; #define SG_SECTOR_SZ 512 static int sg_add_device(struct device *); static void sg_remove_device(struct device *); static DEFINE_IDR(sg_index_idr); static DEFINE_RWLOCK(sg_index_lock); /* Also used to lock file descriptor list for device */ static struct class_interface sg_interface = { .add_dev = sg_add_device, .remove_dev = sg_remove_device, }; typedef struct sg_scatter_hold { /* holding area for scsi scatter gather info */ unsigned short k_use_sg; /* Count of kernel scatter-gather pieces */ unsigned sglist_len; /* size of malloc'd scatter-gather list ++ */ unsigned bufflen; /* Size of (aggregate) data buffer */ struct page **pages; int page_order; char dio_in_use; /* 0->indirect IO (or mmap), 1->dio */ unsigned char cmd_opcode; /* first byte of command */ } Sg_scatter_hold; struct sg_device; /* forward declarations */ struct sg_fd; typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */ struct list_head entry; /* list entry */ struct sg_fd *parentfp; /* NULL -> not in use */ Sg_scatter_hold data; /* hold buffer, perhaps scatter list */ sg_io_hdr_t header; /* scsi command+info, see <scsi/sg.h> */ unsigned char sense_b[SCSI_SENSE_BUFFERSIZE]; char res_used; /* 1 -> using reserve buffer, 0 -> not ... */ char orphan; /* 1 -> drop on sight, 0 -> normal */ char sg_io_owned; /* 1 -> packet belongs to SG_IO */ /* done protected by rq_list_lock */ char done; /* 0->before bh, 1->before read, 2->read */ struct request *rq; struct bio *bio; struct execute_work ew; } Sg_request; typedef struct sg_fd { /* holds the state of a file descriptor */ struct list_head sfd_siblings; /* protected by device's sfd_lock */ struct sg_device *parentdp; /* owning device */ wait_queue_head_t read_wait; /* queue read until command done */ rwlock_t rq_list_lock; /* protect access to list in req_arr */ struct mutex f_mutex; /* protect against changes in this fd */ int timeout; /* defaults to SG_DEFAULT_TIMEOUT */ int timeout_user; /* defaults to SG_DEFAULT_TIMEOUT_USER */ Sg_scatter_hold reserve; /* buffer held for this file descriptor */ struct list_head rq_list; /* head of request list */ struct fasync_struct *async_qp; /* used by asynchronous notification */ Sg_request req_arr[SG_MAX_QUEUE]; /* used as singly-linked list */ char force_packid; /* 1 -> pack_id input to read(), 0 -> ignored */ char cmd_q; /* 1 -> allow command queuing, 0 -> don't */ unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */ char keep_orphan; /* 0 -> drop orphan (def), 1 -> keep for read() */ char mmap_called; /* 0 -> mmap() never called on this fd */ char res_in_use; /* 1 -> 'reserve' array in use */ struct kref f_ref; struct execute_work ew; } Sg_fd; typedef struct sg_device { /* holds the state of each scsi generic device */ struct scsi_device *device; wait_queue_head_t open_wait; /* queue open() when O_EXCL present */ struct mutex open_rel_lock; /* held when in open() or release() */ int sg_tablesize; /* adapter's max scatter-gather table size */ u32 index; /* device index number */ struct list_head sfds; rwlock_t sfd_lock; /* protect access to sfd list */ atomic_t detaching; /* 0->device usable, 1->device detaching */ bool exclude; /* 1->open(O_EXCL) succeeded and is active */ int open_cnt; /* count of opens (perhaps < num(sfds) ) */ char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */ char name[DISK_NAME_LEN]; struct cdev * cdev; /* char_dev [sysfs: /sys/cdev/major/sg<n>] */ struct kref d_ref; } Sg_device; /* tasklet or soft irq callback */ static enum rq_end_io_ret sg_rq_end_io(struct request *rq, blk_status_t status, const struct io_comp_batch *iob); static int sg_start_req(Sg_request *srp, unsigned char *cmd); static int sg_finish_rem_req(Sg_request * srp); static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size); static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp); static ssize_t sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, size_t count, int blocking, int read_only, int sg_io_owned, Sg_request **o_srp); static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking); static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer); static void sg_remove_scat(Sg_fd * sfp, Sg_scatter_hold * schp); static void sg_build_reserve(Sg_fd * sfp, int req_size); static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size); static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp); static Sg_fd *sg_add_sfp(Sg_device * sdp); static void sg_remove_sfp(struct kref *); static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id, bool *busy); static Sg_request *sg_add_request(Sg_fd * sfp); static int sg_remove_request(Sg_fd * sfp, Sg_request * srp); static Sg_device *sg_get_dev(int dev); static void sg_device_destroy(struct kref *kref); #define SZ_SG_HEADER sizeof(struct sg_header) #define SZ_SG_IO_HDR sizeof(sg_io_hdr_t) #define SZ_SG_IOVEC sizeof(sg_iovec_t) #define SZ_SG_REQ_INFO sizeof(sg_req_info_t) #define sg_printk(prefix, sdp, fmt, a...) \ sdev_prefix_printk(prefix, (sdp)->device, (sdp)->name, fmt, ##a) /* * The SCSI interfaces that use read() and write() as an asynchronous variant of * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways * to trigger read() and write() calls from various contexts with elevated * privileges. This can lead to kernel memory corruption (e.g. if these * interfaces are called through splice()) and privilege escalation inside * userspace (e.g. if a process with access to such a device passes a file * descriptor to a SUID binary as stdin/stdout/stderr). * * This function provides protection for the legacy API by restricting the * calling context. */ static int sg_check_file_access(struct file *filp, const char *caller) { if (filp->f_cred != current_real_cred()) { pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", caller, task_tgid_vnr(current), current->comm); return -EPERM; } return 0; } static int sg_allow_access(struct file *filp, unsigned char *cmd) { struct sg_fd *sfp = filp->private_data; if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; if (!scsi_cmd_allowed(cmd, filp->f_mode & FMODE_WRITE)) return -EPERM; return 0; } static int open_wait(Sg_device *sdp, int flags) { int retval = 0; if (flags & O_EXCL) { while (sdp->open_cnt > 0) { mutex_unlock(&sdp->open_rel_lock); retval = wait_event_interruptible(sdp->open_wait, (atomic_read(&sdp->detaching) || !sdp->open_cnt)); mutex_lock(&sdp->open_rel_lock); if (retval) /* -ERESTARTSYS */ return retval; if (atomic_read(&sdp->detaching)) return -ENODEV; } } else { while (sdp->exclude) { mutex_unlock(&sdp->open_rel_lock); retval = wait_event_interruptible(sdp->open_wait, (atomic_read(&sdp->detaching) || !sdp->exclude)); mutex_lock(&sdp->open_rel_lock); if (retval) /* -ERESTARTSYS */ return retval; if (atomic_read(&sdp->detaching)) return -ENODEV; } } return retval; } /* Returns 0 on success, else a negated errno value */ static int sg_open(struct inode *inode, struct file *filp) { int dev = iminor(inode); int flags = filp->f_flags; struct request_queue *q; struct scsi_device *device; Sg_device *sdp; Sg_fd *sfp; int retval; nonseekable_open(inode, filp); if ((flags & O_EXCL) && (O_RDONLY == (flags & O_ACCMODE))) return -EPERM; /* Can't lock it with read only access */ sdp = sg_get_dev(dev); if (IS_ERR(sdp)) return PTR_ERR(sdp); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_open: flags=0x%x\n", flags)); /* This driver's module count bumped by fops_get in <linux/fs.h> */ /* Prevent the device driver from vanishing while we sleep */ device = sdp->device; retval = scsi_device_get(device); if (retval) goto sg_put; /* scsi_block_when_processing_errors() may block so bypass * check if O_NONBLOCK. Permits SCSI commands to be issued * during error recovery. Tread carefully. */ if (!((flags & O_NONBLOCK) || scsi_block_when_processing_errors(device))) { retval = -ENXIO; /* we are in error recovery for this device */ goto sdp_put; } mutex_lock(&sdp->open_rel_lock); if (flags & O_NONBLOCK) { if (flags & O_EXCL) { if (sdp->open_cnt > 0) { retval = -EBUSY; goto error_mutex_locked; } } else { if (sdp->exclude) { retval = -EBUSY; goto error_mutex_locked; } } } else { retval = open_wait(sdp, flags); if (retval) /* -ERESTARTSYS or -ENODEV */ goto error_mutex_locked; } /* N.B. at this point we are holding the open_rel_lock */ if (flags & O_EXCL) sdp->exclude = true; if (sdp->open_cnt < 1) { /* no existing opens */ sdp->sgdebug = 0; q = device->request_queue; sdp->sg_tablesize = queue_max_segments(q); } sfp = sg_add_sfp(sdp); if (IS_ERR(sfp)) { retval = PTR_ERR(sfp); goto out_undo; } filp->private_data = sfp; sdp->open_cnt++; mutex_unlock(&sdp->open_rel_lock); retval = 0; sg_put: kref_put(&sdp->d_ref, sg_device_destroy); return retval; out_undo: if (flags & O_EXCL) { sdp->exclude = false; /* undo if error */ wake_up_interruptible(&sdp->open_wait); } error_mutex_locked: mutex_unlock(&sdp->open_rel_lock); sdp_put: kref_put(&sdp->d_ref, sg_device_destroy); scsi_device_put(device); return retval; } /* Release resources associated with a successful sg_open() * Returns 0 on success, else a negated errno value */ static int sg_release(struct inode *inode, struct file *filp) { Sg_device *sdp; Sg_fd *sfp; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_release\n")); mutex_lock(&sdp->open_rel_lock); sdp->open_cnt--; /* possibly many open()s waiting on exlude clearing, start many; * only open(O_EXCL)s wait on 0==open_cnt so only start one */ if (sdp->exclude) { sdp->exclude = false; wake_up_interruptible_all(&sdp->open_wait); } else if (0 == sdp->open_cnt) { wake_up_interruptible(&sdp->open_wait); } mutex_unlock(&sdp->open_rel_lock); kref_put(&sfp->f_ref, sg_remove_sfp); return 0; } static int get_sg_io_pack_id(int *pack_id, void __user *buf, size_t count) { struct sg_header __user *old_hdr = buf; int reply_len; if (count >= SZ_SG_HEADER) { /* negative reply_len means v3 format, otherwise v1/v2 */ if (get_user(reply_len, &old_hdr->reply_len)) return -EFAULT; if (reply_len >= 0) return get_user(*pack_id, &old_hdr->pack_id); if (in_compat_syscall() && count >= sizeof(struct compat_sg_io_hdr)) { struct compat_sg_io_hdr __user *hp = buf; return get_user(*pack_id, &hp->pack_id); } if (count >= sizeof(struct sg_io_hdr)) { struct sg_io_hdr __user *hp = buf; return get_user(*pack_id, &hp->pack_id); } } /* no valid header was passed, so ignore the pack_id */ *pack_id = -1; return 0; } static ssize_t sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos) { Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; int req_pack_id = -1; bool busy; sg_io_hdr_t *hp; struct sg_header *old_hdr; int retval; /* * This could cause a response to be stranded. Close the associated * file descriptor to free up any resources being held. */ retval = sg_check_file_access(filp, __func__); if (retval) return retval; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_read: count=%d\n", (int) count)); if (sfp->force_packid) retval = get_sg_io_pack_id(&req_pack_id, buf, count); if (retval) return retval; srp = sg_get_rq_mark(sfp, req_pack_id, &busy); if (!srp) { /* now wait on packet to arrive */ if (filp->f_flags & O_NONBLOCK) return -EAGAIN; retval = wait_event_interruptible(sfp->read_wait, ((srp = sg_get_rq_mark(sfp, req_pack_id, &busy)) || (!busy && atomic_read(&sdp->detaching)))); if (!srp) /* signal or detaching */ return retval ? retval : -ENODEV; } if (srp->header.interface_id != '\0') return sg_new_read(sfp, buf, count, srp); hp = &srp->header; old_hdr = kzalloc(SZ_SG_HEADER, GFP_KERNEL); if (!old_hdr) return -ENOMEM; old_hdr->reply_len = (int) hp->timeout; old_hdr->pack_len = old_hdr->reply_len; /* old, strange behaviour */ old_hdr->pack_id = hp->pack_id; old_hdr->twelve_byte = ((srp->data.cmd_opcode >= 0xc0) && (12 == hp->cmd_len)) ? 1 : 0; old_hdr->target_status = hp->masked_status; old_hdr->host_status = hp->host_status; old_hdr->driver_status = hp->driver_status; if ((CHECK_CONDITION & hp->masked_status) || (srp->sense_b[0] & 0x70) == 0x70) { old_hdr->driver_status = DRIVER_SENSE; memcpy(old_hdr->sense_buffer, srp->sense_b, sizeof (old_hdr->sense_buffer)); } switch (hp->host_status) { /* This setup of 'result' is for backward compatibility and is best ignored by the user who should use target, host + driver status */ case DID_OK: case DID_PASSTHROUGH: case DID_SOFT_ERROR: old_hdr->result = 0; break; case DID_NO_CONNECT: case DID_BUS_BUSY: case DID_TIME_OUT: old_hdr->result = EBUSY; break; case DID_BAD_TARGET: case DID_ABORT: case DID_PARITY: case DID_RESET: case DID_BAD_INTR: old_hdr->result = EIO; break; case DID_ERROR: old_hdr->result = (srp->sense_b[0] == 0 && hp->masked_status == GOOD) ? 0 : EIO; break; default: old_hdr->result = EIO; break; } /* Now copy the result back to the user buffer. */ if (count >= SZ_SG_HEADER) { if (copy_to_user(buf, old_hdr, SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } buf += SZ_SG_HEADER; if (count > old_hdr->reply_len) count = old_hdr->reply_len; if (count > SZ_SG_HEADER) { if (sg_read_oxfer(srp, buf, count - SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } } } else count = (old_hdr->result == 0) ? 0 : -EIO; sg_finish_rem_req(srp); sg_remove_request(sfp, srp); retval = count; free_old_hdr: kfree(old_hdr); return retval; } static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) { sg_io_hdr_t *hp = &srp->header; int err = 0, err2; int len; if (in_compat_syscall()) { if (count < sizeof(struct compat_sg_io_hdr)) { err = -EINVAL; goto err_out; } } else if (count < SZ_SG_IO_HDR) { err = -EINVAL; goto err_out; } hp->sb_len_wr = 0; if ((hp->mx_sb_len > 0) && hp->sbp) { if ((CHECK_CONDITION & hp->masked_status) || (srp->sense_b[0] & 0x70) == 0x70) { int sb_len = SCSI_SENSE_BUFFERSIZE; sb_len = (hp->mx_sb_len > sb_len) ? sb_len : hp->mx_sb_len; len = 8 + (int) srp->sense_b[7]; /* Additional sense length field */ len = (len > sb_len) ? sb_len : len; if (copy_to_user(hp->sbp, srp->sense_b, len)) { err = -EFAULT; goto err_out; } hp->driver_status = DRIVER_SENSE; hp->sb_len_wr = len; } } if (hp->masked_status || hp->host_status || hp->driver_status) hp->info |= SG_INFO_CHECK; err = put_sg_io_hdr(hp, buf); err_out: err2 = sg_finish_rem_req(srp); sg_remove_request(sfp, srp); return err ? : err2 ? : count; } static ssize_t sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos) { int mxsize, cmd_size, k; int input_size, blocking; unsigned char opcode; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; struct sg_header old_hdr; sg_io_hdr_t *hp; unsigned char cmnd[SG_MAX_CDB_SIZE]; int retval; retval = sg_check_file_access(filp, __func__); if (retval) return retval; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_write: count=%d\n", (int) count)); if (atomic_read(&sdp->detaching)) return -ENODEV; if (!((filp->f_flags & O_NONBLOCK) || scsi_block_when_processing_errors(sdp->device))) return -ENXIO; if (count < SZ_SG_HEADER) return -EIO; if (copy_from_user(&old_hdr, buf, SZ_SG_HEADER)) return -EFAULT; blocking = !(filp->f_flags & O_NONBLOCK); if (old_hdr.reply_len < 0) return sg_new_write(sfp, filp, buf, count, blocking, 0, 0, NULL); if (count < (SZ_SG_HEADER + 6)) return -EIO; /* The minimum scsi command length is 6 bytes. */ buf += SZ_SG_HEADER; if (get_user(opcode, buf)) return -EFAULT; if (!(srp = sg_add_request(sfp))) { SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sdp, "sg_write: queue full\n")); return -EDOM; } mutex_lock(&sfp->f_mutex); if (sfp->next_cmd_len > 0) { cmd_size = sfp->next_cmd_len; sfp->next_cmd_len = 0; /* reset so only this write() effected */ } else { cmd_size = COMMAND_SIZE(opcode); /* based on SCSI command group */ if ((opcode >= 0xc0) && old_hdr.twelve_byte) cmd_size = 12; } mutex_unlock(&sfp->f_mutex); SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp, "sg_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) opcode, cmd_size)); /* Determine buffer size. */ input_size = count - cmd_size; mxsize = (input_size > old_hdr.reply_len) ? input_size : old_hdr.reply_len; mxsize -= SZ_SG_HEADER; input_size -= SZ_SG_HEADER; if (input_size < 0) { sg_remove_request(sfp, srp); return -EIO; /* User did not pass enough bytes for this command. */ } hp = &srp->header; hp->interface_id = '\0'; /* indicator of old interface tunnelled */ hp->cmd_len = (unsigned char) cmd_size; hp->iovec_count = 0; hp->mx_sb_len = 0; if (input_size > 0) hp->dxfer_direction = (old_hdr.reply_len > SZ_SG_HEADER) ? SG_DXFER_TO_FROM_DEV : SG_DXFER_TO_DEV; else hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE; hp->dxfer_len = mxsize; if ((hp->dxfer_direction == SG_DXFER_TO_DEV) || (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV)) hp->dxferp = (char __user *)buf + cmd_size; else hp->dxferp = NULL; hp->sbp = NULL; hp->timeout = old_hdr.reply_len; /* structure abuse ... */ hp->flags = input_size; /* structure abuse ... */ hp->pack_id = old_hdr.pack_id; hp->usr_ptr = NULL; if (copy_from_user(cmnd, buf, cmd_size)) { sg_remove_request(sfp, srp); return -EFAULT; } /* * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV, * but is is possible that the app intended SG_DXFER_TO_DEV, because there * is a non-zero input_size, so emit a warning. */ if (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV) { printk_ratelimited(KERN_WARNING "sg_write: data in/out %d/%d bytes " "for SCSI command 0x%x-- guessing " "data in;\n program %s not setting " "count and/or reply_len properly\n", old_hdr.reply_len - (int)SZ_SG_HEADER, input_size, (unsigned int) cmnd[0], current->comm); } k = sg_common_write(sfp, srp, cmnd, sfp->timeout, blocking); return (k < 0) ? k : count; } static ssize_t sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, size_t count, int blocking, int read_only, int sg_io_owned, Sg_request **o_srp) { int k; Sg_request *srp; sg_io_hdr_t *hp; unsigned char cmnd[SG_MAX_CDB_SIZE]; int timeout; unsigned long ul_timeout; if (count < SZ_SG_IO_HDR) return -EINVAL; sfp->cmd_q = 1; /* when sg_io_hdr seen, set command queuing on */ if (!(srp = sg_add_request(sfp))) { SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp, "sg_new_write: queue full\n")); return -EDOM; } srp->sg_io_owned = sg_io_owned; hp = &srp->header; if (get_sg_io_hdr(hp, buf)) { sg_remove_request(sfp, srp); return -EFAULT; } hp->duration = jiffies_to_msecs(jiffies); if (hp->interface_id != 'S') { sg_remove_request(sfp, srp); return -ENOSYS; } if (hp->flags & SG_FLAG_MMAP_IO) { if (hp->dxfer_len > sfp->reserve.bufflen) { sg_remove_request(sfp, srp); return -ENOMEM; /* MMAP_IO size must fit in reserve buffer */ } if (hp->flags & SG_FLAG_DIRECT_IO) { sg_remove_request(sfp, srp); return -EINVAL; /* either MMAP_IO or DIRECT_IO (not both) */ } if (sfp->res_in_use) { sg_remove_request(sfp, srp); return -EBUSY; /* reserve buffer already being used */ } } ul_timeout = msecs_to_jiffies(srp->header.timeout); timeout = (ul_timeout < INT_MAX) ? ul_timeout : INT_MAX; if ((!hp->cmdp) || (hp->cmd_len < 6) || (hp->cmd_len > sizeof (cmnd))) { sg_remove_request(sfp, srp); return -EMSGSIZE; } if (copy_from_user(cmnd, hp->cmdp, hp->cmd_len)) { sg_remove_request(sfp, srp); return -EFAULT; } if (read_only && sg_allow_access(file, cmnd)) { sg_remove_request(sfp, srp); return -EPERM; } k = sg_common_write(sfp, srp, cmnd, timeout, blocking); if (k < 0) return k; if (o_srp) *o_srp = srp; return count; } static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking) { int k, at_head; Sg_device *sdp = sfp->parentdp; sg_io_hdr_t *hp = &srp->header; srp->data.cmd_opcode = cmnd[0]; /* hold opcode of command */ hp->status = 0; hp->masked_status = 0; hp->msg_status = 0; hp->info = 0; hp->host_status = 0; hp->driver_status = 0; hp->resid = 0; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_common_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) cmnd[0], (int) hp->cmd_len)); if (hp->dxfer_len >= SZ_256M) { sg_remove_request(sfp, srp); return -EINVAL; } k = sg_start_req(srp, cmnd); if (k) { SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp, "sg_common_write: start_req err=%d\n", k)); sg_finish_rem_req(srp); sg_remove_request(sfp, srp); return k; /* probably out of space --> ENOMEM */ } if (atomic_read(&sdp->detaching)) { if (srp->bio) { blk_mq_free_request(srp->rq); srp->rq = NULL; } sg_finish_rem_req(srp); sg_remove_request(sfp, srp); return -ENODEV; } if (hp->interface_id != '\0' && /* v3 (or later) interface */ (SG_FLAG_Q_AT_TAIL & hp->flags)) at_head = 0; else at_head = 1; srp->rq->timeout = timeout; kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */ srp->rq->end_io = sg_rq_end_io; blk_execute_rq_nowait(srp->rq, at_head); return 0; } static int srp_done(Sg_fd *sfp, Sg_request *srp) { unsigned long flags; int ret; read_lock_irqsave(&sfp->rq_list_lock, flags); ret = srp->done; read_unlock_irqrestore(&sfp->rq_list_lock, flags); return ret; } static int max_sectors_bytes(struct request_queue *q) { unsigned int max_sectors = queue_max_sectors(q); max_sectors = min_t(unsigned int, max_sectors, INT_MAX >> 9); return max_sectors << 9; } static void sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo) { Sg_request *srp; int val; unsigned int ms; val = 0; list_for_each_entry(srp, &sfp->rq_list, entry) { if (val >= SG_MAX_QUEUE) break; rinfo[val].req_state = srp->done + 1; rinfo[val].problem = srp->header.masked_status || srp->header.host_status || srp->header.driver_status; if (srp->done) rinfo[val].duration = srp->header.duration; else { ms = jiffies_to_msecs(jiffies); rinfo[val].duration = (ms > srp->header.duration) ? (ms - srp->header.duration) : 0; } rinfo[val].orphan = srp->orphan; rinfo[val].sg_io_owned = srp->sg_io_owned; rinfo[val].pack_id = srp->header.pack_id; rinfo[val].usr_ptr = srp->header.usr_ptr; val++; } } #ifdef CONFIG_COMPAT struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ char req_state; char orphan; char sg_io_owned; char problem; int pack_id; compat_uptr_t usr_ptr; unsigned int duration; int unused; }; static int put_compat_request_table(struct compat_sg_req_info __user *o, struct sg_req_info *rinfo) { int i; for (i = 0; i < SG_MAX_QUEUE; i++) { if (copy_to_user(o + i, rinfo + i, offsetof(sg_req_info_t, usr_ptr)) || put_user((uintptr_t)rinfo[i].usr_ptr, &o[i].usr_ptr) || put_user(rinfo[i].duration, &o[i].duration) || put_user(rinfo[i].unused, &o[i].unused)) return -EFAULT; } return 0; } #endif static long sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp, unsigned int cmd_in, void __user *p) { int __user *ip = p; int result, val, read_only; Sg_request *srp; unsigned long iflags; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_ioctl: cmd=0x%x\n", (int) cmd_in)); read_only = (O_RDWR != (filp->f_flags & O_ACCMODE)); switch (cmd_in) { case SG_IO: if (atomic_read(&sdp->detaching)) return -ENODEV; if (!scsi_block_when_processing_errors(sdp->device)) return -ENXIO; result = sg_new_write(sfp, filp, p, SZ_SG_IO_HDR, 1, read_only, 1, &srp); if (result < 0) return result; result = wait_event_interruptible(sfp->read_wait, srp_done(sfp, srp)); write_lock_irq(&sfp->rq_list_lock); if (srp->done) { srp->done = 2; write_unlock_irq(&sfp->rq_list_lock); result = sg_new_read(sfp, p, SZ_SG_IO_HDR, srp); return (result < 0) ? result : 0; } srp->orphan = 1; write_unlock_irq(&sfp->rq_list_lock); return result; /* -ERESTARTSYS because signal hit process */ case SG_SET_TIMEOUT: result = get_user(val, ip); if (result) return result; if (val < 0) return -EIO; if (val >= mult_frac((s64)INT_MAX, USER_HZ, HZ)) val = min_t(s64, mult_frac((s64)INT_MAX, USER_HZ, HZ), INT_MAX); sfp->timeout_user = val; sfp->timeout = mult_frac(val, HZ, USER_HZ); return 0; case SG_GET_TIMEOUT: /* N.B. User receives timeout as return value */ /* strange ..., for backward compatibility */ return sfp->timeout_user; case SG_SET_FORCE_LOW_DMA: /* * N.B. This ioctl never worked properly, but failed to * return an error value. So returning '0' to keep compability * with legacy applications. */ return 0; case SG_GET_LOW_DMA: return put_user(0, ip); case SG_GET_SCSI_ID: { sg_scsi_id_t v; if (atomic_read(&sdp->detaching)) return -ENODEV; memset(&v, 0, sizeof(v)); v.host_no = sdp->device->host->host_no; v.channel = sdp->device->channel; v.scsi_id = sdp->device->id; v.lun = sdp->device->lun; v.scsi_type = sdp->device->type; v.h_cmd_per_lun = sdp->device->host->cmd_per_lun; v.d_queue_depth = sdp->device->queue_depth; if (copy_to_user(p, &v, sizeof(sg_scsi_id_t))) return -EFAULT; return 0; } case SG_SET_FORCE_PACK_ID: result = get_user(val, ip); if (result) return result; sfp->force_packid = val ? 1 : 0; return 0; case SG_GET_PACK_ID: read_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(srp, &sfp->rq_list, entry) { if ((1 == srp->done) && (!srp->sg_io_owned)) { read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(srp->header.pack_id, ip); } } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(-1, ip); case SG_GET_NUM_WAITING: read_lock_irqsave(&sfp->rq_list_lock, iflags); val = 0; list_for_each_entry(srp, &sfp->rq_list, entry) { if ((1 == srp->done) && (!srp->sg_io_owned)) ++val; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(val, ip); case SG_GET_SG_TABLESIZE: return put_user(sdp->sg_tablesize, ip); case SG_SET_RESERVED_SIZE: result = get_user(val, ip); if (result) return result; if (val < 0) return -EINVAL; val = min_t(int, val, max_sectors_bytes(sdp->device->request_queue)); mutex_lock(&sfp->f_mutex); if (val != sfp->reserve.bufflen) { if (sfp->mmap_called || sfp->res_in_use) { mutex_unlock(&sfp->f_mutex); return -EBUSY; } sg_remove_scat(sfp, &sfp->reserve); sg_build_reserve(sfp, val); } mutex_unlock(&sfp->f_mutex); return 0; case SG_GET_RESERVED_SIZE: val = min_t(int, sfp->reserve.bufflen, max_sectors_bytes(sdp->device->request_queue)); return put_user(val, ip); case SG_SET_COMMAND_Q: result = get_user(val, ip); if (result) return result; sfp->cmd_q = val ? 1 : 0; return 0; case SG_GET_COMMAND_Q: return put_user((int) sfp->cmd_q, ip); case SG_SET_KEEP_ORPHAN: result = get_user(val, ip); if (result) return result; sfp->keep_orphan = val; return 0; case SG_GET_KEEP_ORPHAN: return put_user((int) sfp->keep_orphan, ip); case SG_NEXT_CMD_LEN: result = get_user(val, ip); if (result) return result; if (val > SG_MAX_CDB_SIZE) return -ENOMEM; sfp->next_cmd_len = (val > 0) ? val : 0; return 0; case SG_GET_VERSION_NUM: return put_user(sg_version_num, ip); case SG_GET_ACCESS_COUNT: /* faked - we don't have a real access count anymore */ val = (sdp->device ? 1 : 0); return put_user(val, ip); case SG_GET_REQUEST_TABLE: { sg_req_info_t *rinfo; rinfo = kcalloc(SG_MAX_QUEUE, SZ_SG_REQ_INFO, GFP_KERNEL); if (!rinfo) return -ENOMEM; read_lock_irqsave(&sfp->rq_list_lock, iflags); sg_fill_request_table(sfp, rinfo); read_unlock_irqrestore(&sfp->rq_list_lock, iflags); #ifdef CONFIG_COMPAT if (in_compat_syscall()) result = put_compat_request_table(p, rinfo); else #endif result = copy_to_user(p, rinfo, SZ_SG_REQ_INFO * SG_MAX_QUEUE); result = result ? -EFAULT : 0; kfree(rinfo); return result; } case SG_EMULATED_HOST: if (atomic_read(&sdp->detaching)) return -ENODEV; return put_user(sdp->device->host->hostt->emulated, ip); case SCSI_IOCTL_SEND_COMMAND: if (atomic_read(&sdp->detaching)) return -ENODEV; return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, cmd_in, p); case SG_SET_DEBUG: result = get_user(val, ip); if (result) return result; sdp->sgdebug = (char) val; return 0; case BLKSECTGET: return put_user(max_sectors_bytes(sdp->device->request_queue), ip); case BLKTRACESETUP: return blk_trace_setup(sdp->device->request_queue, sdp->name, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), NULL, p); case BLKTRACESTART: return blk_trace_startstop(sdp->device->request_queue, 1); case BLKTRACESTOP: return blk_trace_startstop(sdp->device->request_queue, 0); case BLKTRACETEARDOWN: return blk_trace_remove(sdp->device->request_queue); case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: case SCSI_IOCTL_PROBE_HOST: case SG_GET_TRANSFORM: case SG_SCSI_RESET: if (atomic_read(&sdp->detaching)) return -ENODEV; break; default: if (read_only) return -EPERM; /* don't know so take safe approach */ break; } result = scsi_ioctl_block_when_processing_errors(sdp->device, cmd_in, filp->f_flags & O_NDELAY); if (result) return result; return -ENOIOCTLCMD; } static long sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) { void __user *p = (void __user *)arg; Sg_device *sdp; Sg_fd *sfp; int ret; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; ret = sg_ioctl_common(filp, sdp, sfp, cmd_in, p); if (ret != -ENOIOCTLCMD) return ret; return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, cmd_in, p); } static __poll_t sg_poll(struct file *filp, poll_table * wait) { __poll_t res = 0; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; int count = 0; unsigned long iflags; sfp = filp->private_data; if (!sfp) return EPOLLERR; sdp = sfp->parentdp; if (!sdp) return EPOLLERR; poll_wait(filp, &sfp->read_wait, wait); read_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(srp, &sfp->rq_list, entry) { /* if any read waiting, flag it */ if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned)) res = EPOLLIN | EPOLLRDNORM; ++count; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (atomic_read(&sdp->detaching)) res |= EPOLLHUP; else if (!sfp->cmd_q) { if (0 == count) res |= EPOLLOUT | EPOLLWRNORM; } else if (count < SG_MAX_QUEUE) res |= EPOLLOUT | EPOLLWRNORM; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_poll: res=0x%x\n", (__force u32) res)); return res; } static int sg_fasync(int fd, struct file *filp, int mode) { Sg_device *sdp; Sg_fd *sfp; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_fasync: mode=%d\n", mode)); return fasync_helper(fd, filp, mode, &sfp->async_qp); } static vm_fault_t sg_vma_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; Sg_fd *sfp; unsigned long offset, len, sa; Sg_scatter_hold *rsv_schp; int k, length; if ((NULL == vma) || (!(sfp = (Sg_fd *) vma->vm_private_data))) return VM_FAULT_SIGBUS; rsv_schp = &sfp->reserve; offset = vmf->pgoff << PAGE_SHIFT; if (offset >= rsv_schp->bufflen) return VM_FAULT_SIGBUS; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sfp->parentdp, "sg_vma_fault: offset=%lu, scatg=%d\n", offset, rsv_schp->k_use_sg)); sa = vma->vm_start; length = 1 << (PAGE_SHIFT + rsv_schp->page_order); for (k = 0; k < rsv_schp->k_use_sg && sa < vma->vm_end; k++) { len = vma->vm_end - sa; len = (len < length) ? len : length; if (offset < len) { struct page *page = rsv_schp->pages[k] + (offset >> PAGE_SHIFT); get_page(page); /* increment page count */ vmf->page = page; return 0; /* success */ } sa += len; offset -= len; } return VM_FAULT_SIGBUS; } static const struct vm_operations_struct sg_mmap_vm_ops = { .fault = sg_vma_fault, }; static int sg_mmap(struct file *filp, struct vm_area_struct *vma) { Sg_fd *sfp; unsigned long req_sz, len, sa; Sg_scatter_hold *rsv_schp; int k, length; int ret = 0; if ((!filp) || (!vma) || (!(sfp = (Sg_fd *) filp->private_data))) return -ENXIO; req_sz = vma->vm_end - vma->vm_start; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sfp->parentdp, "sg_mmap starting, vm_start=%p, len=%d\n", (void *) vma->vm_start, (int) req_sz)); if (vma->vm_pgoff) return -EINVAL; /* want no offset */ rsv_schp = &sfp->reserve; mutex_lock(&sfp->f_mutex); if (req_sz > rsv_schp->bufflen) { ret = -ENOMEM; /* cannot map more than reserved buffer */ goto out; } sa = vma->vm_start; length = 1 << (PAGE_SHIFT + rsv_schp->page_order); for (k = 0; k < rsv_schp->k_use_sg && sa < vma->vm_end; k++) { len = vma->vm_end - sa; len = (len < length) ? len : length; sa += len; } sfp->mmap_called = 1; vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; out: mutex_unlock(&sfp->f_mutex); return ret; } static void sg_rq_end_io_usercontext(struct work_struct *work) { struct sg_request *srp = container_of(work, struct sg_request, ew.work); struct sg_fd *sfp = srp->parentfp; sg_finish_rem_req(srp); sg_remove_request(sfp, srp); kref_put(&sfp->f_ref, sg_remove_sfp); } /* * This function is a "bottom half" handler that is called by the mid * level when a command is completed (or has failed). */ static enum rq_end_io_ret sg_rq_end_io(struct request *rq, blk_status_t status, const struct io_comp_batch *iob) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); struct sg_request *srp = rq->end_io_data; Sg_device *sdp; Sg_fd *sfp; unsigned long iflags; unsigned int ms; char *sense; int result, resid, done = 1; if (WARN_ON(srp->done != 0)) return RQ_END_IO_NONE; sfp = srp->parentfp; if (WARN_ON(sfp == NULL)) return RQ_END_IO_NONE; sdp = sfp->parentdp; if (unlikely(atomic_read(&sdp->detaching))) pr_info("%s: device detaching\n", __func__); sense = scmd->sense_buffer; result = scmd->result; resid = scmd->resid_len; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp, "sg_cmd_done: pack_id=%d, res=0x%x\n", srp->header.pack_id, result)); srp->header.resid = resid; if (0 != result) { struct scsi_sense_hdr sshdr; srp->header.status = 0xff & result; srp->header.masked_status = sg_status_byte(result); srp->header.msg_status = COMMAND_COMPLETE; srp->header.host_status = host_byte(result); srp->header.driver_status = driver_byte(result); if ((sdp->sgdebug > 0) && ((CHECK_CONDITION == srp->header.masked_status) || (COMMAND_TERMINATED == srp->header.masked_status))) __scsi_print_sense(sdp->device, __func__, sense, SCSI_SENSE_BUFFERSIZE); /* Following if statement is a patch supplied by Eric Youngdale */ if (driver_byte(result) != 0 && scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr) && !scsi_sense_is_deferred(&sshdr) && sshdr.sense_key == UNIT_ATTENTION && sdp->device->removable) { /* Detected possible disc change. Set the bit - this */ /* may be used if there are filesystems using this device */ sdp->device->changed = 1; } } if (scmd->sense_len) memcpy(srp->sense_b, scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE); /* Rely on write phase to clean out srp status values, so no "else" */ /* * Free the request as soon as it is complete so that its resources * can be reused without waiting for userspace to read() the * result. But keep the associated bio (if any) around until * blk_rq_unmap_user() can be called from user context. */ srp->rq = NULL; blk_mq_free_request(rq); write_lock_irqsave(&sfp->rq_list_lock, iflags); if (unlikely(srp->orphan)) { if (sfp->keep_orphan) srp->sg_io_owned = 0; else done = 0; } srp->done = done; ms = jiffies_to_msecs(jiffies); srp->header.duration = (ms > srp->header.duration) ? (ms - srp->header.duration) : 0; write_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (likely(done)) { /* Now wake up any sg_read() that is waiting for this * packet. */ wake_up_interruptible(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_IN); kref_put(&sfp->f_ref, sg_remove_sfp); } else { INIT_WORK(&srp->ew.work, sg_rq_end_io_usercontext); schedule_work(&srp->ew.work); } return RQ_END_IO_NONE; } static const struct file_operations sg_fops = { .owner = THIS_MODULE, .read = sg_read, .write = sg_write, .poll = sg_poll, .unlocked_ioctl = sg_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = sg_open, .mmap = sg_mmap, .release = sg_release, .fasync = sg_fasync, }; static const struct class sg_sysfs_class = { .name = "scsi_generic" }; static int sg_sysfs_valid = 0; static Sg_device * sg_alloc(struct scsi_device *scsidp) { struct request_queue *q = scsidp->request_queue; Sg_device *sdp; unsigned long iflags; int error; u32 k; sdp = kzalloc_obj(Sg_device); if (!sdp) { sdev_printk(KERN_WARNING, scsidp, "%s: kmalloc Sg_device " "failure\n", __func__); return ERR_PTR(-ENOMEM); } idr_preload(GFP_KERNEL); write_lock_irqsave(&sg_index_lock, iflags); error = idr_alloc(&sg_index_idr, sdp, 0, SG_MAX_DEVS, GFP_NOWAIT); if (error < 0) { if (error == -ENOSPC) { sdev_printk(KERN_WARNING, scsidp, "Unable to attach sg device type=%d, minor number exceeds %d\n", scsidp->type, SG_MAX_DEVS - 1); error = -ENODEV; } else { sdev_printk(KERN_WARNING, scsidp, "%s: idr " "allocation Sg_device failure: %d\n", __func__, error); } goto out_unlock; } k = error; SCSI_LOG_TIMEOUT(3, sdev_printk(KERN_INFO, scsidp, "sg_alloc: dev=%d \n", k)); sprintf(sdp->name, "sg%d", k); sdp->device = scsidp; mutex_init(&sdp->open_rel_lock); INIT_LIST_HEAD(&sdp->sfds); init_waitqueue_head(&sdp->open_wait); atomic_set(&sdp->detaching, 0); rwlock_init(&sdp->sfd_lock); sdp->sg_tablesize = queue_max_segments(q); sdp->index = k; kref_init(&sdp->d_ref); error = 0; out_unlock: write_unlock_irqrestore(&sg_index_lock, iflags); idr_preload_end(); if (error) { kfree(sdp); return ERR_PTR(error); } return sdp; } static int sg_add_device(struct device *cl_dev) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); Sg_device *sdp = NULL; struct cdev * cdev = NULL; int error; unsigned long iflags; if (!blk_get_queue(scsidp->request_queue)) { pr_warn("%s: get scsi_device queue failed\n", __func__); return -ENODEV; } error = -ENOMEM; cdev = cdev_alloc(); if (!cdev) { pr_warn("%s: cdev_alloc failed\n", __func__); goto out; } cdev->owner = THIS_MODULE; cdev->ops = &sg_fops; sdp = sg_alloc(scsidp); if (IS_ERR(sdp)) { pr_warn("%s: sg_alloc failed\n", __func__); error = PTR_ERR(sdp); goto out; } error = cdev_add(cdev, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), 1); if (error) goto cdev_add_err; sdp->cdev = cdev; if (sg_sysfs_valid) { struct device *sg_class_member; sg_class_member = device_create(&sg_sysfs_class, cl_dev->parent, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), sdp, "%s", sdp->name); if (IS_ERR(sg_class_member)) { pr_err("%s: device_create failed\n", __func__); error = PTR_ERR(sg_class_member); goto cdev_add_err; } error = sysfs_create_link(&scsidp->sdev_gendev.kobj, &sg_class_member->kobj, "generic"); if (error) pr_err("%s: unable to make symlink 'generic' back " "to sg%d\n", __func__, sdp->index); } else pr_warn("%s: sg_sys Invalid\n", __func__); sdev_printk(KERN_NOTICE, scsidp, "Attached scsi generic sg%d " "type %d\n", sdp->index, scsidp->type); dev_set_drvdata(cl_dev, sdp); return 0; cdev_add_err: write_lock_irqsave(&sg_index_lock, iflags); idr_remove(&sg_index_idr, sdp->index); write_unlock_irqrestore(&sg_index_lock, iflags); kfree(sdp); out: if (cdev) cdev_del(cdev); blk_put_queue(scsidp->request_queue); return error; } static void sg_device_destroy(struct kref *kref) { struct sg_device *sdp = container_of(kref, struct sg_device, d_ref); struct request_queue *q = sdp->device->request_queue; unsigned long flags; /* CAUTION! Note that the device can still be found via idr_find() * even though the refcount is 0. Therefore, do idr_remove() BEFORE * any other cleanup. */ blk_trace_remove(q); blk_put_queue(q); write_lock_irqsave(&sg_index_lock, flags); idr_remove(&sg_index_idr, sdp->index); write_unlock_irqrestore(&sg_index_lock, flags); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_device_destroy\n")); kfree(sdp); } static void sg_remove_device(struct device *cl_dev) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); Sg_device *sdp = dev_get_drvdata(cl_dev); unsigned long iflags; Sg_fd *sfp; int val; if (!sdp) return; /* want sdp->detaching non-zero as soon as possible */ val = atomic_inc_return(&sdp->detaching); if (val > 1) return; /* only want to do following once per device */ SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "%s\n", __func__)); read_lock_irqsave(&sdp->sfd_lock, iflags); list_for_each_entry(sfp, &sdp->sfds, sfd_siblings) { wake_up_interruptible_all(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP); } wake_up_interruptible_all(&sdp->open_wait); read_unlock_irqrestore(&sdp->sfd_lock, iflags); sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic"); device_destroy(&sg_sysfs_class, MKDEV(SCSI_GENERIC_MAJOR, sdp->index)); cdev_del(sdp->cdev); sdp->cdev = NULL; kref_put(&sdp->d_ref, sg_device_destroy); } module_param_named(scatter_elem_sz, scatter_elem_sz, int, S_IRUGO | S_IWUSR); module_param_named(allow_dio, sg_allow_dio, int, S_IRUGO | S_IWUSR); static int def_reserved_size_set(const char *val, const struct kernel_param *kp) { int size, ret; if (!val) return -EINVAL; ret = kstrtoint(val, 0, &size); if (ret) return ret; /* limit to 1 MB */ if (size < 0 || size > 1048576) return -ERANGE; def_reserved_size = size; return 0; } static const struct kernel_param_ops def_reserved_size_ops = { .set = def_reserved_size_set, .get = param_get_int, }; module_param_cb(def_reserved_size, &def_reserved_size_ops, &def_reserved_size, S_IRUGO | S_IWUSR); MODULE_AUTHOR("Douglas Gilbert"); MODULE_DESCRIPTION("SCSI generic (sg) driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(SG_VERSION_STR); MODULE_ALIAS_CHARDEV_MAJOR(SCSI_GENERIC_MAJOR); MODULE_PARM_DESC(scatter_elem_sz, "scatter gather element " "size (default: max(SG_SCATTER_SZ, PAGE_SIZE))"); MODULE_PARM_DESC(def_reserved_size, "size of buffer reserved for each fd"); MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))"); static int __init init_sg(void) { int rc; if (scatter_elem_sz < PAGE_SIZE) { scatter_elem_sz = PAGE_SIZE; scatter_elem_sz_prev = scatter_elem_sz; } rc = register_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS, "sg"); if (rc) return rc; rc = class_register(&sg_sysfs_class); if (rc) goto err_out; sg_sysfs_valid = 1; rc = scsi_register_interface(&sg_interface); if (0 == rc) { #ifdef CONFIG_SCSI_PROC_FS sg_proc_init(); #endif /* CONFIG_SCSI_PROC_FS */ return 0; } class_unregister(&sg_sysfs_class); err_out: unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS); return rc; } static void __exit exit_sg(void) { #ifdef CONFIG_SCSI_PROC_FS remove_proc_subtree("scsi/sg", NULL); #endif /* CONFIG_SCSI_PROC_FS */ scsi_unregister_interface(&sg_interface); class_unregister(&sg_sysfs_class); sg_sysfs_valid = 0; unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS); idr_destroy(&sg_index_idr); } static int sg_start_req(Sg_request *srp, unsigned char *cmd) { int res; struct request *rq; Sg_fd *sfp = srp->parentfp; sg_io_hdr_t *hp = &srp->header; int dxfer_len = (int) hp->dxfer_len; int dxfer_dir = hp->dxfer_direction; unsigned int iov_count = hp->iovec_count; Sg_scatter_hold *req_schp = &srp->data; Sg_scatter_hold *rsv_schp = &sfp->reserve; struct request_queue *q = sfp->parentdp->device->request_queue; struct rq_map_data *md, map_data; int rw = hp->dxfer_direction == SG_DXFER_TO_DEV ? ITER_SOURCE : ITER_DEST; struct scsi_cmnd *scmd; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_start_req: dxfer_len=%d\n", dxfer_len)); /* * NOTE * * With scsi-mq enabled, there are a fixed number of preallocated * requests equal in number to shost->can_queue. If all of the * preallocated requests are already in use, then scsi_alloc_request() * will sleep until an active command completes, freeing up a request. * Although waiting in an asynchronous interface is less than ideal, we * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might * not expect an EWOULDBLOCK from this condition. */ rq = scsi_alloc_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); scmd = blk_mq_rq_to_pdu(rq); if (hp->cmd_len > sizeof(scmd->cmnd)) { blk_mq_free_request(rq); return -EINVAL; } memcpy(scmd->cmnd, cmd, hp->cmd_len); scmd->cmd_len = hp->cmd_len; srp->rq = rq; rq->end_io_data = srp; scmd->allowed = SG_DEFAULT_RETRIES; if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE)) return 0; if (sg_allow_dio && hp->flags & SG_FLAG_DIRECT_IO && dxfer_dir != SG_DXFER_UNKNOWN && !iov_count && blk_rq_aligned(q, (unsigned long)hp->dxferp, dxfer_len)) md = NULL; else md = &map_data; if (md) { mutex_lock(&sfp->f_mutex); if (dxfer_len <= rsv_schp->bufflen && !sfp->res_in_use) { sfp->res_in_use = 1; sg_link_reserve(sfp, srp, dxfer_len); } else if (hp->flags & SG_FLAG_MMAP_IO) { res = -EBUSY; /* sfp->res_in_use == 1 */ if (dxfer_len > rsv_schp->bufflen) res = -ENOMEM; mutex_unlock(&sfp->f_mutex); return res; } else { res = sg_build_indirect(req_schp, sfp, dxfer_len); if (res) { mutex_unlock(&sfp->f_mutex); return res; } } mutex_unlock(&sfp->f_mutex); md->pages = req_schp->pages; md->page_order = req_schp->page_order; md->nr_entries = req_schp->k_use_sg; md->offset = 0; md->null_mapped = hp->dxferp ? 0 : 1; if (dxfer_dir == SG_DXFER_TO_FROM_DEV) md->from_user = 1; else md->from_user = 0; } res = blk_rq_map_user_io(rq, md, hp->dxferp, hp->dxfer_len, GFP_KERNEL, iov_count, iov_count, 1, rw); if (!res) { srp->bio = rq->bio; if (!md) { req_schp->dio_in_use = 1; hp->info |= SG_INFO_DIRECT_IO; } } return res; } static int sg_finish_rem_req(Sg_request *srp) { int ret = 0; Sg_fd *sfp = srp->parentfp; Sg_scatter_hold *req_schp = &srp->data; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_finish_rem_req: res_used=%d\n", (int) srp->res_used)); if (srp->bio) ret = blk_rq_unmap_user(srp->bio); if (srp->rq) blk_mq_free_request(srp->rq); if (srp->res_used) sg_unlink_reserve(sfp, srp); else sg_remove_scat(sfp, req_schp); return ret; } static int sg_build_sgat(Sg_scatter_hold * schp, const Sg_fd * sfp, int tablesize) { int sg_bufflen = tablesize * sizeof(struct page *); gfp_t gfp_flags = GFP_ATOMIC | __GFP_NOWARN; schp->pages = kzalloc(sg_bufflen, gfp_flags); if (!schp->pages) return -ENOMEM; schp->sglist_len = sg_bufflen; return tablesize; /* number of scat_gath elements allocated */ } static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size) { int ret_sz = 0, i, k, rem_sz, num, mx_sc_elems; int sg_tablesize = sfp->parentdp->sg_tablesize; int blk_size = buff_size, order; gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN | __GFP_ZERO; if (blk_size < 0) return -EFAULT; if (0 == blk_size) ++blk_size; /* don't know why */ /* round request up to next highest SG_SECTOR_SZ byte boundary */ blk_size = ALIGN(blk_size, SG_SECTOR_SZ); SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_indirect: buff_size=%d, blk_size=%d\n", buff_size, blk_size)); /* N.B. ret_sz carried into this block ... */ mx_sc_elems = sg_build_sgat(schp, sfp, sg_tablesize); if (mx_sc_elems < 0) return mx_sc_elems; /* most likely -ENOMEM */ num = scatter_elem_sz; if (unlikely(num != scatter_elem_sz_prev)) { if (num < PAGE_SIZE) { scatter_elem_sz = PAGE_SIZE; scatter_elem_sz_prev = PAGE_SIZE; } else scatter_elem_sz_prev = num; } order = get_order(num); retry: ret_sz = 1 << (PAGE_SHIFT + order); for (k = 0, rem_sz = blk_size; rem_sz > 0 && k < mx_sc_elems; k++, rem_sz -= ret_sz) { num = (rem_sz > scatter_elem_sz_prev) ? scatter_elem_sz_prev : rem_sz; schp->pages[k] = alloc_pages(gfp_mask, order); if (!schp->pages[k]) goto out; if (num == scatter_elem_sz_prev) { if (unlikely(ret_sz > scatter_elem_sz_prev)) { scatter_elem_sz = ret_sz; scatter_elem_sz_prev = ret_sz; } } SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_indirect: k=%d, num=%d, ret_sz=%d\n", k, num, ret_sz)); } /* end of for loop */ schp->page_order = order; schp->k_use_sg = k; SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_indirect: k_use_sg=%d, rem_sz=%d\n", k, rem_sz)); schp->bufflen = blk_size; if (rem_sz > 0) /* must have failed */ return -ENOMEM; return 0; out: for (i = 0; i < k; i++) __free_pages(schp->pages[i], order); if (--order >= 0) goto retry; return -ENOMEM; } static void sg_remove_scat(Sg_fd * sfp, Sg_scatter_hold * schp) { SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_remove_scat: k_use_sg=%d\n", schp->k_use_sg)); if (schp->pages && schp->sglist_len > 0) { if (!schp->dio_in_use) { int k; for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) { SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp, "sg_remove_scat: k=%d, pg=0x%p\n", k, schp->pages[k])); __free_pages(schp->pages[k], schp->page_order); } kfree(schp->pages); } } memset(schp, 0, sizeof (*schp)); } static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer) { Sg_scatter_hold *schp = &srp->data; int k, num; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, srp->parentfp->parentdp, "sg_read_oxfer: num_read_xfer=%d\n", num_read_xfer)); if ((!outp) || (num_read_xfer <= 0)) return 0; num = 1 << (PAGE_SHIFT + schp->page_order); for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) { if (num > num_read_xfer) { if (copy_to_user(outp, page_address(schp->pages[k]), num_read_xfer)) return -EFAULT; break; } else { if (copy_to_user(outp, page_address(schp->pages[k]), num)) return -EFAULT; num_read_xfer -= num; if (num_read_xfer <= 0) break; outp += num; } } return 0; } static void sg_build_reserve(Sg_fd * sfp, int req_size) { Sg_scatter_hold *schp = &sfp->reserve; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_reserve: req_size=%d\n", req_size)); do { if (req_size < PAGE_SIZE) req_size = PAGE_SIZE; if (0 == sg_build_indirect(schp, sfp, req_size)) return; else sg_remove_scat(sfp, schp); req_size >>= 1; /* divide by 2 */ } while (req_size > (PAGE_SIZE / 2)); } static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size) { Sg_scatter_hold *req_schp = &srp->data; Sg_scatter_hold *rsv_schp = &sfp->reserve; int k, num, rem; srp->res_used = 1; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_link_reserve: size=%d\n", size)); rem = size; num = 1 << (PAGE_SHIFT + rsv_schp->page_order); for (k = 0; k < rsv_schp->k_use_sg; k++) { if (rem <= num) { req_schp->k_use_sg = k + 1; req_schp->sglist_len = rsv_schp->sglist_len; req_schp->pages = rsv_schp->pages; req_schp->bufflen = size; req_schp->page_order = rsv_schp->page_order; break; } else rem -= num; } if (k >= rsv_schp->k_use_sg) SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp, "sg_link_reserve: BAD size\n")); } static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp) { Sg_scatter_hold *req_schp = &srp->data; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, srp->parentfp->parentdp, "sg_unlink_reserve: req->k_use_sg=%d\n", (int) req_schp->k_use_sg)); req_schp->k_use_sg = 0; req_schp->bufflen = 0; req_schp->pages = NULL; req_schp->page_order = 0; req_schp->sglist_len = 0; srp->res_used = 0; /* Called without mutex lock to avoid deadlock */ sfp->res_in_use = 0; } static Sg_request * sg_get_rq_mark(Sg_fd * sfp, int pack_id, bool *busy) { Sg_request *resp; unsigned long iflags; *busy = false; write_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(resp, &sfp->rq_list, entry) { /* look for requests that are not SG_IO owned */ if ((!resp->sg_io_owned) && ((-1 == pack_id) || (resp->header.pack_id == pack_id))) { switch (resp->done) { case 0: /* request active */ *busy = true; break; case 1: /* request done; response ready to return */ resp->done = 2; /* guard against other readers */ write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return resp; case 2: /* response already being returned */ break; } } } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return NULL; } /* always adds to end of list */ static Sg_request * sg_add_request(Sg_fd * sfp) { int k; unsigned long iflags; Sg_request *rp = sfp->req_arr; write_lock_irqsave(&sfp->rq_list_lock, iflags); if (!list_empty(&sfp->rq_list)) { if (!sfp->cmd_q) goto out_unlock; for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) { if (!rp->parentfp) break; } if (k >= SG_MAX_QUEUE) goto out_unlock; } memset(rp, 0, sizeof (Sg_request)); rp->parentfp = sfp; rp->header.duration = jiffies_to_msecs(jiffies); list_add_tail(&rp->entry, &sfp->rq_list); write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return rp; out_unlock: write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return NULL; } /* Return of 1 for found; 0 for not found */ static int sg_remove_request(Sg_fd * sfp, Sg_request * srp) { unsigned long iflags; int res = 0; if (!sfp || !srp || list_empty(&sfp->rq_list)) return res; write_lock_irqsave(&sfp->rq_list_lock, iflags); if (!list_empty(&srp->entry)) { list_del(&srp->entry); srp->parentfp = NULL; res = 1; } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); /* * If the device is detaching, wakeup any readers in case we just * removed the last response, which would leave nothing for them to * return other than -ENODEV. */ if (unlikely(atomic_read(&sfp->parentdp->detaching))) wake_up_interruptible_all(&sfp->read_wait); return res; } static Sg_fd * sg_add_sfp(Sg_device * sdp) { Sg_fd *sfp; unsigned long iflags; int bufflen; sfp = kzalloc_obj(*sfp, GFP_ATOMIC | __GFP_NOWARN); if (!sfp) return ERR_PTR(-ENOMEM); init_waitqueue_head(&sfp->read_wait); rwlock_init(&sfp->rq_list_lock); INIT_LIST_HEAD(&sfp->rq_list); kref_init(&sfp->f_ref); mutex_init(&sfp->f_mutex); sfp->timeout = SG_DEFAULT_TIMEOUT; sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER; sfp->force_packid = SG_DEF_FORCE_PACK_ID; sfp->cmd_q = SG_DEF_COMMAND_Q; sfp->keep_orphan = SG_DEF_KEEP_ORPHAN; sfp->parentdp = sdp; write_lock_irqsave(&sdp->sfd_lock, iflags); if (atomic_read(&sdp->detaching)) { write_unlock_irqrestore(&sdp->sfd_lock, iflags); kfree(sfp); return ERR_PTR(-ENODEV); } list_add_tail(&sfp->sfd_siblings, &sdp->sfds); write_unlock_irqrestore(&sdp->sfd_lock, iflags); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_add_sfp: sfp=0x%p\n", sfp)); bufflen = min_t(int, def_reserved_size, max_sectors_bytes(sdp->device->request_queue)); sg_build_reserve(sfp, bufflen); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_add_sfp: bufflen=%d, k_use_sg=%d\n", sfp->reserve.bufflen, sfp->reserve.k_use_sg)); kref_get(&sdp->d_ref); __module_get(THIS_MODULE); return sfp; } static void sg_remove_sfp_usercontext(struct work_struct *work) { struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work); struct sg_device *sdp = sfp->parentdp; struct scsi_device *device = sdp->device; Sg_request *srp; unsigned long iflags; /* Cleanup any responses which were never read(). */ write_lock_irqsave(&sfp->rq_list_lock, iflags); while (!list_empty(&sfp->rq_list)) { srp = list_first_entry(&sfp->rq_list, Sg_request, entry); list_del(&srp->entry); write_unlock_irqrestore(&sfp->rq_list_lock, iflags); sg_finish_rem_req(srp); /* * sg_rq_end_io() uses srp->parentfp. Hence, only clear * srp->parentfp after blk_mq_free_request() has been called. */ srp->parentfp = NULL; write_lock_irqsave(&sfp->rq_list_lock, iflags); } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (sfp->reserve.bufflen > 0) { SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp, "sg_remove_sfp: bufflen=%d, k_use_sg=%d\n", (int) sfp->reserve.bufflen, (int) sfp->reserve.k_use_sg)); sg_remove_scat(sfp, &sfp->reserve); } SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp, "sg_remove_sfp: sfp=0x%p\n", sfp)); kfree(sfp); kref_put(&sdp->d_ref, sg_device_destroy); scsi_device_put(device); module_put(THIS_MODULE); } static void sg_remove_sfp(struct kref *kref) { struct sg_fd *sfp = container_of(kref, struct sg_fd, f_ref); struct sg_device *sdp = sfp->parentdp; unsigned long iflags; write_lock_irqsave(&sdp->sfd_lock, iflags); list_del(&sfp->sfd_siblings); write_unlock_irqrestore(&sdp->sfd_lock, iflags); INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext); schedule_work(&sfp->ew.work); } #ifdef CONFIG_SCSI_PROC_FS static int sg_idr_max_id(int id, void *p, void *data) { int *k = data; if (*k < id) *k = id; return 0; } static int sg_last_dev(void) { int k = -1; unsigned long iflags; read_lock_irqsave(&sg_index_lock, iflags); idr_for_each(&sg_index_idr, sg_idr_max_id, &k); read_unlock_irqrestore(&sg_index_lock, iflags); return k + 1; /* origin 1 */ } #endif /* must be called with sg_index_lock held */ static Sg_device *sg_lookup_dev(int dev) { return idr_find(&sg_index_idr, dev); } static Sg_device * sg_get_dev(int dev) { struct sg_device *sdp; unsigned long flags; read_lock_irqsave(&sg_index_lock, flags); sdp = sg_lookup_dev(dev); if (!sdp) sdp = ERR_PTR(-ENXIO); else if (atomic_read(&sdp->detaching)) { /* If sdp->detaching, then the refcount may already be 0, in * which case it would be a bug to do kref_get(). */ sdp = ERR_PTR(-ENODEV); } else kref_get(&sdp->d_ref); read_unlock_irqrestore(&sg_index_lock, flags); return sdp; } #ifdef CONFIG_SCSI_PROC_FS static int sg_proc_seq_show_int(struct seq_file *s, void *v); static int sg_proc_single_open_adio(struct inode *inode, struct file *file); static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off); static const struct proc_ops adio_proc_ops = { .proc_open = sg_proc_single_open_adio, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_write = sg_proc_write_adio, .proc_release = single_release, }; static int sg_proc_single_open_dressz(struct inode *inode, struct file *file); static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off); static const struct proc_ops dressz_proc_ops = { .proc_open = sg_proc_single_open_dressz, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_write = sg_proc_write_dressz, .proc_release = single_release, }; static int sg_proc_seq_show_version(struct seq_file *s, void *v); static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v); static int sg_proc_seq_show_dev(struct seq_file *s, void *v); static void * dev_seq_start(struct seq_file *s, loff_t *pos); static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos); static void dev_seq_stop(struct seq_file *s, void *v); static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = sg_proc_seq_show_dev, }; static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v); static const struct seq_operations devstrs_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = sg_proc_seq_show_devstrs, }; static int sg_proc_seq_show_debug(struct seq_file *s, void *v); static const struct seq_operations debug_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = sg_proc_seq_show_debug, }; static int sg_proc_init(void) { struct proc_dir_entry *p; p = proc_mkdir("scsi/sg", NULL); if (!p) return 1; proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_proc_ops); proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops); proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_proc_ops); proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr); proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops); proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops); proc_create_single("version", S_IRUGO, p, sg_proc_seq_show_version); return 0; } static int sg_proc_seq_show_int(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *((int *)s->private)); return 0; } static int sg_proc_single_open_adio(struct inode *inode, struct file *file) { return single_open(file, sg_proc_seq_show_int, &sg_allow_dio); } static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off) { int err; unsigned long num; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; err = kstrtoul_from_user(buffer, count, 0, &num); if (err) return err; sg_allow_dio = num ? 1 : 0; return count; } static int sg_proc_single_open_dressz(struct inode *inode, struct file *file) { return single_open(file, sg_proc_seq_show_int, &def_reserved_size); } static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off) { int err; unsigned long k = ULONG_MAX; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; err = kstrtoul_from_user(buffer, count, 0, &k); if (err) return err; if (k <= 1048576) { /* limit "big buff" to 1 MB */ def_reserved_size = k; return count; } return -ERANGE; } static int sg_proc_seq_show_version(struct seq_file *s, void *v) { seq_printf(s, "%d\t%s [%s]\n", sg_version_num, SG_VERSION_STR, sg_version_date); return 0; } static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v) { seq_puts(s, "host\tchan\tid\tlun\ttype\topens\tqdepth\tbusy\tonline\n"); return 0; } struct sg_proc_deviter { loff_t index; size_t max; }; static void * dev_seq_start(struct seq_file *s, loff_t *pos) { struct sg_proc_deviter * it = kmalloc_obj(*it); s->private = it; if (! it) return NULL; it->index = *pos; it->max = sg_last_dev(); if (it->index >= it->max) return NULL; return it; } static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct sg_proc_deviter * it = s->private; *pos = ++it->index; return (it->index < it->max) ? it : NULL; } static void dev_seq_stop(struct seq_file *s, void *v) { kfree(s->private); } static int sg_proc_seq_show_dev(struct seq_file *s, void *v) { struct sg_proc_deviter * it = (struct sg_proc_deviter *) v; Sg_device *sdp; struct scsi_device *scsidp; unsigned long iflags; read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; if ((NULL == sdp) || (NULL == sdp->device) || (atomic_read(&sdp->detaching))) seq_puts(s, "-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n"); else { scsidp = sdp->device; seq_printf(s, "%d\t%d\t%d\t%llu\t%d\t%d\t%d\t%d\t%d\n", scsidp->host->host_no, scsidp->channel, scsidp->id, scsidp->lun, (int) scsidp->type, 1, (int) scsidp->queue_depth, (int) scsi_device_busy(scsidp), (int) scsi_device_online(scsidp)); } read_unlock_irqrestore(&sg_index_lock, iflags); return 0; } static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v) { struct sg_proc_deviter * it = (struct sg_proc_deviter *) v; Sg_device *sdp; struct scsi_device *scsidp; unsigned long iflags; read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; scsidp = sdp ? sdp->device : NULL; if (sdp && scsidp && (!atomic_read(&sdp->detaching))) seq_printf(s, "%8.8s\t%16.16s\t%4.4s\n", scsidp->vendor, scsidp->model, scsidp->rev); else seq_puts(s, "<no active device>\n"); read_unlock_irqrestore(&sg_index_lock, iflags); return 0; } /* must be called while holding sg_index_lock */ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) { int k, new_interface, blen, usg; Sg_request *srp; Sg_fd *fp; const sg_io_hdr_t *hp; const char * cp; unsigned int ms; unsigned int duration; k = 0; list_for_each_entry(fp, &sdp->sfds, sfd_siblings) { k++; read_lock(&fp->rq_list_lock); /* irqs already disabled */ seq_printf(s, " FD(%d): timeout=%dms bufflen=%d " "(res)sgat=%d low_dma=%d\n", k, jiffies_to_msecs(fp->timeout), fp->reserve.bufflen, (int) fp->reserve.k_use_sg, 0); seq_printf(s, " cmd_q=%d f_packid=%d k_orphan=%d closed=0\n", (int) fp->cmd_q, (int) fp->force_packid, (int) fp->keep_orphan); list_for_each_entry(srp, &fp->rq_list, entry) { hp = &srp->header; new_interface = (hp->interface_id == '\0') ? 0 : 1; if (srp->res_used) { if (new_interface && (SG_FLAG_MMAP_IO & hp->flags)) cp = " mmap>> "; else cp = " rb>> "; } else { if (SG_INFO_DIRECT_IO_MASK & hp->info) cp = " dio>> "; else cp = " "; } seq_puts(s, cp); blen = srp->data.bufflen; usg = srp->data.k_use_sg; seq_puts(s, srp->done ? ((1 == srp->done) ? "rcv:" : "fin:") : "act:"); seq_printf(s, " id=%d blen=%d", srp->header.pack_id, blen); if (srp->done) seq_printf(s, " dur=%u", hp->duration); else { ms = jiffies_to_msecs(jiffies); duration = READ_ONCE(hp->duration); if (duration) duration = (ms > duration ? ms - duration : 0); seq_printf(s, " t_o/elap=%u/%u", (new_interface ? hp->timeout : jiffies_to_msecs(fp->timeout)), duration); } seq_printf(s, "ms sgat=%d op=0x%02x\n", usg, (int) srp->data.cmd_opcode); } if (list_empty(&fp->rq_list)) seq_puts(s, " No requests active\n"); read_unlock(&fp->rq_list_lock); } } static int sg_proc_seq_show_debug(struct seq_file *s, void *v) { struct sg_proc_deviter * it = (struct sg_proc_deviter *) v; Sg_device *sdp; unsigned long iflags; if (it && (0 == it->index)) seq_printf(s, "max_active_device=%d def_reserved_size=%d\n", (int)it->max, def_reserved_size); read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; if (NULL == sdp) goto skip; read_lock(&sdp->sfd_lock); if (!list_empty(&sdp->sfds)) { seq_printf(s, " >>> device=%s ", sdp->name); if (atomic_read(&sdp->detaching)) seq_puts(s, "detaching pending close "); else if (sdp->device) { struct scsi_device *scsidp = sdp->device; seq_printf(s, "%d:%d:%d:%llu em=%d", scsidp->host->host_no, scsidp->channel, scsidp->id, scsidp->lun, scsidp->host->hostt->emulated); } seq_printf(s, " sg_tablesize=%d excl=%d open_cnt=%d\n", sdp->sg_tablesize, sdp->exclude, sdp->open_cnt); sg_proc_debug_helper(s, sdp); } read_unlock(&sdp->sfd_lock); skip: read_unlock_irqrestore(&sg_index_lock, iflags); return 0; } #endif /* CONFIG_SCSI_PROC_FS */ module_init(init_sg); module_exit(exit_sg); |
| 109 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* user-type.h: User-defined key type * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _KEYS_USER_TYPE_H #define _KEYS_USER_TYPE_H #include <linux/key.h> #include <linux/rcupdate.h> #ifdef CONFIG_KEYS /*****************************************************************************/ /* * the payload for a key of type "user" or "logon" * - once filled in and attached to a key: * - the payload struct is invariant may not be changed, only replaced * - the payload must be read with RCU procedures or with the key semaphore * held * - the payload may only be replaced with the key semaphore write-locked * - the key's data length is the size of the actual data, not including the * payload wrapper */ struct user_key_payload { struct rcu_head rcu; /* RCU destructor */ unsigned short datalen; /* length of this data */ char data[] __aligned(__alignof__(u64)); /* actual data */ }; extern struct key_type key_type_user; extern struct key_type key_type_logon; struct key_preparsed_payload; extern int user_preparse(struct key_preparsed_payload *prep); extern void user_free_preparse(struct key_preparsed_payload *prep); extern int user_update(struct key *key, struct key_preparsed_payload *prep); extern void user_revoke(struct key *key); extern void user_destroy(struct key *key); extern void user_describe(const struct key *user, struct seq_file *m); extern long user_read(const struct key *key, char *buffer, size_t buflen); static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key) { return (struct user_key_payload *)dereference_key_rcu(key); } static inline struct user_key_payload *user_key_payload_locked(const struct key *key) { return (struct user_key_payload *)dereference_key_locked((struct key *)key); } #endif /* CONFIG_KEYS */ #endif /* _KEYS_USER_TYPE_H */ |
| 5 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NVM Express device driver tracepoints * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH */ #undef TRACE_SYSTEM #define TRACE_SYSTEM nvme #if !defined(_TRACE_NVME_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NVME_H #include <linux/nvme.h> #include <linux/tracepoint.h> #include <linux/trace_seq.h> #include "nvme.h" const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode, u8 *cdw10); const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode, u8 *cdw10); const char *nvme_trace_parse_fabrics_cmd(struct trace_seq *p, u8 fctype, u8 *spc); #define parse_nvme_cmd(qid, opcode, fctype, cdw10) \ ((opcode) == nvme_fabrics_command ? \ nvme_trace_parse_fabrics_cmd(p, fctype, cdw10) : \ ((qid) ? \ nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : \ nvme_trace_parse_admin_cmd(p, opcode, cdw10))) const char *nvme_trace_disk_name(struct trace_seq *p, char *name); #define __print_disk_name(name) \ nvme_trace_disk_name(p, name) #ifndef TRACE_HEADER_MULTI_READ static inline void __assign_disk_name(char *name, struct gendisk *disk) { if (disk) memcpy(name, disk->disk_name, DISK_NAME_LEN); else memset(name, 0, DISK_NAME_LEN); } #endif TRACE_EVENT(nvme_setup_cmd, TP_PROTO(struct request *req, struct nvme_command *cmd), TP_ARGS(req, cmd), TP_STRUCT__entry( __array(char, disk, DISK_NAME_LEN) __field(int, ctrl_id) __field(int, qid) __field(u8, opcode) __field(u8, flags) __field(u8, fctype) __field(u16, cid) __field(u32, nsid) __field(bool, metadata) __array(u8, cdw10, 24) ), TP_fast_assign( __entry->ctrl_id = nvme_req(req)->ctrl->instance; __entry->qid = nvme_req_qid(req); __entry->opcode = cmd->common.opcode; __entry->flags = cmd->common.flags; __entry->cid = cmd->common.command_id; __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = !!blk_integrity_rq(req); __entry->fctype = cmd->fabrics.fctype; __assign_disk_name(__entry->disk, req->q->disk); memcpy(__entry->cdw10, &cmd->common.cdws, sizeof(__entry->cdw10)); ), TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%x, cmd=(%s %s)", __entry->ctrl_id, __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->nsid, __entry->flags, __entry->metadata, show_opcode_name(__entry->qid, __entry->opcode, __entry->fctype), parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->fctype, __entry->cdw10)) ); TRACE_EVENT(nvme_complete_rq, TP_PROTO(struct request *req), TP_ARGS(req), TP_STRUCT__entry( __array(char, disk, DISK_NAME_LEN) __field(int, ctrl_id) __field(int, qid) __field(int, cid) __field(u64, result) __field(u8, retries) __field(u8, flags) __field(u16, status) ), TP_fast_assign( __entry->ctrl_id = nvme_req(req)->ctrl->instance; __entry->qid = nvme_req_qid(req); __entry->cid = nvme_req(req)->cmd->common.command_id; __entry->result = le64_to_cpu(nvme_req(req)->result.u64); __entry->retries = nvme_req(req)->retries; __entry->flags = nvme_req(req)->flags; __entry->status = nvme_req(req)->status; __assign_disk_name(__entry->disk, req->q->disk); ), TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%#llx, retries=%u, flags=0x%x, status=%#x", __entry->ctrl_id, __print_disk_name(__entry->disk), __entry->qid, __entry->cid, __entry->result, __entry->retries, __entry->flags, __entry->status) ); #define aer_name(aer) { aer, #aer } TRACE_EVENT(nvme_async_event, TP_PROTO(struct nvme_ctrl *ctrl, u32 result), TP_ARGS(ctrl, result), TP_STRUCT__entry( __field(int, ctrl_id) __field(u32, result) ), TP_fast_assign( __entry->ctrl_id = ctrl->instance; __entry->result = result; ), TP_printk("nvme%d: NVME_AEN=%#08x [%s]", __entry->ctrl_id, __entry->result, __print_symbolic(__entry->result & 0x7, aer_name(NVME_AER_ERROR), aer_name(NVME_AER_SMART), aer_name(NVME_AER_NOTICE), aer_name(NVME_AER_CSS), aer_name(NVME_AER_VS)) ) ); #undef aer_name TRACE_EVENT(nvme_sq, TP_PROTO(struct request *req, __le16 sq_head, int sq_tail), TP_ARGS(req, sq_head, sq_tail), TP_STRUCT__entry( __field(int, ctrl_id) __array(char, disk, DISK_NAME_LEN) __field(int, qid) __field(u16, sq_head) __field(u16, sq_tail) ), TP_fast_assign( __entry->ctrl_id = nvme_req(req)->ctrl->instance; __assign_disk_name(__entry->disk, req->q->disk); __entry->qid = nvme_req_qid(req); __entry->sq_head = le16_to_cpu(sq_head); __entry->sq_tail = sq_tail; ), TP_printk("nvme%d: %sqid=%d, head=%u, tail=%u", __entry->ctrl_id, __print_disk_name(__entry->disk), __entry->qid, __entry->sq_head, __entry->sq_tail ) ); #endif /* _TRACE_NVME_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace /* This part must be outside protection */ #include <trace/define_trace.h> |
| 22 22 80 3 3 74 72 63 49 52 22 21 22 22 22 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/atari.c * * Code extracted from drivers/block/genhd.c * * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King */ #include <linux/ctype.h> #include "check.h" #include "atari.h" /* ++guenther: this should be settable by the user ("make config")?. */ #define ICD_PARTS /* check if a partition entry looks valid -- Atari format is assumed if at least one of the primary entries is ok this way */ #define VALID_PARTITION(pi,hdsiz) \ (((pi)->flg & 1) && \ isalnum((pi)->id[0]) && isalnum((pi)->id[1]) && isalnum((pi)->id[2]) && \ be32_to_cpu((pi)->st) <= (hdsiz) && \ be32_to_cpu((pi)->st) + be32_to_cpu((pi)->siz) <= (hdsiz)) static inline int OK_id(char *s) { return memcmp (s, "GEM", 3) == 0 || memcmp (s, "BGM", 3) == 0 || memcmp (s, "LNX", 3) == 0 || memcmp (s, "SWP", 3) == 0 || memcmp (s, "RAW", 3) == 0 ; } int atari_partition(struct parsed_partitions *state) { Sector sect; struct rootsector *rs; struct partition_info *pi; u32 extensect; u32 hd_size; int slot; #ifdef ICD_PARTS int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */ #endif /* * ATARI partition scheme supports 512 lba only. If this is not * the case, bail early to avoid miscalculating hd_size. */ if (queue_logical_block_size(state->disk->queue) != 512) return 0; rs = read_part_sector(state, 0, §); if (!rs) return -1; /* Verify this is an Atari rootsector: */ hd_size = get_capacity(state->disk); if (!VALID_PARTITION(&rs->part[0], hd_size) && !VALID_PARTITION(&rs->part[1], hd_size) && !VALID_PARTITION(&rs->part[2], hd_size) && !VALID_PARTITION(&rs->part[3], hd_size)) { /* * if there's no valid primary partition, assume that no Atari * format partition table (there's no reliable magic or the like * :-() */ put_dev_sector(sect); return 0; } pi = &rs->part[0]; seq_buf_puts(&state->pp_buf, " AHDI"); for (slot = 1; pi < &rs->part[4] && slot < state->limit; slot++, pi++) { struct rootsector *xrs; Sector sect2; ulong partsect; if ( !(pi->flg & 1) ) continue; /* active partition */ if (memcmp (pi->id, "XGM", 3) != 0) { /* we don't care about other id's */ put_partition (state, slot, be32_to_cpu(pi->st), be32_to_cpu(pi->siz)); continue; } /* extension partition */ #ifdef ICD_PARTS part_fmt = 1; #endif seq_buf_puts(&state->pp_buf, " XGM<"); partsect = extensect = be32_to_cpu(pi->st); while (1) { xrs = read_part_sector(state, partsect, §2); if (!xrs) { printk (" block %ld read failed\n", partsect); put_dev_sector(sect); return -1; } /* ++roman: sanity check: bit 0 of flg field must be set */ if (!(xrs->part[0].flg & 1)) { printk( "\nFirst sub-partition in extended partition is not valid!\n" ); put_dev_sector(sect2); break; } put_partition(state, slot, partsect + be32_to_cpu(xrs->part[0].st), be32_to_cpu(xrs->part[0].siz)); if (!(xrs->part[1].flg & 1)) { /* end of linked partition list */ put_dev_sector(sect2); break; } if (memcmp( xrs->part[1].id, "XGM", 3 ) != 0) { printk("\nID of extended partition is not XGM!\n"); put_dev_sector(sect2); break; } partsect = be32_to_cpu(xrs->part[1].st) + extensect; put_dev_sector(sect2); if (++slot == state->limit) { printk( "\nMaximum number of partitions reached!\n" ); break; } } seq_buf_puts(&state->pp_buf, " >"); } #ifdef ICD_PARTS if ( part_fmt!=1 ) { /* no extended partitions -> test ICD-format */ pi = &rs->icdpart[0]; /* sanity check: no ICD format if first partition invalid */ if (OK_id(pi->id)) { seq_buf_puts(&state->pp_buf, " ICD<"); for (; pi < &rs->icdpart[8] && slot < state->limit; slot++, pi++) { /* accept only GEM,BGM,RAW,LNX,SWP partitions */ if (!((pi->flg & 1) && OK_id(pi->id))) continue; put_partition (state, slot, be32_to_cpu(pi->st), be32_to_cpu(pi->siz)); } seq_buf_puts(&state->pp_buf, " >"); } } #endif put_dev_sector(sect); seq_buf_puts(&state->pp_buf, "\n"); return 1; } |
| 43 167 51 6 1 7 27 27 176 33 48 61 57 5 27 4 18 2 32 108 13 215 160 156 76 215 45 28 15 206 177 52 205 62 36 124 18 73 37 29 110 78 31 2 2 30 8 31 31 45 69 110 28 123 18 42 43 18 72 10 214 32 94 43 186 128 18 106 72 60 13 5 2 67 87 19 192 24 5 18 18 18 16 2 1 11 11 6 2 3 3 1 4 4 12 2 5 5 7 3 1 9 1 1 2 2 2 16 5 7 1 1 1 2 48 3 45 41 5 38 8 24 20 30 5 30 4 33 17 16 27 4 29 2 10 21 30 1 30 1 29 2 27 4 27 4 27 3 28 3 29 2 21 10 29 2 33 48 1 46 32 31 1 18 10 8 18 4 14 18 12 2 4 4 2 6 18 18 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_netem.c Network emulator * * Many of the algorithms and ideas for this came from * NIST Net which is not copyrighted. * * Authors: Stephen Hemminger <shemminger@osdl.org> * Catalin(ux aka Dino) BOIE <catab at umbrella dot ro> */ #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/prandom.h> #include <linux/rtnetlink.h> #include <linux/reciprocal_div.h> #include <linux/rbtree.h> #include <net/gso.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> /* Network Emulation Queuing algorithm. ==================================== Sources: [1] Mark Carson, Darrin Santay, "NIST Net - A Linux-based Network Emulation Tool [2] Luigi Rizzo, DummyNet for FreeBSD ---------------------------------------------------------------- This started out as a simple way to delay outgoing packets to test TCP but has grown to include most of the functionality of a full blown network emulator like NISTnet. It can delay packets and add random jitter (and correlation). The random distribution can be loaded from a table as well to provide normal, Pareto, or experimental curves. Packet loss, duplication, and reordering can also be emulated. This qdisc does not do classification that can be handled in layering other disciplines. It does not need to do bandwidth control either since that can be handled by using token bucket or other rate control. Correlated Loss Generator models Added generation of correlated loss according to the "Gilbert-Elliot" model, a 4-state markov model. References: [1] NetemCLG Home http://netgroup.uniroma2.it/NetemCLG [2] S. Salsano, F. Ludovici, A. Ordine, "Definition of a general and intuitive loss model for packet networks and its implementation in the Netem module in the Linux kernel", available in [1] Authors: Stefano Salsano <stefano.salsano at uniroma2.it Fabio Ludovici <fabio.ludovici at yahoo.it> */ struct disttable { u32 size; s16 table[] __counted_by(size); }; /* Loss models */ enum { CLG_RANDOM, CLG_4_STATES, CLG_GILB_ELL, }; /* States in GE model */ enum { GOOD_STATE = 1, BAD_STATE, }; /* States in 4 state model */ enum { TX_IN_GAP_PERIOD = 1, TX_IN_BURST_PERIOD, LOST_IN_GAP_PERIOD, LOST_IN_BURST_PERIOD, }; struct netem_sched_data { /* Cacheline 0: tfifo state and per-packet enqueue/dequeue scalars. */ struct rb_root t_root; struct sk_buff *t_head; struct sk_buff *t_tail; u32 t_len; u32 counter; s64 latency; s64 jitter; u64 rate; u32 gap; u32 loss; /* Cacheline 1: zero-check scalars and correlation states. */ u32 duplicate; u32 reorder; u32 corrupt; u32 ecn; struct crndstate { u32 last; u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; u8 loss_model; /* Cacheline 2: PRNG, distribution tables, slot dequeue state etc. */ struct prng { u64 seed; struct rnd_state prng_state; } prng; struct disttable *delay_dist; struct slotstate { u64 slot_next; s32 packets_left; s32 bytes_left; } slot; struct disttable *slot_dist; struct Qdisc *qdisc; /* * Warm: rate-shaping parameters (only read when rate != 0) and * configuration-only fields. The fast path reads sch->limit, not * q->limit. */ s32 packet_overhead; u32 cell_size; struct reciprocal_value cell_size_reciprocal; s32 cell_overhead; u32 limit; /* Correlated Loss Generation models */ struct clgstate { /* 4-states and Gilbert-Elliot models */ u32 a1; /* p13 for 4-states or p for GE */ u32 a2; /* p31 for 4-states or r for GE */ u32 a3; /* p32 for 4-states or h for GE */ u32 a4; /* p14 for 4-states or 1-k for GE */ u32 a5; /* p23 used only in 4-states */ /* state of the Markov chain */ u8 state; } clg; /* Impairment counters */ u64 delayed; u64 dropped; u64 corrupted; u64 duplicated; u64 ecn_marked; u64 reordered; u64 allocation_errors; /* Cold tail: slot reschedule config and the watchdog timer. */ struct tc_netem_slot slot_config; struct qdisc_watchdog watchdog; }; /* Time stamp put into socket buffer control block * Only valid when skbs are in our internal t(ime)fifo queue. * * As skb->rbnode uses same storage than skb->next, skb->prev and skb->tstamp, * and skb->next & skb->prev are scratch space for a qdisc, * we save skb->tstamp value in skb->cb[] before destroying it. */ struct netem_skb_cb { u64 time_to_send; }; static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ qdisc_cb_private_validate(skb, sizeof(struct netem_skb_cb)); return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data; } /* init_crandom - initialize correlated random number generator * Use entropy source for initial seed. */ static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; state->last = get_random_u32(); } /* get_crandom - correlated random number generator * Next number depends on last value. * rho is scaled to avoid floating point. */ static u32 get_crandom(struct crndstate *state, struct prng *p) { u64 value, rho; unsigned long answer; struct rnd_state *s = &p->prng_state; if (!state || state->rho == 0) /* no correlation */ return prandom_u32_state(s); value = prandom_u32_state(s); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; return answer; } /* loss_4state - 4-state model loss generator * Generates losses according to the 4-state Markov chain adopted in * the GI (General and Intuitive) loss model. */ static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; u32 rnd = prandom_u32_state(&q->prng.prng_state); /* * Makes a comparison between rnd and the transition * probabilities outgoing from the current state, then decides the * next state and if the next packet has to be transmitted or lost. * The four states correspond to: * TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period * LOST_IN_GAP_PERIOD => isolated losses within a gap period * LOST_IN_BURST_PERIOD => lost packets within a burst period * TX_IN_BURST_PERIOD => successfully transmitted packets within a burst period */ switch (clg->state) { case TX_IN_GAP_PERIOD: if (rnd < clg->a4) { clg->state = LOST_IN_GAP_PERIOD; return true; } else if (rnd < clg->a1 + clg->a4) { clg->state = LOST_IN_BURST_PERIOD; return true; } else { clg->state = TX_IN_GAP_PERIOD; } break; case TX_IN_BURST_PERIOD: if (rnd < clg->a5) { clg->state = LOST_IN_BURST_PERIOD; return true; } else { clg->state = TX_IN_BURST_PERIOD; } break; case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; else if (rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; } else { clg->state = LOST_IN_BURST_PERIOD; return true; } break; case LOST_IN_GAP_PERIOD: clg->state = TX_IN_GAP_PERIOD; break; } return false; } /* loss_gilb_ell - Gilbert-Elliot model loss generator * Generates losses according to the Gilbert-Elliot loss model or * its special cases (Gilbert or Simple Gilbert) * * Makes a comparison between random number and the transition * probabilities outgoing from the current state, then decides the * next state. A second random number is extracted and the comparison * with the loss probability of the current state decides if the next * packet will be transmitted or lost. */ static bool loss_gilb_ell(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; struct rnd_state *s = &q->prng.prng_state; switch (clg->state) { case GOOD_STATE: if (prandom_u32_state(s) < clg->a1) clg->state = BAD_STATE; if (prandom_u32_state(s) < clg->a4) return true; break; case BAD_STATE: if (prandom_u32_state(s) < clg->a2) clg->state = GOOD_STATE; if (prandom_u32_state(s) > clg->a3) return true; } return false; } static bool loss_event(struct netem_sched_data *q) { switch (q->loss_model) { case CLG_RANDOM: /* Random packet drop 0 => none, ~0 => all */ return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng); case CLG_4_STATES: /* 4state loss model algorithm (used also for GI model) * Extracts a value from the markov 4 state loss generator, * if it is 1 drops a packet and if needed writes the event in * the kernel logs */ return loss_4state(q); case CLG_GILB_ELL: /* Gilbert-Elliot loss model algorithm * Extracts a value from the Gilbert-Elliot loss generator, * if it is 1 drops a packet and if needed writes the event in * the kernel logs */ return loss_gilb_ell(q); } return false; /* not reached */ } /* tabledist - return a pseudo-randomly distributed value with mean mu and * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. */ static s64 tabledist(s64 mu, s32 sigma, struct crndstate *state, struct prng *prng, const struct disttable *dist) { s64 x; long t; u32 rnd; if (sigma == 0) return mu; rnd = get_crandom(state, prng); /* default uniform distribution */ if (dist == NULL) return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; if (x >= 0) x += NETEM_DIST_SCALE/2; else x -= NETEM_DIST_SCALE/2; return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu; } static u64 packet_time_ns(u64 len, const struct netem_sched_data *q) { len += q->packet_overhead; if (q->cell_size) { u32 cells = reciprocal_divide(len, q->cell_size_reciprocal); if (len > cells * q->cell_size) /* extra cell needed for remainder */ cells++; len = cells * (q->cell_size + q->cell_overhead); } return div64_u64(len * NSEC_PER_SEC, q->rate); } static void tfifo_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct rb_node *p = rb_first(&q->t_root); while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } rtnl_kfree_skbs(q->t_head, q->t_tail); q->t_head = NULL; q->t_tail = NULL; q->t_len = 0; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); u64 tnext = netem_skb_cb(nskb)->time_to_send; if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) { if (q->t_tail) q->t_tail->next = nskb; else q->t_head = nskb; q->t_tail = nskb; } else { struct rb_node **p = &q->t_root.rb_node, *parent = NULL; while (*p) { struct sk_buff *skb; parent = *p; skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&nskb->rbnode, parent, p); rb_insert_color(&nskb->rbnode, &q->t_root); } q->t_len++; qdisc_qlen_inc(sch); } /* netem can't properly corrupt a megapacket (like we get from GSO), so instead * when we statistically choose to corrupt one, we instead segment it, returning * the first packet to be corrupted, and re-enqueue the remaining frames */ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct sk_buff *segs; netdev_features_t features = netif_skb_features(skb); qdisc_skb_cb(skb)->pkt_segs = 1; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { qdisc_drop(skb, sch, to_free); return NULL; } consume_skb(skb); return segs; } /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. * NET_XMIT_DROP: queue length didn't change. * NET_XMIT_SUCCESS: one skb was queued. */ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; /* Random duplication */ if (q->duplicate && skb->tc_depth == 0 && q->duplicate >= get_crandom(&q->dup_cor, &q->prng)) { ++count; WRITE_ONCE(q->duplicated, q->duplicated + 1); } /* Drop packet? */ if (loss_event(q)) { if (q->ecn && INET_ECN_set_ce(skb)) { WRITE_ONCE(q->ecn_marked, q->ecn_marked + 1); } else { WRITE_ONCE(q->dropped, q->dropped + 1); --count; } } if (count == 0) { qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) */ if (q->latency || q->jitter || q->rate) skb_orphan_partial(skb); /* * If we need to duplicate packet, then clone it before * original is modified. */ if (count > 1) { skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); } /* * Randomized packet corruption. * Make copy if needed since we are modifying * If packet is going to be hardware checksummed, then * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) { if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) { WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); goto finish_segs; } segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; } skb = skb_unshare(skb, GFP_ATOMIC); if (unlikely(!skb)) { WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); qdisc_qstats_drop(sch); goto finish_segs; } if (skb_linearize(skb) || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) { WRITE_ONCE(q->allocation_errors, q->allocation_errors + 1); qdisc_drop(skb, sch, to_free); skb = NULL; goto finish_segs; } if (skb->len) { u32 offset = get_random_u32_below(skb->len); skb->data[offset] ^= 1 << get_random_u32_below(8); WRITE_ONCE(q->corrupted, q->corrupted + 1); } } if (unlikely(sch->q.qlen >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); if (skb2) __qdisc_drop(skb2, to_free); return NET_XMIT_DROP; } /* * If doing duplication then re-insert at top of the * qdisc tree, since parent queuer expects that only one * skb will be queued. */ if (skb2) { struct Qdisc *rootq = qdisc_root_bh(sch); skb2->tc_depth++; /* prevent duplicating a dup... */ rootq->enqueue(skb2, rootq, to_free); skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor, &q->prng)) { u64 now; s64 delay; delay = tabledist(q->latency, q->jitter, &q->delay_cor, &q->prng, q->delay_dist); now = ktime_get_ns(); if (q->rate) { struct netem_skb_cb *last = NULL; if (sch->q.tail) last = netem_skb_cb(sch->q.tail); if (q->t_root.rb_node) { struct sk_buff *t_skb; struct netem_skb_cb *t_last; t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || t_last->time_to_send > last->time_to_send) last = t_last; } if (q->t_tail) { struct netem_skb_cb *t_last = netem_skb_cb(q->t_tail); if (!last || t_last->time_to_send > last->time_to_send) last = t_last; } if (last) { /* * Last packet in queue is reference point (now), * calculate this time bonus and subtract * from delay. */ delay -= last->time_to_send - now; delay = max_t(s64, 0, delay); now = last->time_to_send; } delay += packet_time_ns(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; ++q->counter; if (delay) WRITE_ONCE(q->delayed, q->delayed + 1); tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front * of the queue. */ WRITE_ONCE(q->reordered, q->reordered + 1); cb->time_to_send = ktime_get_ns(); q->counter = 0; __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } finish_segs: if (skb2) __qdisc_drop(skb2, to_free); if (segs) { unsigned int len, last_len; int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); if (rc != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(rc)) qdisc_qstats_drop(sch); } else { nb++; len += last_len; } segs = skb2; } /* Parent qdiscs accounted for 1 skb of size @prev_len */ qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); } else if (!skb) { return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } /* Delay the next round with a new future slot with a * correct number of bytes and packets. */ static void get_slot_next(struct netem_sched_data *q, u64 now) { s64 next_delay; if (!q->slot_dist) next_delay = q->slot_config.min_delay + mul_u64_u32_shr(q->slot_config.max_delay - q->slot_config.min_delay, get_random_u32(), 32); else next_delay = tabledist(q->slot_config.dist_delay, (s32)(q->slot_config.dist_jitter), NULL, &q->prng, q->slot_dist); q->slot.slot_next = now + next_delay; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; } static struct sk_buff *netem_peek(struct netem_sched_data *q) { struct sk_buff *skb = skb_rb_first(&q->t_root); u64 t1, t2; if (!skb) return q->t_head; if (!q->t_head) return skb; t1 = netem_skb_cb(skb)->time_to_send; t2 = netem_skb_cb(q->t_head)->time_to_send; if (t1 < t2) return skb; return q->t_head; } static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb) { if (skb == q->t_head) { q->t_head = skb->next; if (!q->t_head) q->t_tail = NULL; } else { rb_erase(&skb->rbnode, &q->t_root); } } static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); if (skb) { deliver: qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } skb = netem_peek(q); if (skb) { u64 time_to_send; u64 now = ktime_get_ns(); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; if (q->slot.slot_next && q->slot.slot_next < time_to_send) get_slot_next(q, now); if (time_to_send <= now && q->slot.slot_next <= now) { netem_erase_head(q, skb); q->t_len--; skb->next = NULL; skb->prev = NULL; /* skb->dev shares skb->rbnode area, * we need to restore its value. */ skb->dev = qdisc_dev(sch); if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); if (q->slot.packets_left <= 0 || q->slot.bytes_left <= 0) get_slot_next(q, now); } if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); struct sk_buff *to_free = NULL; int err; err = qdisc_enqueue(skb, q->qdisc, &to_free); kfree_skb_list(to_free); if (err != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); qstats_backlog_sub(sch, pkt_len); qdisc_qlen_dec(sch); qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } qdisc_qlen_dec(sch); goto deliver; } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) { qdisc_qlen_dec(sch); goto deliver; } } qdisc_watchdog_schedule_ns(&q->watchdog, max(time_to_send, q->slot.slot_next)); } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) { qdisc_qlen_dec(sch); goto deliver; } } return NULL; } static void netem_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); } static void dist_free(struct disttable *d) { kvfree(d); } /* * Distribution data is a variable size payload containing * signed 16 bit values. */ static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); struct disttable *d; int i; if (!n || n > NETEM_DIST_MAX) return -EINVAL; d = kvmalloc_flex(*d, table, n); if (!d) return -ENOMEM; d->size = n; for (i = 0; i < n; i++) d->table[i] = data[i]; *tbl = d; return 0; } static int validate_time(const struct nlattr *attr, const char *name, struct netlink_ext_ack *extack) { if (nla_get_s64(attr) < 0) { NL_SET_ERR_MSG_ATTR_FMT(extack, attr, "negative %s", name); return -EINVAL; } return 0; } static int validate_slot(const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct tc_netem_slot *c = nla_data(attr); if (c->min_delay < 0 || c->max_delay < 0) { NL_SET_ERR_MSG_ATTR(extack, attr, "negative slot delay"); return -EINVAL; } if (c->min_delay > c->max_delay) { NL_SET_ERR_MSG_ATTR(extack, attr, "slot min delay greater than max delay"); return -EINVAL; } if (c->dist_delay < 0 || c->dist_jitter < 0) { NL_SET_ERR_MSG_ATTR(extack, attr, "negative dist delay"); return -EINVAL; } if (c->max_packets < 0 || c->max_bytes < 0) { NL_SET_ERR_MSG_ATTR(extack, attr, "negative slot limit"); return -EINVAL; } return 0; } static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_slot *c = nla_data(attr); q->slot_config = *c; if (q->slot_config.max_packets == 0) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; /* capping dist_jitter to the range acceptable by tabledist() */ q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | q->slot_config.dist_jitter) q->slot.slot_next = ktime_get_ns(); else q->slot.slot_next = 0; } static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); init_crandom(&q->delay_cor, c->delay_corr); init_crandom(&q->loss_cor, c->loss_corr); init_crandom(&q->dup_cor, c->dup_corr); } static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_reorder *r = nla_data(attr); q->reorder = r->probability; init_crandom(&q->reorder_cor, r->correlation); } static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corrupt *r = nla_data(attr); q->corrupt = r->probability; init_crandom(&q->corrupt_cor, r->correlation); } static void get_rate(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_rate *r = nla_data(attr); q->rate = r->rate; q->packet_overhead = r->packet_overhead; q->cell_size = r->cell_size; q->cell_overhead = r->cell_overhead; if (q->cell_size) q->cell_size_reciprocal = reciprocal_value(q->cell_size); else q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr, struct netlink_ext_ack *extack) { const struct nlattr *la; int rem; nla_for_each_nested(la, attr, rem) { u16 type = nla_type(la); switch (type) { case NETEM_LOSS_GI: { const struct tc_netem_gimodel *gi = nla_data(la); if (nla_len(la) < sizeof(struct tc_netem_gimodel)) { NL_SET_ERR_MSG_ATTR(extack, la, "netem: incorrect gi model size"); return -EINVAL; } q->loss_model = CLG_4_STATES; q->clg.state = TX_IN_GAP_PERIOD; q->clg.a1 = gi->p13; q->clg.a2 = gi->p31; q->clg.a3 = gi->p32; q->clg.a4 = gi->p14; q->clg.a5 = gi->p23; break; } case NETEM_LOSS_GE: { const struct tc_netem_gemodel *ge = nla_data(la); if (nla_len(la) < sizeof(struct tc_netem_gemodel)) { NL_SET_ERR_MSG_ATTR(extack, la, "netem: incorrect ge model size"); return -EINVAL; } q->loss_model = CLG_GILB_ELL; q->clg.state = GOOD_STATE; q->clg.a1 = ge->p; q->clg.a2 = ge->r; q->clg.a3 = ge->h; q->clg.a4 = ge->k1; break; } default: NL_SET_ERR_MSG_ATTR_FMT(extack, la, "netem: unknown loss type %u", type); return -EINVAL; } } return 0; } static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_CORR] = { .len = sizeof(struct tc_netem_corr) }, [TCA_NETEM_REORDER] = { .len = sizeof(struct tc_netem_reorder) }, [TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) }, [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) }, [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, const struct nla_policy *policy, int len, struct netlink_ext_ack *extack) { int nested_len = nla_len(nla) - NLA_ALIGN(len); if (nested_len < 0) { NL_SET_ERR_MSG_FMT(extack, "netem: invalid attributes len %d < %d", nla_len(nla), NLA_ALIGN(len)); return -EINVAL; } if (nested_len >= nla_attr_size(0)) return nla_parse_deprecated(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy, extack); memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } /* Parse netlink message to set options */ static int netem_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; struct disttable *delay_dist = NULL; struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; int ret; qopt = nla_data(opt); ret = parse_attr(tb, TCA_NETEM_MAX, opt, netem_policy, sizeof(*qopt), extack); if (ret < 0) return ret; if (tb[TCA_NETEM_DELAY_DIST]) { ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); if (ret) goto table_free; } if (tb[TCA_NETEM_SLOT_DIST]) { ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); if (ret) goto table_free; } if (tb[TCA_NETEM_SLOT]) { ret = validate_slot(tb[TCA_NETEM_SLOT], extack); if (ret) goto table_free; } if (tb[TCA_NETEM_LATENCY64]) { ret = validate_time(tb[TCA_NETEM_LATENCY64], "latency", extack); if (ret) goto table_free; } if (tb[TCA_NETEM_JITTER64]) { ret = validate_time(tb[TCA_NETEM_JITTER64], "jitter", extack); if (ret) goto table_free; } sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; if (tb[TCA_NETEM_LOSS]) { ret = get_loss_clg(q, tb[TCA_NETEM_LOSS], extack); if (ret) { q->loss_model = old_loss_model; q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } if (delay_dist) swap(q->delay_dist, delay_dist); if (slot_dist) swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); q->jitter = PSCHED_TICKS2NS(qopt->jitter); q->limit = qopt->limit; q->gap = qopt->gap; q->counter = 0; q->loss = qopt->loss; q->duplicate = qopt->duplicate; /* for compatibility with earlier versions. * if gap is set, need to assume 100% probability */ if (q->gap) q->reorder = ~0; if (tb[TCA_NETEM_CORR]) get_correlation(q, tb[TCA_NETEM_CORR]); if (tb[TCA_NETEM_REORDER]) get_reorder(q, tb[TCA_NETEM_REORDER]); if (tb[TCA_NETEM_CORRUPT]) get_corrupt(q, tb[TCA_NETEM_CORRUPT]); if (tb[TCA_NETEM_RATE]) get_rate(q, tb[TCA_NETEM_RATE]); if (tb[TCA_NETEM_RATE64]) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); if (tb[TCA_NETEM_LATENCY64]) q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); if (tb[TCA_NETEM_JITTER64]) q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); if (tb[TCA_NETEM_PRNG_SEED]) { q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); prandom_seed_state(&q->prng.prng_state, q->prng.seed); } unlock: sch_tree_unlock(sch); table_free: dist_free(delay_dist); dist_free(slot_dist); return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_watchdog_init(&q->watchdog, sch); if (!opt) return -EINVAL; q->loss_model = CLG_RANDOM; q->prng.seed = get_random_u64(); prandom_seed_state(&q->prng.prng_state, q->prng.seed); return netem_change(sch, opt, extack); } static void netem_destroy(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) qdisc_put(q->qdisc); dist_free(q->delay_dist); dist_free(q->slot_dist); } static int dump_loss_model(const struct netem_sched_data *q, struct sk_buff *skb) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS); if (nest == NULL) goto nla_put_failure; switch (q->loss_model) { case CLG_RANDOM: /* legacy loss model */ nla_nest_cancel(skb, nest); return 0; /* no data */ case CLG_4_STATES: { struct tc_netem_gimodel gi = { .p13 = q->clg.a1, .p31 = q->clg.a2, .p32 = q->clg.a3, .p14 = q->clg.a4, .p23 = q->clg.a5, }; if (nla_put(skb, NETEM_LOSS_GI, sizeof(gi), &gi)) goto nla_put_failure; break; } case CLG_GILB_ELL: { struct tc_netem_gemodel ge = { .p = q->clg.a1, .r = q->clg.a2, .h = q->clg.a3, .k1 = q->clg.a4, }; if (nla_put(skb, NETEM_LOSS_GE, sizeof(ge), &ge)) goto nla_put_failure; break; } } nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) { const struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *nla = (struct nlattr *) skb_tail_pointer(skb); struct tc_netem_qopt qopt; struct tc_netem_corr cor; struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; struct tc_netem_slot slot; qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency), UINT_MAX); qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter), UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; qopt.gap = q->gap; qopt.duplicate = q->duplicate; if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) goto nla_put_failure; if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) goto nla_put_failure; cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; if (nla_put(skb, TCA_NETEM_CORR, sizeof(cor), &cor)) goto nla_put_failure; reorder.probability = q->reorder; reorder.correlation = q->reorder_cor.rho; if (nla_put(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder)) goto nla_put_failure; corrupt.probability = q->corrupt; corrupt.correlation = q->corrupt_cor.rho; if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt)) goto nla_put_failure; if (q->rate >= (1ULL << 32)) { if (nla_put_u64_64bit(skb, TCA_NETEM_RATE64, q->rate, TCA_NETEM_PAD)) goto nla_put_failure; rate.rate = ~0U; } else { rate.rate = q->rate; } rate.packet_overhead = q->packet_overhead; rate.cell_size = q->cell_size; rate.cell_overhead = q->cell_overhead; if (nla_put(skb, TCA_NETEM_RATE, sizeof(rate), &rate)) goto nla_put_failure; if (q->ecn && nla_put_u32(skb, TCA_NETEM_ECN, q->ecn)) goto nla_put_failure; if (dump_loss_model(q, skb) != 0) goto nla_put_failure; if (q->slot_config.min_delay | q->slot_config.max_delay | q->slot_config.dist_jitter) { slot = q->slot_config; if (slot.max_packets == INT_MAX) slot.max_packets = 0; if (slot.max_bytes == INT_MAX) slot.max_bytes = 0; if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) goto nla_put_failure; } if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed, TCA_NETEM_PAD)) goto nla_put_failure; return nla_nest_end(skb, nla); nla_put_failure: nlmsg_trim(skb, nla); return -1; } static int netem_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct netem_sched_data *q = qdisc_priv(sch); struct tc_netem_xstats st = { .delayed = READ_ONCE(q->delayed), .dropped = READ_ONCE(q->dropped), .corrupted = READ_ONCE(q->corrupted), .duplicated = READ_ONCE(q->duplicated), .reordered = READ_ONCE(q->reordered), .ecn_marked = READ_ONCE(q->ecn_marked), .allocation_errors = READ_ONCE(q->allocation_errors), }; return gnet_stats_copy_app(d, &st, sizeof(st)); } static int netem_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct netem_sched_data *q = qdisc_priv(sch); if (cl != 1 || !q->qdisc) /* only one class */ return -ENOENT; tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; return 0; } static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); *old = qdisc_replace(sch, new, &q->qdisc); return 0; } static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg) { struct netem_sched_data *q = qdisc_priv(sch); return q->qdisc; } static unsigned long netem_find(struct Qdisc *sch, u32 classid) { return 1; } static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { if (!tc_qdisc_stats_dump(sch, 1, walker)) return; } } static const struct Qdisc_class_ops netem_class_ops = { .graft = netem_graft, .leaf = netem_leaf, .find = netem_find, .walk = netem_walk, .dump = netem_dump_class, }; static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .id = "netem", .cl_ops = &netem_class_ops, .priv_size = sizeof(struct netem_sched_data), .enqueue = netem_enqueue, .dequeue = netem_dequeue, .peek = qdisc_peek_dequeued, .init = netem_init, .reset = netem_reset, .destroy = netem_destroy, .change = netem_change, .dump = netem_dump, .dump_stats = netem_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("netem"); static int __init netem_module_init(void) { return register_qdisc(&netem_qdisc_ops); } static void __exit netem_module_exit(void) { unregister_qdisc(&netem_qdisc_ops); } module_init(netem_module_init) module_exit(netem_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Network characteristics emulator qdisc"); |
| 20 20 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/ceph/ceph_debug.h> #include <linux/types.h> #include <linux/percpu_counter.h> #include <linux/math64.h> #include <linux/ratelimit.h> #include <linux/ceph/decode.h> #include "metric.h" #include "mds_client.h" static bool metrics_disable_warned; static inline u32 ceph_subvolume_entry_payload_len(void) { return sizeof(struct ceph_subvolume_metric_entry_wire); } static inline u32 ceph_subvolume_entry_encoded_len(void) { return CEPH_ENCODING_START_BLK_LEN + ceph_subvolume_entry_payload_len(); } static inline u32 ceph_subvolume_outer_payload_len(u32 nr_subvols) { /* count is encoded as le64 (size_t on wire) to match FUSE client */ return sizeof(__le64) + nr_subvols * ceph_subvolume_entry_encoded_len(); } static inline u32 ceph_subvolume_metric_data_len(u32 nr_subvols) { return CEPH_ENCODING_START_BLK_LEN + ceph_subvolume_outer_payload_len(nr_subvols); } static inline u32 ceph_subvolume_clamp_u32(u64 val) { return val > U32_MAX ? U32_MAX : (u32)val; } static void ceph_init_subvolume_wire_entry( struct ceph_subvolume_metric_entry_wire *dst, const struct ceph_subvol_metric_snapshot *src) { dst->subvolume_id = cpu_to_le64(src->subvolume_id); dst->read_ops = cpu_to_le32(ceph_subvolume_clamp_u32(src->read_ops)); dst->write_ops = cpu_to_le32(ceph_subvolume_clamp_u32(src->write_ops)); dst->read_bytes = cpu_to_le64(src->read_bytes); dst->write_bytes = cpu_to_le64(src->write_bytes); dst->read_latency_us = cpu_to_le64(src->read_latency_us); dst->write_latency_us = cpu_to_le64(src->write_latency_us); dst->time_stamp = 0; } static int ceph_encode_subvolume_metrics(void **p, void *end, struct ceph_subvol_metric_snapshot *subvols, u32 nr_subvols) { u32 i; ceph_start_encoding(p, 1, 1, ceph_subvolume_outer_payload_len(nr_subvols)); /* count is encoded as le64 (size_t on wire) to match FUSE client */ ceph_encode_64_safe(p, end, (u64)nr_subvols, enc_err); for (i = 0; i < nr_subvols; i++) { struct ceph_subvolume_metric_entry_wire wire_entry; ceph_init_subvolume_wire_entry(&wire_entry, &subvols[i]); ceph_start_encoding(p, 1, 1, ceph_subvolume_entry_payload_len()); ceph_encode_copy_safe(p, end, &wire_entry, sizeof(wire_entry), enc_err); } return 0; enc_err: return -ERANGE; } static void ktime_to_ceph_timespec(struct ceph_timespec *ts, ktime_t val) { struct timespec64 t = ktime_to_timespec64(val); ceph_encode_timespec64(ts, &t); } static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, struct ceph_mds_session *s) { struct ceph_metric_head *head; struct ceph_metric_cap *cap; struct ceph_metric_read_latency *read; struct ceph_metric_write_latency *write; struct ceph_metric_metadata_latency *meta; struct ceph_metric_dlease *dlease; struct ceph_opened_files *files; struct ceph_pinned_icaps *icaps; struct ceph_opened_inodes *inodes; struct ceph_read_io_size *rsize; struct ceph_write_io_size *wsize; struct ceph_client_metric *m = &mdsc->metric; struct ceph_subvol_metric_snapshot *subvols = NULL; u64 nr_caps = atomic64_read(&m->total_caps); u32 header_len = sizeof(struct ceph_metric_header); struct ceph_client *cl = mdsc->fsc->client; struct ceph_msg *msg; u32 nr_subvols = 0; size_t subvol_len = 0; void *cursor; s64 sum; s32 items = 0; s32 len; /* Do not send the metrics until the MDS rank is ready */ mutex_lock(&mdsc->mutex); if (ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) != CEPH_MDS_STATE_ACTIVE) { mutex_unlock(&mdsc->mutex); return false; } mutex_unlock(&mdsc->mutex); if (ceph_subvolume_metrics_enabled(&mdsc->subvol_metrics) && test_bit(CEPHFS_FEATURE_SUBVOLUME_METRICS, &s->s_features)) { int ret; ret = ceph_subvolume_metrics_snapshot(&mdsc->subvol_metrics, &subvols, &nr_subvols, true); if (ret) { pr_warn_client(cl, "failed to snapshot subvolume metrics: %d\n", ret); /* * On error, ceph_subvolume_metrics_snapshot() guarantees * *out = NULL and *nr = 0 at function entry, so subvols * is already NULL here - no cleanup needed. */ nr_subvols = 0; subvols = NULL; } } if (nr_subvols) { /* type (le32) + ENCODE_START payload - no metric header */ subvol_len = sizeof(__le32) + ceph_subvolume_metric_data_len(nr_subvols); } len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write) + sizeof(*meta) + sizeof(*dlease) + sizeof(*files) + sizeof(*icaps) + sizeof(*inodes) + sizeof(*rsize) + sizeof(*wsize) + subvol_len; msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true); if (!msg) { pr_err_client(cl, "to mds%d, failed to allocate message\n", s->s_mds); kfree(subvols); return false; } head = msg->front.iov_base; /* encode the cap metric */ cap = (struct ceph_metric_cap *)(head + 1); cap->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO); cap->header.ver = 1; cap->header.compat = 1; cap->header.data_len = cpu_to_le32(sizeof(*cap) - header_len); cap->hit = cpu_to_le64(percpu_counter_sum(&m->i_caps_hit)); cap->mis = cpu_to_le64(percpu_counter_sum(&m->i_caps_mis)); cap->total = cpu_to_le64(nr_caps); items++; /* encode the read latency metric */ read = (struct ceph_metric_read_latency *)(cap + 1); read->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY); read->header.ver = 2; read->header.compat = 1; read->header.data_len = cpu_to_le32(sizeof(*read) - header_len); sum = m->metric[METRIC_READ].latency_sum; ktime_to_ceph_timespec(&read->lat, sum); ktime_to_ceph_timespec(&read->avg, m->metric[METRIC_READ].latency_avg); read->sq_sum = cpu_to_le64(m->metric[METRIC_READ].latency_sq_sum); read->count = cpu_to_le64(m->metric[METRIC_READ].total); items++; /* encode the write latency metric */ write = (struct ceph_metric_write_latency *)(read + 1); write->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY); write->header.ver = 2; write->header.compat = 1; write->header.data_len = cpu_to_le32(sizeof(*write) - header_len); sum = m->metric[METRIC_WRITE].latency_sum; ktime_to_ceph_timespec(&write->lat, sum); ktime_to_ceph_timespec(&write->avg, m->metric[METRIC_WRITE].latency_avg); write->sq_sum = cpu_to_le64(m->metric[METRIC_WRITE].latency_sq_sum); write->count = cpu_to_le64(m->metric[METRIC_WRITE].total); items++; /* encode the metadata latency metric */ meta = (struct ceph_metric_metadata_latency *)(write + 1); meta->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY); meta->header.ver = 2; meta->header.compat = 1; meta->header.data_len = cpu_to_le32(sizeof(*meta) - header_len); sum = m->metric[METRIC_METADATA].latency_sum; ktime_to_ceph_timespec(&meta->lat, sum); ktime_to_ceph_timespec(&meta->avg, m->metric[METRIC_METADATA].latency_avg); meta->sq_sum = cpu_to_le64(m->metric[METRIC_METADATA].latency_sq_sum); meta->count = cpu_to_le64(m->metric[METRIC_METADATA].total); items++; /* encode the dentry lease metric */ dlease = (struct ceph_metric_dlease *)(meta + 1); dlease->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_DENTRY_LEASE); dlease->header.ver = 1; dlease->header.compat = 1; dlease->header.data_len = cpu_to_le32(sizeof(*dlease) - header_len); dlease->hit = cpu_to_le64(percpu_counter_sum(&m->d_lease_hit)); dlease->mis = cpu_to_le64(percpu_counter_sum(&m->d_lease_mis)); dlease->total = cpu_to_le64(atomic64_read(&m->total_dentries)); items++; sum = percpu_counter_sum(&m->total_inodes); /* encode the opened files metric */ files = (struct ceph_opened_files *)(dlease + 1); files->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_OPENED_FILES); files->header.ver = 1; files->header.compat = 1; files->header.data_len = cpu_to_le32(sizeof(*files) - header_len); files->opened_files = cpu_to_le64(atomic64_read(&m->opened_files)); files->total = cpu_to_le64(sum); items++; /* encode the pinned icaps metric */ icaps = (struct ceph_pinned_icaps *)(files + 1); icaps->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_PINNED_ICAPS); icaps->header.ver = 1; icaps->header.compat = 1; icaps->header.data_len = cpu_to_le32(sizeof(*icaps) - header_len); icaps->pinned_icaps = cpu_to_le64(nr_caps); icaps->total = cpu_to_le64(sum); items++; /* encode the opened inodes metric */ inodes = (struct ceph_opened_inodes *)(icaps + 1); inodes->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_OPENED_INODES); inodes->header.ver = 1; inodes->header.compat = 1; inodes->header.data_len = cpu_to_le32(sizeof(*inodes) - header_len); inodes->opened_inodes = cpu_to_le64(percpu_counter_sum(&m->opened_inodes)); inodes->total = cpu_to_le64(sum); items++; /* encode the read io size metric */ rsize = (struct ceph_read_io_size *)(inodes + 1); rsize->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_IO_SIZES); rsize->header.ver = 1; rsize->header.compat = 1; rsize->header.data_len = cpu_to_le32(sizeof(*rsize) - header_len); rsize->total_ops = cpu_to_le64(m->metric[METRIC_READ].total); rsize->total_size = cpu_to_le64(m->metric[METRIC_READ].size_sum); items++; /* encode the write io size metric */ wsize = (struct ceph_write_io_size *)(rsize + 1); wsize->header.type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_IO_SIZES); wsize->header.ver = 1; wsize->header.compat = 1; wsize->header.data_len = cpu_to_le32(sizeof(*wsize) - header_len); wsize->total_ops = cpu_to_le64(m->metric[METRIC_WRITE].total); wsize->total_size = cpu_to_le64(m->metric[METRIC_WRITE].size_sum); items++; cursor = wsize + 1; if (nr_subvols) { void *payload; void *payload_end; int ret; /* Emit only the type (le32), no ver/compat/data_len */ ceph_encode_32(&cursor, CLIENT_METRIC_TYPE_SUBVOLUME_METRICS); items++; payload = cursor; payload_end = (char *)payload + ceph_subvolume_metric_data_len(nr_subvols); ret = ceph_encode_subvolume_metrics(&payload, payload_end, subvols, nr_subvols); if (ret) { pr_warn_client(cl, "failed to encode subvolume metrics\n"); kfree(subvols); ceph_msg_put(msg); return false; } WARN_ON(payload != payload_end); cursor = payload; } put_unaligned_le32(items, &head->num); msg->front.iov_len = (char *)cursor - (char *)head; msg->hdr.version = cpu_to_le16(1); msg->hdr.compat_version = cpu_to_le16(1); msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); ceph_con_send(&s->s_con, msg); if (nr_subvols) { mutex_lock(&mdsc->subvol_metrics_last_mutex); kfree(mdsc->subvol_metrics_last); mdsc->subvol_metrics_last = subvols; mdsc->subvol_metrics_last_nr = nr_subvols; mdsc->subvol_metrics_sent += nr_subvols; mdsc->subvol_metrics_nonzero_sends++; mutex_unlock(&mdsc->subvol_metrics_last_mutex); subvols = NULL; } kfree(subvols); return true; } static void metric_get_session(struct ceph_mds_client *mdsc) { struct ceph_mds_session *s; int i; mutex_lock(&mdsc->mutex); for (i = 0; i < mdsc->max_sessions; i++) { s = __ceph_lookup_mds_session(mdsc, i); if (!s) continue; /* * Skip it if MDS doesn't support the metric collection, * or the MDS will close the session's socket connection * directly when it get this message. * * Also skip sessions that don't support SUBVOLUME_METRICS * when subvolume metrics collection is enabled. This ensures * we only send subvolume metrics to MDSs that understand them. * If no session supports the feature, metrics won't be sent. */ if (check_session_state(s) && test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) { if (ceph_subvolume_metrics_enabled(&mdsc->subvol_metrics) && !test_bit(CEPHFS_FEATURE_SUBVOLUME_METRICS, &s->s_features)) { ceph_put_mds_session(s); continue; } mdsc->metric.session = s; break; } ceph_put_mds_session(s); } mutex_unlock(&mdsc->mutex); } static void metric_delayed_work(struct work_struct *work) { struct ceph_client_metric *m = container_of(work, struct ceph_client_metric, delayed_work.work); struct ceph_mds_client *mdsc = container_of(m, struct ceph_mds_client, metric); if (mdsc->stopping) return; if (disable_send_metrics) { if (!metrics_disable_warned) { pr_info("ceph: metrics sending disabled via module parameter\n"); metrics_disable_warned = true; } return; } metrics_disable_warned = false; if (!m->session || !check_session_state(m->session)) { if (m->session) { ceph_put_mds_session(m->session); m->session = NULL; } metric_get_session(mdsc); } if (m->session) ceph_mdsc_send_metrics(mdsc, m->session); else pr_warn_ratelimited("ceph: metrics worker has no MDS session\n"); metric_schedule_delayed(m); } int ceph_metric_init(struct ceph_client_metric *m) { struct ceph_metric *metric; int ret, i; if (!m) return -EINVAL; atomic64_set(&m->total_dentries, 0); ret = percpu_counter_init(&m->d_lease_hit, 0, GFP_KERNEL); if (ret) return ret; ret = percpu_counter_init(&m->d_lease_mis, 0, GFP_KERNEL); if (ret) goto err_d_lease_mis; atomic64_set(&m->total_caps, 0); ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL); if (ret) goto err_i_caps_hit; ret = percpu_counter_init(&m->i_caps_mis, 0, GFP_KERNEL); if (ret) goto err_i_caps_mis; for (i = 0; i < METRIC_MAX; i++) { metric = &m->metric[i]; spin_lock_init(&metric->lock); metric->size_sum = 0; metric->size_min = U64_MAX; metric->size_max = 0; metric->total = 0; metric->latency_sum = 0; metric->latency_avg = 0; metric->latency_sq_sum = 0; metric->latency_min = KTIME_MAX; metric->latency_max = 0; } atomic64_set(&m->opened_files, 0); ret = percpu_counter_init(&m->opened_inodes, 0, GFP_KERNEL); if (ret) goto err_opened_inodes; ret = percpu_counter_init(&m->total_inodes, 0, GFP_KERNEL); if (ret) goto err_total_inodes; m->session = NULL; INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work); return 0; err_total_inodes: percpu_counter_destroy(&m->opened_inodes); err_opened_inodes: percpu_counter_destroy(&m->i_caps_mis); err_i_caps_mis: percpu_counter_destroy(&m->i_caps_hit); err_i_caps_hit: percpu_counter_destroy(&m->d_lease_mis); err_d_lease_mis: percpu_counter_destroy(&m->d_lease_hit); return ret; } void ceph_metric_destroy(struct ceph_client_metric *m) { if (!m) return; cancel_delayed_work_sync(&m->delayed_work); percpu_counter_destroy(&m->total_inodes); percpu_counter_destroy(&m->opened_inodes); percpu_counter_destroy(&m->i_caps_mis); percpu_counter_destroy(&m->i_caps_hit); percpu_counter_destroy(&m->d_lease_mis); percpu_counter_destroy(&m->d_lease_hit); ceph_put_mds_session(m->session); } #define METRIC_UPDATE_MIN_MAX(min, max, new) \ { \ if (unlikely(new < min)) \ min = new; \ if (unlikely(new > max)) \ max = new; \ } static inline void __update_mean_and_stdev(ktime_t total, ktime_t *lavg, ktime_t *sq_sump, ktime_t lat) { ktime_t avg; if (unlikely(total == 1)) { *lavg = lat; } else { /* the sq is (lat - old_avg) * (lat - new_avg) */ avg = *lavg + div64_s64(lat - *lavg, total); *sq_sump += (lat - *lavg)*(lat - avg); *lavg = avg; } } void ceph_update_metrics(struct ceph_metric *m, ktime_t r_start, ktime_t r_end, unsigned int size, int rc) { ktime_t lat = ktime_sub(r_end, r_start); ktime_t total; if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT)) return; spin_lock(&m->lock); total = ++m->total; m->size_sum += size; METRIC_UPDATE_MIN_MAX(m->size_min, m->size_max, size); m->latency_sum += lat; METRIC_UPDATE_MIN_MAX(m->latency_min, m->latency_max, lat); __update_mean_and_stdev(total, &m->latency_avg, &m->latency_sq_sum, lat); spin_unlock(&m->lock); } |
| 1 1 1 2 2 4 4 4 4 4 2 2 1 1 1 4 9 3 1 1 1 3 7 3 3 7 7 6 1 2 3 3 4 2 2 4 1 21 1 10 10 13 5 1 13 4 3 14 6 1 10 11 15 2 17 15 2 10 7 13 4 9 1 7 7 2 1 4 4 12 12 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /****************************************************************************** * usbtouchscreen.c * Driver for USB Touchscreens, supporting those devices: * - eGalax Touchkit * includes eTurboTouch CT-410/510/700 * - 3M/Microtouch EX II series * - ITM * - PanJit TouchSet * - eTurboTouch * - Gunze AHL61 * - DMC TSC-10/25 * - IRTOUCHSYSTEMS/UNITOP * - IdealTEK URTC1000 * - General Touch * - GoTop Super_Q2/GogoPen/PenPower tablets * - JASTEC USB touch controller/DigiTech DTR-02U * - Zytronic capacitive touchscreen * - NEXIO/iNexio * - Elo TouchSystems 2700 IntelliTouch * - EasyTouch USB Dual/Multi touch controller from Data Modul * * Copyright (C) 2004-2007 by Daniel Ritz <daniel.ritz@gmx.ch> * Copyright (C) by Todd E. Johnson (mtouchusb.c) * * Driver is based on touchkitusb.c * - ITM parts are from itmtouch.c * - 3M parts are from mtouchusb.c * - PanJit parts are from an unmerged driver by Lanslott Gish * - DMC TSC 10/25 are from Holger Schurig, with ideas from an unmerged * driver from Marius Vollmer * *****************************************************************************/ //#define DEBUG #include <linux/kernel.h> #include <linux/slab.h> #include <linux/input.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/input.h> #include <linux/hid.h> #include <linux/mutex.h> static bool swap_xy; module_param(swap_xy, bool, 0644); MODULE_PARM_DESC(swap_xy, "If set X and Y axes are swapped."); static bool hwcalib_xy; module_param(hwcalib_xy, bool, 0644); MODULE_PARM_DESC(hwcalib_xy, "If set hw-calibrated X/Y are used if available"); /* device specifc data/functions */ struct usbtouch_usb; struct usbtouch_device_info { int min_xc, max_xc; int min_yc, max_yc; int min_press, max_press; int rept_size; /* * Always service the USB devices irq not just when the input device is * open. This is useful when devices have a watchdog which prevents us * from periodically polling the device. Leave this unset unless your * touchscreen device requires it, as it does consume more of the USB * bandwidth. */ bool irq_always; /* * used to get the packet len. possible return values: * > 0: packet len * = 0: skip one byte * < 0: -return value more bytes needed */ int (*get_pkt_len) (unsigned char *pkt, int len); int (*read_data) (struct usbtouch_usb *usbtouch, unsigned char *pkt); int (*alloc) (struct usbtouch_usb *usbtouch); int (*init) (struct usbtouch_usb *usbtouch); void (*exit) (struct usbtouch_usb *usbtouch); }; /* a usbtouch device */ struct usbtouch_usb { unsigned char *data; dma_addr_t data_dma; int data_size; unsigned char *buffer; int buf_len; struct urb *irq; struct usb_interface *interface; struct input_dev *input; const struct usbtouch_device_info *type; struct mutex pm_mutex; /* serialize access to open/suspend */ bool is_open; char name[128]; char phys[64]; void *priv; int x, y; int touch, press; void (*process_pkt)(struct usbtouch_usb *usbtouch, unsigned char *pkt, int len); }; /***************************************************************************** * e2i Part */ #ifdef CONFIG_TOUCHSCREEN_USB_E2I static int e2i_init(struct usbtouch_usb *usbtouch) { int ret; struct usb_device *udev = interface_to_usbdev(usbtouch->interface); ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), 0x01, 0x02, 0x0000, 0x0081, NULL, 0, USB_CTRL_SET_TIMEOUT); dev_dbg(&usbtouch->interface->dev, "%s - usb_control_msg - E2I_RESET - bytes|err: %d\n", __func__, ret); return ret; } static int e2i_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { int tmp = (pkt[0] << 8) | pkt[1]; dev->x = (pkt[2] << 8) | pkt[3]; dev->y = (pkt[4] << 8) | pkt[5]; tmp = tmp - 0xA000; dev->touch = (tmp > 0); dev->press = (tmp > 0 ? tmp : 0); return 1; } static const struct usbtouch_device_info e2i_dev_info = { .min_xc = 0x0, .max_xc = 0x7fff, .min_yc = 0x0, .max_yc = 0x7fff, .rept_size = 6, .init = e2i_init, .read_data = e2i_read_data, }; #endif /***************************************************************************** * eGalax part */ #ifdef CONFIG_TOUCHSCREEN_USB_EGALAX #ifndef MULTI_PACKET #define MULTI_PACKET #endif #define EGALAX_PKT_TYPE_MASK 0xFE #define EGALAX_PKT_TYPE_REPT 0x80 #define EGALAX_PKT_TYPE_DIAG 0x0A static int egalax_init(struct usbtouch_usb *usbtouch) { struct usb_device *udev = interface_to_usbdev(usbtouch->interface); int ret, i; /* * An eGalax diagnostic packet kicks the device into using the right * protocol. We send a "check active" packet. The response will be * read later and ignored. */ u8 *buf __free(kfree) = kmalloc(3, GFP_KERNEL); if (!buf) return -ENOMEM; buf[0] = EGALAX_PKT_TYPE_DIAG; buf[1] = 1; /* length */ buf[2] = 'A'; /* command - check active */ for (i = 0; i < 3; i++) { ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), 0, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, buf, 3, USB_CTRL_SET_TIMEOUT); if (ret != -EPIPE) break; } return ret < 0 ? ret : 0; } static int egalax_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { if ((pkt[0] & EGALAX_PKT_TYPE_MASK) != EGALAX_PKT_TYPE_REPT) return 0; dev->x = ((pkt[3] & 0x0F) << 7) | (pkt[4] & 0x7F); dev->y = ((pkt[1] & 0x0F) << 7) | (pkt[2] & 0x7F); dev->touch = pkt[0] & 0x01; return 1; } static int egalax_get_pkt_len(unsigned char *buf, int len) { switch (buf[0] & EGALAX_PKT_TYPE_MASK) { case EGALAX_PKT_TYPE_REPT: return 5; case EGALAX_PKT_TYPE_DIAG: if (len < 2) return -1; return buf[1] + 2; } return 0; } static const struct usbtouch_device_info egalax_dev_info = { .min_xc = 0x0, .max_xc = 0x07ff, .min_yc = 0x0, .max_yc = 0x07ff, .rept_size = 16, .get_pkt_len = egalax_get_pkt_len, .read_data = egalax_read_data, .init = egalax_init, }; #endif /***************************************************************************** * EasyTouch part */ #ifdef CONFIG_TOUCHSCREEN_USB_EASYTOUCH #ifndef MULTI_PACKET #define MULTI_PACKET #endif #define ETOUCH_PKT_TYPE_MASK 0xFE #define ETOUCH_PKT_TYPE_REPT 0x80 #define ETOUCH_PKT_TYPE_REPT2 0xB0 #define ETOUCH_PKT_TYPE_DIAG 0x0A static int etouch_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { if ((pkt[0] & ETOUCH_PKT_TYPE_MASK) != ETOUCH_PKT_TYPE_REPT && (pkt[0] & ETOUCH_PKT_TYPE_MASK) != ETOUCH_PKT_TYPE_REPT2) return 0; dev->x = ((pkt[1] & 0x1F) << 7) | (pkt[2] & 0x7F); dev->y = ((pkt[3] & 0x1F) << 7) | (pkt[4] & 0x7F); dev->touch = pkt[0] & 0x01; return 1; } static int etouch_get_pkt_len(unsigned char *buf, int len) { switch (buf[0] & ETOUCH_PKT_TYPE_MASK) { case ETOUCH_PKT_TYPE_REPT: case ETOUCH_PKT_TYPE_REPT2: return 5; case ETOUCH_PKT_TYPE_DIAG: if (len < 2) return -1; return buf[1] + 2; } return 0; } static const struct usbtouch_device_info etouch_dev_info = { .min_xc = 0x0, .max_xc = 0x07ff, .min_yc = 0x0, .max_yc = 0x07ff, .rept_size = 16, .get_pkt_len = etouch_get_pkt_len, .read_data = etouch_read_data, }; #endif /***************************************************************************** * PanJit Part */ #ifdef CONFIG_TOUCHSCREEN_USB_PANJIT static int panjit_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = ((pkt[2] & 0x0F) << 8) | pkt[1]; dev->y = ((pkt[4] & 0x0F) << 8) | pkt[3]; dev->touch = pkt[0] & 0x01; return 1; } static const struct usbtouch_device_info panjit_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .rept_size = 8, .read_data = panjit_read_data, }; #endif /***************************************************************************** * 3M/Microtouch Part */ #ifdef CONFIG_TOUCHSCREEN_USB_3M #define MTOUCHUSB_ASYNC_REPORT 1 #define MTOUCHUSB_RESET 7 #define MTOUCHUSB_REQ_CTRLLR_ID 10 #define MTOUCHUSB_REQ_CTRLLR_ID_LEN 16 static int mtouch_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { if (hwcalib_xy) { dev->x = (pkt[4] << 8) | pkt[3]; dev->y = 0xffff - ((pkt[6] << 8) | pkt[5]); } else { dev->x = (pkt[8] << 8) | pkt[7]; dev->y = (pkt[10] << 8) | pkt[9]; } dev->touch = (pkt[2] & 0x40) ? 1 : 0; return 1; } struct mtouch_priv { u8 fw_rev_major; u8 fw_rev_minor; }; static int mtouch_get_fw_revision(struct usbtouch_usb *usbtouch) { struct usb_device *udev = interface_to_usbdev(usbtouch->interface); struct mtouch_priv *priv = usbtouch->priv; int ret; u8 *buf __free(kfree) = kzalloc(MTOUCHUSB_REQ_CTRLLR_ID_LEN, GFP_NOIO); if (!buf) return -ENOMEM; ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), MTOUCHUSB_REQ_CTRLLR_ID, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, buf, MTOUCHUSB_REQ_CTRLLR_ID_LEN, USB_CTRL_SET_TIMEOUT); if (ret != MTOUCHUSB_REQ_CTRLLR_ID_LEN) { dev_warn(&usbtouch->interface->dev, "Failed to read FW rev: %d\n", ret); return ret < 0 ? ret : -EIO; } priv->fw_rev_major = buf[3]; priv->fw_rev_minor = buf[4]; return 0; } static int mtouch_alloc(struct usbtouch_usb *usbtouch) { struct mtouch_priv *priv; priv = kmalloc_obj(*priv); if (!priv) return -ENOMEM; usbtouch->priv = priv; return 0; } static int mtouch_init(struct usbtouch_usb *usbtouch) { int ret, i; struct usb_device *udev = interface_to_usbdev(usbtouch->interface); ret = mtouch_get_fw_revision(usbtouch); if (ret) return ret; ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), MTOUCHUSB_RESET, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 1, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); dev_dbg(&usbtouch->interface->dev, "%s - usb_control_msg - MTOUCHUSB_RESET - bytes|err: %d\n", __func__, ret); if (ret < 0) return ret; msleep(150); for (i = 0; i < 3; i++) { ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), MTOUCHUSB_ASYNC_REPORT, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 1, 1, NULL, 0, USB_CTRL_SET_TIMEOUT); dev_dbg(&usbtouch->interface->dev, "%s - usb_control_msg - MTOUCHUSB_ASYNC_REPORT - bytes|err: %d\n", __func__, ret); if (ret >= 0) break; if (ret != -EPIPE) return ret; } /* Default min/max xy are the raw values, override if using hw-calib */ if (hwcalib_xy) { input_set_abs_params(usbtouch->input, ABS_X, 0, 0xffff, 0, 0); input_set_abs_params(usbtouch->input, ABS_Y, 0, 0xffff, 0, 0); } return 0; } static void mtouch_exit(struct usbtouch_usb *usbtouch) { struct mtouch_priv *priv = usbtouch->priv; kfree(priv); } static struct usbtouch_device_info mtouch_dev_info = { .min_xc = 0x0, .max_xc = 0x4000, .min_yc = 0x0, .max_yc = 0x4000, .rept_size = 11, .read_data = mtouch_read_data, .alloc = mtouch_alloc, .init = mtouch_init, .exit = mtouch_exit, }; static ssize_t mtouch_firmware_rev_show(struct device *dev, struct device_attribute *attr, char *output) { struct usb_interface *intf = to_usb_interface(dev); struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); struct mtouch_priv *priv = usbtouch->priv; return sysfs_emit(output, "%1x.%1x\n", priv->fw_rev_major, priv->fw_rev_minor); } static DEVICE_ATTR(firmware_rev, 0444, mtouch_firmware_rev_show, NULL); static struct attribute *mtouch_attrs[] = { &dev_attr_firmware_rev.attr, NULL }; static bool mtouch_group_visible(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); struct usb_interface *intf = to_usb_interface(dev); struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); return usbtouch->type == &mtouch_dev_info; } DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(mtouch); static const struct attribute_group mtouch_attr_group = { .is_visible = SYSFS_GROUP_VISIBLE(mtouch), .attrs = mtouch_attrs, }; #endif /***************************************************************************** * ITM Part */ #ifdef CONFIG_TOUCHSCREEN_USB_ITM static int itm_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { int touch; /* * ITM devices report invalid x/y data if not touched. * if the screen was touched before but is not touched any more * report touch as 0 with the last valid x/y data once. then stop * reporting data until touched again. */ dev->press = ((pkt[2] & 0x01) << 7) | (pkt[5] & 0x7F); touch = ~pkt[7] & 0x20; if (!touch) { if (dev->touch) { dev->touch = 0; return 1; } return 0; } dev->x = ((pkt[0] & 0x1F) << 7) | (pkt[3] & 0x7F); dev->y = ((pkt[1] & 0x1F) << 7) | (pkt[4] & 0x7F); dev->touch = touch; return 1; } static const struct usbtouch_device_info itm_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .max_press = 0xff, .rept_size = 8, .read_data = itm_read_data, }; #endif /***************************************************************************** * eTurboTouch part */ #ifdef CONFIG_TOUCHSCREEN_USB_ETURBO #ifndef MULTI_PACKET #define MULTI_PACKET #endif static int eturbo_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { unsigned int shift; /* packets should start with sync */ if (!(pkt[0] & 0x80)) return 0; shift = (6 - (pkt[0] & 0x03)); dev->x = ((pkt[3] << 7) | pkt[4]) >> shift; dev->y = ((pkt[1] << 7) | pkt[2]) >> shift; dev->touch = (pkt[0] & 0x10) ? 1 : 0; return 1; } static int eturbo_get_pkt_len(unsigned char *buf, int len) { if (buf[0] & 0x80) return 5; if (buf[0] == 0x01) return 3; return 0; } static const struct usbtouch_device_info eturbo_dev_info = { .min_xc = 0x0, .max_xc = 0x07ff, .min_yc = 0x0, .max_yc = 0x07ff, .rept_size = 8, .get_pkt_len = eturbo_get_pkt_len, .read_data = eturbo_read_data, }; #endif /***************************************************************************** * Gunze part */ #ifdef CONFIG_TOUCHSCREEN_USB_GUNZE static int gunze_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { if (!(pkt[0] & 0x80) || ((pkt[1] | pkt[2] | pkt[3]) & 0x80)) return 0; dev->x = ((pkt[0] & 0x1F) << 7) | (pkt[2] & 0x7F); dev->y = ((pkt[1] & 0x1F) << 7) | (pkt[3] & 0x7F); dev->touch = pkt[0] & 0x20; return 1; } static const struct usbtouch_device_info gunze_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .rept_size = 4, .read_data = gunze_read_data, }; #endif /***************************************************************************** * DMC TSC-10/25 Part * * Documentation about the controller and it's protocol can be found at * http://www.dmccoltd.com/files/controler/tsc10usb_pi_e.pdf * http://www.dmccoltd.com/files/controler/tsc25_usb_e.pdf */ #ifdef CONFIG_TOUCHSCREEN_USB_DMC_TSC10 /* supported data rates. currently using 130 */ #define TSC10_RATE_POINT 0x50 #define TSC10_RATE_30 0x40 #define TSC10_RATE_50 0x41 #define TSC10_RATE_80 0x42 #define TSC10_RATE_100 0x43 #define TSC10_RATE_130 0x44 #define TSC10_RATE_150 0x45 /* commands */ #define TSC10_CMD_RESET 0x55 #define TSC10_CMD_RATE 0x05 #define TSC10_CMD_DATA1 0x01 static int dmc_tsc10_init(struct usbtouch_usb *usbtouch) { struct usb_device *dev = interface_to_usbdev(usbtouch->interface); int ret; u8 *buf __free(kfree) = kmalloc(2, GFP_NOIO); if (!buf) return -ENOMEM; /* reset */ buf[0] = buf[1] = 0xFF; ret = usb_control_msg(dev, usb_rcvctrlpipe (dev, 0), TSC10_CMD_RESET, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, buf, 2, USB_CTRL_SET_TIMEOUT); if (ret < 0) return ret; if (buf[0] != 0x06) return -ENODEV; /* TSC-25 data sheet specifies a delay after the RESET command */ msleep(150); /* set coordinate output rate */ buf[0] = buf[1] = 0xFF; ret = usb_control_msg(dev, usb_rcvctrlpipe (dev, 0), TSC10_CMD_RATE, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, TSC10_RATE_150, 0, buf, 2, USB_CTRL_SET_TIMEOUT); if (ret < 0) return ret; if (buf[0] != 0x06 && (buf[0] != 0x15 || buf[1] != 0x01)) return -ENODEV; /* start sending data */ return usb_control_msg(dev, usb_sndctrlpipe(dev, 0), TSC10_CMD_DATA1, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); } static int dmc_tsc10_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = ((pkt[2] & 0x03) << 8) | pkt[1]; dev->y = ((pkt[4] & 0x03) << 8) | pkt[3]; dev->touch = pkt[0] & 0x01; return 1; } static const struct usbtouch_device_info dmc_tsc10_dev_info = { .min_xc = 0x0, .max_xc = 0x03ff, .min_yc = 0x0, .max_yc = 0x03ff, .rept_size = 5, .init = dmc_tsc10_init, .read_data = dmc_tsc10_read_data, }; #endif /***************************************************************************** * IRTOUCH Part */ #ifdef CONFIG_TOUCHSCREEN_USB_IRTOUCH static int irtouch_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = (pkt[3] << 8) | pkt[2]; dev->y = (pkt[5] << 8) | pkt[4]; dev->touch = (pkt[1] & 0x03) ? 1 : 0; return 1; } static const struct usbtouch_device_info irtouch_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .rept_size = 8, .read_data = irtouch_read_data, }; static const struct usbtouch_device_info irtouch_hires_dev_info = { .min_xc = 0x0, .max_xc = 0x7fff, .min_yc = 0x0, .max_yc = 0x7fff, .rept_size = 8, .read_data = irtouch_read_data, }; #endif /***************************************************************************** * ET&T TC5UH/TC4UM part */ #ifdef CONFIG_TOUCHSCREEN_USB_ETT_TC45USB static int tc45usb_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = ((pkt[2] & 0x0F) << 8) | pkt[1]; dev->y = ((pkt[4] & 0x0F) << 8) | pkt[3]; dev->touch = pkt[0] & 0x01; return 1; } static const struct usbtouch_device_info tc45usb_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .rept_size = 5, .read_data = tc45usb_read_data, }; #endif /***************************************************************************** * IdealTEK URTC1000 Part */ #ifdef CONFIG_TOUCHSCREEN_USB_IDEALTEK #ifndef MULTI_PACKET #define MULTI_PACKET #endif static int idealtek_get_pkt_len(unsigned char *buf, int len) { if (buf[0] & 0x80) return 5; if (buf[0] == 0x01) return len; return 0; } static int idealtek_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { switch (pkt[0] & 0x98) { case 0x88: /* touch data in IdealTEK mode */ dev->x = (pkt[1] << 5) | (pkt[2] >> 2); dev->y = (pkt[3] << 5) | (pkt[4] >> 2); dev->touch = (pkt[0] & 0x40) ? 1 : 0; return 1; case 0x98: /* touch data in MT emulation mode */ dev->x = (pkt[2] << 5) | (pkt[1] >> 2); dev->y = (pkt[4] << 5) | (pkt[3] >> 2); dev->touch = (pkt[0] & 0x40) ? 1 : 0; return 1; default: return 0; } } static const struct usbtouch_device_info idealtek_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .rept_size = 8, .get_pkt_len = idealtek_get_pkt_len, .read_data = idealtek_read_data, }; #endif /***************************************************************************** * General Touch Part */ #ifdef CONFIG_TOUCHSCREEN_USB_GENERAL_TOUCH static int general_touch_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = (pkt[2] << 8) | pkt[1]; dev->y = (pkt[4] << 8) | pkt[3]; dev->press = pkt[5] & 0xff; dev->touch = pkt[0] & 0x01; return 1; } static const struct usbtouch_device_info general_touch_dev_info = { .min_xc = 0x0, .max_xc = 0x7fff, .min_yc = 0x0, .max_yc = 0x7fff, .rept_size = 7, .read_data = general_touch_read_data, }; #endif /***************************************************************************** * GoTop Part */ #ifdef CONFIG_TOUCHSCREEN_USB_GOTOP static int gotop_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = ((pkt[1] & 0x38) << 4) | pkt[2]; dev->y = ((pkt[1] & 0x07) << 7) | pkt[3]; dev->touch = pkt[0] & 0x01; return 1; } static const struct usbtouch_device_info gotop_dev_info = { .min_xc = 0x0, .max_xc = 0x03ff, .min_yc = 0x0, .max_yc = 0x03ff, .rept_size = 4, .read_data = gotop_read_data, }; #endif /***************************************************************************** * JASTEC Part */ #ifdef CONFIG_TOUCHSCREEN_USB_JASTEC static int jastec_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = ((pkt[0] & 0x3f) << 6) | (pkt[2] & 0x3f); dev->y = ((pkt[1] & 0x3f) << 6) | (pkt[3] & 0x3f); dev->touch = (pkt[0] & 0x40) >> 6; return 1; } static const struct usbtouch_device_info jastec_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .rept_size = 4, .read_data = jastec_read_data, }; #endif /***************************************************************************** * Zytronic Part */ #ifdef CONFIG_TOUCHSCREEN_USB_ZYTRONIC static int zytronic_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { struct usb_interface *intf = dev->interface; switch (pkt[0]) { case 0x3A: /* command response */ dev_dbg(&intf->dev, "%s: Command response %d\n", __func__, pkt[1]); break; case 0xC0: /* down */ dev->x = (pkt[1] & 0x7f) | ((pkt[2] & 0x07) << 7); dev->y = (pkt[3] & 0x7f) | ((pkt[4] & 0x07) << 7); dev->touch = 1; dev_dbg(&intf->dev, "%s: down %d,%d\n", __func__, dev->x, dev->y); return 1; case 0x80: /* up */ dev->x = (pkt[1] & 0x7f) | ((pkt[2] & 0x07) << 7); dev->y = (pkt[3] & 0x7f) | ((pkt[4] & 0x07) << 7); dev->touch = 0; dev_dbg(&intf->dev, "%s: up %d,%d\n", __func__, dev->x, dev->y); return 1; default: dev_dbg(&intf->dev, "%s: Unknown return %d\n", __func__, pkt[0]); break; } return 0; } static const struct usbtouch_device_info zytronic_dev_info = { .min_xc = 0x0, .max_xc = 0x03ff, .min_yc = 0x0, .max_yc = 0x03ff, .rept_size = 5, .read_data = zytronic_read_data, .irq_always = true, }; #endif /***************************************************************************** * NEXIO Part */ #ifdef CONFIG_TOUCHSCREEN_USB_NEXIO #define NEXIO_TIMEOUT 5000 #define NEXIO_BUFSIZE 1024 #define NEXIO_THRESHOLD 50 struct nexio_priv { struct urb *ack; unsigned char *ack_buf; }; struct nexio_touch_packet { u8 flags; /* 0xe1 = touch, 0xe1 = release */ __be16 data_len; /* total bytes of touch data */ __be16 x_len; /* bytes for X axis */ __be16 y_len; /* bytes for Y axis */ u8 data[]; } __attribute__ ((packed)); static unsigned char nexio_ack_pkt[2] = { 0xaa, 0x02 }; static unsigned char nexio_init_pkt[4] = { 0x82, 0x04, 0x0a, 0x0f }; static void nexio_ack_complete(struct urb *urb) { } static int nexio_alloc(struct usbtouch_usb *usbtouch) { struct nexio_priv *priv; int ret = -ENOMEM; priv = kmalloc_obj(*priv); if (!priv) goto out_buf; usbtouch->priv = priv; priv->ack_buf = kmemdup(nexio_ack_pkt, sizeof(nexio_ack_pkt), GFP_KERNEL); if (!priv->ack_buf) goto err_priv; priv->ack = usb_alloc_urb(0, GFP_KERNEL); if (!priv->ack) { dev_dbg(&usbtouch->interface->dev, "%s - usb_alloc_urb failed: usbtouch->ack\n", __func__); goto err_ack_buf; } return 0; err_ack_buf: kfree(priv->ack_buf); err_priv: kfree(priv); out_buf: return ret; } static int nexio_init(struct usbtouch_usb *usbtouch) { struct usb_device *dev = interface_to_usbdev(usbtouch->interface); struct usb_host_interface *interface = usbtouch->interface->cur_altsetting; struct usb_endpoint_descriptor *ep_in, *ep_out; struct nexio_priv *priv = usbtouch->priv; int actual_len, i; char *firmware_ver = NULL, *device_name = NULL; int input_ep, output_ep; int ret; /* find first input and output endpoint */ ret = usb_find_common_endpoints(interface, &ep_in, &ep_out, NULL, NULL); if (ret) return -ENXIO; input_ep = usb_endpoint_num(ep_in); output_ep = usb_endpoint_num(ep_out); u8 *buf __free(kfree) = kmalloc(NEXIO_BUFSIZE, GFP_NOIO); if (!buf) return -ENOMEM; /* two empty reads */ for (i = 0; i < 2; i++) { ret = usb_bulk_msg(dev, usb_rcvbulkpipe(dev, input_ep), buf, NEXIO_BUFSIZE, &actual_len, NEXIO_TIMEOUT); if (ret < 0) return ret; } /* send init command */ memcpy(buf, nexio_init_pkt, sizeof(nexio_init_pkt)); ret = usb_bulk_msg(dev, usb_sndbulkpipe(dev, output_ep), buf, sizeof(nexio_init_pkt), &actual_len, NEXIO_TIMEOUT); if (ret < 0) return ret; /* read replies */ for (i = 0; i < 3; i++) { memset(buf, 0, NEXIO_BUFSIZE); ret = usb_bulk_msg(dev, usb_rcvbulkpipe(dev, input_ep), buf, NEXIO_BUFSIZE, &actual_len, NEXIO_TIMEOUT); if (ret < 0 || actual_len < 1 || buf[1] != actual_len) continue; switch (buf[0]) { case 0x83: /* firmware version */ if (!firmware_ver) firmware_ver = kstrdup(&buf[2], GFP_NOIO); break; case 0x84: /* device name */ if (!device_name) device_name = kstrdup(&buf[2], GFP_NOIO); break; } } printk(KERN_INFO "Nexio device: %s, firmware version: %s\n", device_name, firmware_ver); kfree(firmware_ver); kfree(device_name); usb_fill_bulk_urb(priv->ack, dev, usb_sndbulkpipe(dev, output_ep), priv->ack_buf, sizeof(nexio_ack_pkt), nexio_ack_complete, usbtouch); return 0; } static void nexio_exit(struct usbtouch_usb *usbtouch) { struct nexio_priv *priv = usbtouch->priv; usb_kill_urb(priv->ack); usb_free_urb(priv->ack); kfree(priv->ack_buf); kfree(priv); } static int nexio_read_data(struct usbtouch_usb *usbtouch, unsigned char *pkt) { struct device *dev = &usbtouch->interface->dev; struct nexio_touch_packet *packet = (void *) pkt; struct nexio_priv *priv = usbtouch->priv; unsigned int data_len = be16_to_cpu(packet->data_len); unsigned int x_len = be16_to_cpu(packet->x_len); unsigned int y_len = be16_to_cpu(packet->y_len); int x, y, begin_x, begin_y, end_x, end_y, w, h, ret; /* got touch data? */ if ((pkt[0] & 0xe0) != 0xe0) return 0; if (data_len > 0xff) data_len -= 0x100; if (x_len > 0xff) x_len -= 0x80; if (data_len > usbtouch->data_size - sizeof(*packet)) data_len = usbtouch->data_size - sizeof(*packet); if (x_len > data_len) x_len = data_len; /* send ACK */ ret = usb_submit_urb(priv->ack, GFP_ATOMIC); if (ret) dev_warn(dev, "Failed to submit ACK URB: %d\n", ret); if (!input_abs_get_max(usbtouch->input, ABS_X)) { input_set_abs_params(usbtouch->input, ABS_X, 0, 2 * x_len, 0, 0); input_set_abs_params(usbtouch->input, ABS_Y, 0, 2 * y_len, 0, 0); } /* * The device reports state of IR sensors on X and Y axes. * Each byte represents "darkness" percentage (0-100) of one element. * 17" touchscreen reports only 64 x 52 bytes so the resolution is low. * This also means that there's a limited multi-touch capability but * it's disabled (and untested) here as there's no X driver for that. */ begin_x = end_x = begin_y = end_y = -1; for (x = 0; x < x_len; x++) { if (begin_x == -1 && packet->data[x] > NEXIO_THRESHOLD) { begin_x = x; continue; } if (end_x == -1 && begin_x != -1 && packet->data[x] < NEXIO_THRESHOLD) { end_x = x - 1; for (y = x_len; y < data_len; y++) { if (begin_y == -1 && packet->data[y] > NEXIO_THRESHOLD) { begin_y = y - x_len; continue; } if (end_y == -1 && begin_y != -1 && packet->data[y] < NEXIO_THRESHOLD) { end_y = y - 1 - x_len; w = end_x - begin_x; h = end_y - begin_y; #if 0 /* multi-touch */ input_report_abs(usbtouch->input, ABS_MT_TOUCH_MAJOR, max(w,h)); input_report_abs(usbtouch->input, ABS_MT_TOUCH_MINOR, min(x,h)); input_report_abs(usbtouch->input, ABS_MT_POSITION_X, 2*begin_x+w); input_report_abs(usbtouch->input, ABS_MT_POSITION_Y, 2*begin_y+h); input_report_abs(usbtouch->input, ABS_MT_ORIENTATION, w > h); input_mt_sync(usbtouch->input); #endif /* single touch */ usbtouch->x = 2 * begin_x + w; usbtouch->y = 2 * begin_y + h; usbtouch->touch = packet->flags & 0x01; begin_y = end_y = -1; return 1; } } begin_x = end_x = -1; } } return 0; } static const struct usbtouch_device_info nexio_dev_info = { .rept_size = 1024, .irq_always = true, .read_data = nexio_read_data, .alloc = nexio_alloc, .init = nexio_init, .exit = nexio_exit, }; #endif /***************************************************************************** * ELO part */ #ifdef CONFIG_TOUCHSCREEN_USB_ELO static int elo_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { dev->x = (pkt[3] << 8) | pkt[2]; dev->y = (pkt[5] << 8) | pkt[4]; dev->touch = pkt[6] > 0; dev->press = pkt[6]; return 1; } static const struct usbtouch_device_info elo_dev_info = { .min_xc = 0x0, .max_xc = 0x0fff, .min_yc = 0x0, .max_yc = 0x0fff, .max_press = 0xff, .rept_size = 8, .read_data = elo_read_data, }; #endif /***************************************************************************** * Generic Part */ static void usbtouch_process_pkt(struct usbtouch_usb *usbtouch, unsigned char *pkt, int len) { const struct usbtouch_device_info *type = usbtouch->type; if (!type->read_data(usbtouch, pkt)) return; input_report_key(usbtouch->input, BTN_TOUCH, usbtouch->touch); if (swap_xy) { input_report_abs(usbtouch->input, ABS_X, usbtouch->y); input_report_abs(usbtouch->input, ABS_Y, usbtouch->x); } else { input_report_abs(usbtouch->input, ABS_X, usbtouch->x); input_report_abs(usbtouch->input, ABS_Y, usbtouch->y); } if (type->max_press) input_report_abs(usbtouch->input, ABS_PRESSURE, usbtouch->press); input_sync(usbtouch->input); } #ifdef MULTI_PACKET static void usbtouch_process_multi(struct usbtouch_usb *usbtouch, unsigned char *pkt, int len) { unsigned char *buffer; int pkt_len, pos, buf_len, tmp; /* process buffer */ if (unlikely(usbtouch->buf_len)) { /* try to get size */ pkt_len = usbtouch->type->get_pkt_len( usbtouch->buffer, usbtouch->buf_len); /* drop? */ if (unlikely(!pkt_len)) goto out_flush_buf; /* need to append -pkt_len bytes before able to get size */ if (unlikely(pkt_len < 0)) { int append = -pkt_len; if (unlikely(append > len)) append = len; if (usbtouch->buf_len + append >= usbtouch->type->rept_size) goto out_flush_buf; memcpy(usbtouch->buffer + usbtouch->buf_len, pkt, append); usbtouch->buf_len += append; pkt_len = usbtouch->type->get_pkt_len( usbtouch->buffer, usbtouch->buf_len); if (pkt_len < 0) return; } /* append */ tmp = pkt_len - usbtouch->buf_len; if (usbtouch->buf_len + tmp >= usbtouch->type->rept_size) goto out_flush_buf; memcpy(usbtouch->buffer + usbtouch->buf_len, pkt, tmp); usbtouch_process_pkt(usbtouch, usbtouch->buffer, pkt_len); buffer = pkt + tmp; buf_len = len - tmp; } else { buffer = pkt; buf_len = len; } /* loop over the received packet, process */ pos = 0; while (pos < buf_len) { /* get packet len */ pkt_len = usbtouch->type->get_pkt_len(buffer + pos, buf_len - pos); /* unknown packet: skip one byte */ if (unlikely(!pkt_len)) { pos++; continue; } /* full packet: process */ if (likely((pkt_len > 0) && (pkt_len <= buf_len - pos))) { usbtouch_process_pkt(usbtouch, buffer + pos, pkt_len); } else { /* incomplete packet: save in buffer */ memcpy(usbtouch->buffer, buffer + pos, buf_len - pos); usbtouch->buf_len = buf_len - pos; return; } pos += pkt_len; } out_flush_buf: usbtouch->buf_len = 0; return; } #else static void usbtouch_process_multi(struct usbtouch_usb *usbtouch, unsigned char *pkt, int len) { dev_WARN_ONCE(&usbtouch->interface->dev, 1, "Protocol has ->get_pkt_len() without #define MULTI_PACKET"); } #endif static void usbtouch_irq(struct urb *urb) { struct usbtouch_usb *usbtouch = urb->context; struct device *dev = &usbtouch->interface->dev; int retval; switch (urb->status) { case 0: /* success */ break; case -ETIME: /* this urb is timing out */ dev_dbg(dev, "%s - urb timed out - was the device unplugged?\n", __func__); return; case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: case -EPIPE: /* this urb is terminated, clean up */ dev_dbg(dev, "%s - urb shutting down with status: %d\n", __func__, urb->status); return; default: dev_dbg(dev, "%s - nonzero urb status received: %d\n", __func__, urb->status); goto exit; } usbtouch->process_pkt(usbtouch, usbtouch->data, urb->actual_length); exit: usb_mark_last_busy(interface_to_usbdev(usbtouch->interface)); retval = usb_submit_urb(urb, GFP_ATOMIC); if (retval) dev_err(dev, "%s - usb_submit_urb failed with result: %d\n", __func__, retval); } static int usbtouch_start_io(struct usbtouch_usb *usbtouch) { guard(mutex)(&usbtouch->pm_mutex); if (!usbtouch->type->irq_always) if (usb_submit_urb(usbtouch->irq, GFP_KERNEL)) return -EIO; usbtouch->interface->needs_remote_wakeup = 1; usbtouch->is_open = true; return 0; } static int usbtouch_open(struct input_dev *input) { struct usbtouch_usb *usbtouch = input_get_drvdata(input); int r; usbtouch->irq->dev = interface_to_usbdev(usbtouch->interface); r = usb_autopm_get_interface(usbtouch->interface) ? -EIO : 0; if (r) return r; r = usbtouch_start_io(usbtouch); usb_autopm_put_interface(usbtouch->interface); return r; } static void usbtouch_close(struct input_dev *input) { struct usbtouch_usb *usbtouch = input_get_drvdata(input); int r; scoped_guard(mutex, &usbtouch->pm_mutex) { if (!usbtouch->type->irq_always) usb_kill_urb(usbtouch->irq); usbtouch->is_open = false; } r = usb_autopm_get_interface(usbtouch->interface); usbtouch->interface->needs_remote_wakeup = 0; if (!r) usb_autopm_put_interface(usbtouch->interface); } static int usbtouch_suspend(struct usb_interface *intf, pm_message_t message) { struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); usb_kill_urb(usbtouch->irq); return 0; } static int usbtouch_resume(struct usb_interface *intf) { struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); guard(mutex)(&usbtouch->pm_mutex); if (usbtouch->is_open || usbtouch->type->irq_always) return usb_submit_urb(usbtouch->irq, GFP_NOIO); return 0; } static int usbtouch_reset_resume(struct usb_interface *intf) { struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); int err; /* reinit the device */ if (usbtouch->type->init) { err = usbtouch->type->init(usbtouch); if (err) { dev_dbg(&intf->dev, "%s - type->init() failed, err: %d\n", __func__, err); return err; } } /* restart IO if needed */ guard(mutex)(&usbtouch->pm_mutex); if (usbtouch->is_open) return usb_submit_urb(usbtouch->irq, GFP_NOIO); return 0; } static void usbtouch_free_buffers(struct usb_device *udev, struct usbtouch_usb *usbtouch) { usb_free_coherent(udev, usbtouch->data_size, usbtouch->data, usbtouch->data_dma); kfree(usbtouch->buffer); } static int usbtouch_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usbtouch_usb *usbtouch; struct input_dev *input_dev; struct usb_endpoint_descriptor *endpoint; struct usb_device *udev = interface_to_usbdev(intf); const struct usbtouch_device_info *type; int err; /* some devices are ignored */ type = (const struct usbtouch_device_info *)id->driver_info; if (!type) return -ENODEV; err = usb_find_int_in_endpoint(intf->cur_altsetting, &endpoint); if (err) { err = usb_find_bulk_in_endpoint(intf->cur_altsetting, &endpoint); if (err) return -ENXIO; } err = -ENOMEM; usbtouch = kzalloc_obj(*usbtouch); input_dev = input_allocate_device(); if (!usbtouch || !input_dev) goto out_free; mutex_init(&usbtouch->pm_mutex); usbtouch->type = type; usbtouch->data_size = type->rept_size; if (type->get_pkt_len) { /* * When dealing with variable-length packets we should * not request more than wMaxPacketSize bytes at once * as we do not know if there is more data coming or * we filled exactly wMaxPacketSize bytes and there is * nothing else. */ usbtouch->data_size = min(usbtouch->data_size, usb_endpoint_maxp(endpoint)); } usbtouch->data = usb_alloc_coherent(udev, usbtouch->data_size, GFP_KERNEL, &usbtouch->data_dma); if (!usbtouch->data) goto out_free; if (type->get_pkt_len) { usbtouch->buffer = kmalloc(type->rept_size, GFP_KERNEL); if (!usbtouch->buffer) goto out_free_buffers; usbtouch->process_pkt = usbtouch_process_multi; } else { usbtouch->process_pkt = usbtouch_process_pkt; } usbtouch->irq = usb_alloc_urb(0, GFP_KERNEL); if (!usbtouch->irq) { dev_dbg(&intf->dev, "%s - usb_alloc_urb failed: usbtouch->irq\n", __func__); goto out_free_buffers; } usbtouch->interface = intf; usbtouch->input = input_dev; if (udev->manufacturer) strscpy(usbtouch->name, udev->manufacturer, sizeof(usbtouch->name)); if (udev->product) { if (udev->manufacturer) strlcat(usbtouch->name, " ", sizeof(usbtouch->name)); strlcat(usbtouch->name, udev->product, sizeof(usbtouch->name)); } if (!strlen(usbtouch->name)) snprintf(usbtouch->name, sizeof(usbtouch->name), "USB Touchscreen %04x:%04x", le16_to_cpu(udev->descriptor.idVendor), le16_to_cpu(udev->descriptor.idProduct)); usb_make_path(udev, usbtouch->phys, sizeof(usbtouch->phys)); strlcat(usbtouch->phys, "/input0", sizeof(usbtouch->phys)); input_dev->name = usbtouch->name; input_dev->phys = usbtouch->phys; usb_to_input_id(udev, &input_dev->id); input_dev->dev.parent = &intf->dev; input_set_drvdata(input_dev, usbtouch); input_dev->open = usbtouch_open; input_dev->close = usbtouch_close; input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); input_set_abs_params(input_dev, ABS_X, type->min_xc, type->max_xc, 0, 0); input_set_abs_params(input_dev, ABS_Y, type->min_yc, type->max_yc, 0, 0); if (type->max_press) input_set_abs_params(input_dev, ABS_PRESSURE, type->min_press, type->max_press, 0, 0); if (usb_endpoint_type(endpoint) == USB_ENDPOINT_XFER_INT) usb_fill_int_urb(usbtouch->irq, udev, usb_rcvintpipe(udev, endpoint->bEndpointAddress), usbtouch->data, usbtouch->data_size, usbtouch_irq, usbtouch, endpoint->bInterval); else usb_fill_bulk_urb(usbtouch->irq, udev, usb_rcvbulkpipe(udev, endpoint->bEndpointAddress), usbtouch->data, usbtouch->data_size, usbtouch_irq, usbtouch); usbtouch->irq->dev = udev; usbtouch->irq->transfer_dma = usbtouch->data_dma; usbtouch->irq->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; /* device specific allocations */ if (type->alloc) { err = type->alloc(usbtouch); if (err) { dev_dbg(&intf->dev, "%s - type->alloc() failed, err: %d\n", __func__, err); goto out_free_urb; } } /* device specific initialisation*/ if (type->init) { err = type->init(usbtouch); if (err) { dev_dbg(&intf->dev, "%s - type->init() failed, err: %d\n", __func__, err); goto out_do_exit; } } err = input_register_device(usbtouch->input); if (err) { dev_dbg(&intf->dev, "%s - input_register_device failed, err: %d\n", __func__, err); goto out_do_exit; } usb_set_intfdata(intf, usbtouch); if (usbtouch->type->irq_always) { /* this can't fail */ usb_autopm_get_interface(intf); err = usb_submit_urb(usbtouch->irq, GFP_KERNEL); if (err) { usb_autopm_put_interface(intf); dev_err(&intf->dev, "%s - usb_submit_urb failed with result: %d\n", __func__, err); goto out_unregister_input; } } return 0; out_unregister_input: input_unregister_device(input_dev); input_dev = NULL; out_do_exit: if (type->exit) type->exit(usbtouch); out_free_urb: usb_free_urb(usbtouch->irq); out_free_buffers: usbtouch_free_buffers(udev, usbtouch); out_free: input_free_device(input_dev); kfree(usbtouch); return err; } static void usbtouch_disconnect(struct usb_interface *intf) { struct usbtouch_usb *usbtouch = usb_get_intfdata(intf); if (!usbtouch) return; dev_dbg(&intf->dev, "%s - usbtouch is initialized, cleaning up\n", __func__); usb_set_intfdata(intf, NULL); /* this will stop IO via close */ input_unregister_device(usbtouch->input); usb_free_urb(usbtouch->irq); if (usbtouch->type->exit) usbtouch->type->exit(usbtouch); usbtouch_free_buffers(interface_to_usbdev(intf), usbtouch); kfree(usbtouch); } static const struct attribute_group *usbtouch_groups[] = { #ifdef CONFIG_TOUCHSCREEN_USB_3M &mtouch_attr_group, #endif NULL }; static const struct usb_device_id usbtouch_devices[] = { #ifdef CONFIG_TOUCHSCREEN_USB_EGALAX /* ignore the HID capable devices, handled by usbhid */ { USB_DEVICE_INTERFACE_CLASS(0x0eef, 0x0001, USB_INTERFACE_CLASS_HID), .driver_info = 0 }, { USB_DEVICE_INTERFACE_CLASS(0x0eef, 0x0002, USB_INTERFACE_CLASS_HID), .driver_info = 0 }, /* normal device IDs */ { USB_DEVICE(0x3823, 0x0001), .driver_info = (kernel_ulong_t)&egalax_dev_info }, { USB_DEVICE(0x3823, 0x0002), .driver_info = (kernel_ulong_t)&egalax_dev_info }, { USB_DEVICE(0x0123, 0x0001), .driver_info = (kernel_ulong_t)&egalax_dev_info }, { USB_DEVICE(0x0eef, 0x0001), .driver_info = (kernel_ulong_t)&egalax_dev_info }, { USB_DEVICE(0x0eef, 0x0002), .driver_info = (kernel_ulong_t)&egalax_dev_info }, { USB_DEVICE(0x1234, 0x0001), .driver_info = (kernel_ulong_t)&egalax_dev_info }, { USB_DEVICE(0x1234, 0x0002), .driver_info = (kernel_ulong_t)&egalax_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_PANJIT { USB_DEVICE(0x134c, 0x0001), .driver_info = (kernel_ulong_t)&panjit_dev_info }, { USB_DEVICE(0x134c, 0x0002), .driver_info = (kernel_ulong_t)&panjit_dev_info }, { USB_DEVICE(0x134c, 0x0003), .driver_info = (kernel_ulong_t)&panjit_dev_info }, { USB_DEVICE(0x134c, 0x0004), .driver_info = (kernel_ulong_t)&panjit_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_3M { USB_DEVICE(0x0596, 0x0001), .driver_info = (kernel_ulong_t)&mtouch_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_ITM { USB_DEVICE(0x0403, 0xf9e9), .driver_info = (kernel_ulong_t)&itm_dev_info }, { USB_DEVICE(0x16e3, 0xf9e9), .driver_info = (kernel_ulong_t)&itm_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_ETURBO { USB_DEVICE(0x1234, 0x5678), .driver_info = (kernel_ulong_t)&eturbo_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_GUNZE { USB_DEVICE(0x0637, 0x0001), .driver_info = (kernel_ulong_t)&gunze_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_DMC_TSC10 { USB_DEVICE(0x0afa, 0x03e8), .driver_info = (kernel_ulong_t)&dmc_tsc10_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_IRTOUCH { USB_DEVICE(0x255e, 0x0001), .driver_info = (kernel_ulong_t)&irtouch_dev_info }, { USB_DEVICE(0x595a, 0x0001), .driver_info = (kernel_ulong_t)&irtouch_dev_info }, { USB_DEVICE(0x6615, 0x0001), .driver_info = (kernel_ulong_t)&irtouch_dev_info }, { USB_DEVICE(0x6615, 0x0012), .driver_info = (kernel_ulong_t)&irtouch_hires_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_IDEALTEK { USB_DEVICE(0x1391, 0x1000), .driver_info = (kernel_ulong_t)&idealtek_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_GENERAL_TOUCH { USB_DEVICE(0x0dfc, 0x0001), .driver_info = (kernel_ulong_t)&general_touch_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_GOTOP { USB_DEVICE(0x08f2, 0x007f), .driver_info = (kernel_ulong_t)&gotop_dev_info }, { USB_DEVICE(0x08f2, 0x00ce), .driver_info = (kernel_ulong_t)&gotop_dev_info }, { USB_DEVICE(0x08f2, 0x00f4), .driver_info = (kernel_ulong_t)&gotop_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_JASTEC { USB_DEVICE(0x0f92, 0x0001), .driver_info = (kernel_ulong_t)&jastec_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_E2I { USB_DEVICE(0x1ac7, 0x0001), .driver_info = (kernel_ulong_t)&e2i_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_ZYTRONIC { USB_DEVICE(0x14c8, 0x0003), .driver_info = (kernel_ulong_t)&zytronic_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_ETT_TC45USB /* TC5UH */ { USB_DEVICE(0x0664, 0x0309), .driver_info = (kernel_ulong_t)&tc45usb_dev_info }, /* TC4UM */ { USB_DEVICE(0x0664, 0x0306), .driver_info = (kernel_ulong_t)&tc45usb_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_NEXIO /* data interface only */ { USB_DEVICE_AND_INTERFACE_INFO(0x10f0, 0x2002, 0x0a, 0x00, 0x00), .driver_info = (kernel_ulong_t)&nexio_dev_info }, { USB_DEVICE_AND_INTERFACE_INFO(0x1870, 0x0001, 0x0a, 0x00, 0x00), .driver_info = (kernel_ulong_t)&nexio_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_ELO { USB_DEVICE(0x04e7, 0x0020), .driver_info = (kernel_ulong_t)&elo_dev_info }, #endif #ifdef CONFIG_TOUCHSCREEN_USB_EASYTOUCH { USB_DEVICE(0x7374, 0x0001), .driver_info = (kernel_ulong_t)&etouch_dev_info }, #endif { } }; MODULE_DEVICE_TABLE(usb, usbtouch_devices); static struct usb_driver usbtouch_driver = { .name = "usbtouchscreen", .probe = usbtouch_probe, .disconnect = usbtouch_disconnect, .suspend = usbtouch_suspend, .resume = usbtouch_resume, .reset_resume = usbtouch_reset_resume, .id_table = usbtouch_devices, .dev_groups = usbtouch_groups, .supports_autosuspend = 1, }; module_usb_driver(usbtouch_driver); MODULE_AUTHOR("Daniel Ritz <daniel.ritz@gmx.ch>"); MODULE_DESCRIPTION("USB Touchscreen Driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS("touchkitusb"); MODULE_ALIAS("itmtouch"); MODULE_ALIAS("mtouchusb"); |
| 2 10 10 2 12 11 11 2 10 2 2 46 39 39 39 39 8 7 10 10 10 10 10 2 2 2 1 2 13 3 16 4 12 12 4 10 10 10 10 16 16 2 2 3 3 3 3 2 2 2 2 4 5 2 1 3 9 3 6 3 9 9 10 10 10 10 2 2 2 2 2 17 22 10 10 10 8 2 2 2 2 2 2 2 4 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* RFCOMM implementation for Linux Bluetooth stack (BlueZ). Copyright (C) 2002 Maxim Krasnyansky <maxk@qualcomm.com> Copyright (C) 2002 Marcel Holtmann <marcel@holtmann.org> THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* * Bluetooth RFCOMM core. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/kthread.h> #include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/rfcomm.h> #include <trace/events/sock.h> #define VERSION "1.11" static bool disable_cfc; static bool l2cap_ertm; static int channel_mtu = -1; static struct task_struct *rfcomm_thread; static DEFINE_MUTEX(rfcomm_mutex); #define rfcomm_lock() mutex_lock(&rfcomm_mutex) #define rfcomm_unlock() mutex_unlock(&rfcomm_mutex) static LIST_HEAD(session_list); static int rfcomm_send_frame(struct rfcomm_session *s, u8 *data, int len); static int rfcomm_send_sabm(struct rfcomm_session *s, u8 dlci); static int rfcomm_send_disc(struct rfcomm_session *s, u8 dlci); static int rfcomm_queue_disc(struct rfcomm_dlc *d); static int rfcomm_send_nsc(struct rfcomm_session *s, int cr, u8 type); static int rfcomm_send_pn(struct rfcomm_session *s, int cr, struct rfcomm_dlc *d); static int rfcomm_send_msc(struct rfcomm_session *s, int cr, u8 dlci, u8 v24_sig); static int rfcomm_send_test(struct rfcomm_session *s, int cr, u8 *pattern, int len); static int rfcomm_send_credits(struct rfcomm_session *s, u8 addr, u8 credits); static void rfcomm_make_uih(struct sk_buff *skb, u8 addr); static void rfcomm_process_connect(struct rfcomm_session *s); static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst, u8 sec_level, int *err); static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst); static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s); /* ---- RFCOMM frame parsing macros ---- */ #define __get_dlci(b) ((b & 0xfc) >> 2) #define __get_type(b) ((b & 0xef)) #define __test_ea(b) ((b & 0x01)) #define __test_cr(b) (!!(b & 0x02)) #define __test_pf(b) (!!(b & 0x10)) #define __session_dir(s) ((s)->initiator ? 0x00 : 0x01) #define __addr(cr, dlci) (((dlci & 0x3f) << 2) | (cr << 1) | 0x01) #define __ctrl(type, pf) (((type & 0xef) | (pf << 4))) #define __dlci(dir, chn) (((chn & 0x1f) << 1) | dir) #define __srv_channel(dlci) (dlci >> 1) #define __len8(len) (((len) << 1) | 1) #define __len16(len) ((len) << 1) /* MCC macros */ #define __mcc_type(cr, type) (((type << 2) | (cr << 1) | 0x01)) #define __get_mcc_type(b) ((b & 0xfc) >> 2) #define __get_mcc_len(b) ((b & 0xfe) >> 1) /* RPN macros */ #define __rpn_line_settings(data, stop, parity) ((data & 0x3) | ((stop & 0x1) << 2) | ((parity & 0x7) << 3)) #define __get_rpn_data_bits(line) ((line) & 0x3) #define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1) #define __get_rpn_parity(line) (((line) >> 3) & 0x7) static DECLARE_WAIT_QUEUE_HEAD(rfcomm_wq); static void rfcomm_schedule(void) { wake_up_all(&rfcomm_wq); } /* ---- RFCOMM FCS computation ---- */ /* reversed, 8-bit, poly=0x07 */ static unsigned char rfcomm_crc_table[256] = { 0x00, 0x91, 0xe3, 0x72, 0x07, 0x96, 0xe4, 0x75, 0x0e, 0x9f, 0xed, 0x7c, 0x09, 0x98, 0xea, 0x7b, 0x1c, 0x8d, 0xff, 0x6e, 0x1b, 0x8a, 0xf8, 0x69, 0x12, 0x83, 0xf1, 0x60, 0x15, 0x84, 0xf6, 0x67, 0x38, 0xa9, 0xdb, 0x4a, 0x3f, 0xae, 0xdc, 0x4d, 0x36, 0xa7, 0xd5, 0x44, 0x31, 0xa0, 0xd2, 0x43, 0x24, 0xb5, 0xc7, 0x56, 0x23, 0xb2, 0xc0, 0x51, 0x2a, 0xbb, 0xc9, 0x58, 0x2d, 0xbc, 0xce, 0x5f, 0x70, 0xe1, 0x93, 0x02, 0x77, 0xe6, 0x94, 0x05, 0x7e, 0xef, 0x9d, 0x0c, 0x79, 0xe8, 0x9a, 0x0b, 0x6c, 0xfd, 0x8f, 0x1e, 0x6b, 0xfa, 0x88, 0x19, 0x62, 0xf3, 0x81, 0x10, 0x65, 0xf4, 0x86, 0x17, 0x48, 0xd9, 0xab, 0x3a, 0x4f, 0xde, 0xac, 0x3d, 0x46, 0xd7, 0xa5, 0x34, 0x41, 0xd0, 0xa2, 0x33, 0x54, 0xc5, 0xb7, 0x26, 0x53, 0xc2, 0xb0, 0x21, 0x5a, 0xcb, 0xb9, 0x28, 0x5d, 0xcc, 0xbe, 0x2f, 0xe0, 0x71, 0x03, 0x92, 0xe7, 0x76, 0x04, 0x95, 0xee, 0x7f, 0x0d, 0x9c, 0xe9, 0x78, 0x0a, 0x9b, 0xfc, 0x6d, 0x1f, 0x8e, 0xfb, 0x6a, 0x18, 0x89, 0xf2, 0x63, 0x11, 0x80, 0xf5, 0x64, 0x16, 0x87, 0xd8, 0x49, 0x3b, 0xaa, 0xdf, 0x4e, 0x3c, 0xad, 0xd6, 0x47, 0x35, 0xa4, 0xd1, 0x40, 0x32, 0xa3, 0xc4, 0x55, 0x27, 0xb6, 0xc3, 0x52, 0x20, 0xb1, 0xca, 0x5b, 0x29, 0xb8, 0xcd, 0x5c, 0x2e, 0xbf, 0x90, 0x01, 0x73, 0xe2, 0x97, 0x06, 0x74, 0xe5, 0x9e, 0x0f, 0x7d, 0xec, 0x99, 0x08, 0x7a, 0xeb, 0x8c, 0x1d, 0x6f, 0xfe, 0x8b, 0x1a, 0x68, 0xf9, 0x82, 0x13, 0x61, 0xf0, 0x85, 0x14, 0x66, 0xf7, 0xa8, 0x39, 0x4b, 0xda, 0xaf, 0x3e, 0x4c, 0xdd, 0xa6, 0x37, 0x45, 0xd4, 0xa1, 0x30, 0x42, 0xd3, 0xb4, 0x25, 0x57, 0xc6, 0xb3, 0x22, 0x50, 0xc1, 0xba, 0x2b, 0x59, 0xc8, 0xbd, 0x2c, 0x5e, 0xcf }; /* CRC on 2 bytes */ #define __crc(data) (rfcomm_crc_table[rfcomm_crc_table[0xff ^ data[0]] ^ data[1]]) /* FCS on 2 bytes */ static inline u8 __fcs(u8 *data) { return 0xff - __crc(data); } /* FCS on 3 bytes */ static inline u8 __fcs2(u8 *data) { return 0xff - rfcomm_crc_table[__crc(data) ^ data[2]]; } /* Check FCS */ static inline int __check_fcs(u8 *data, int type, u8 fcs) { u8 f = __crc(data); if (type != RFCOMM_UIH) f = rfcomm_crc_table[f ^ data[2]]; return rfcomm_crc_table[f ^ fcs] != 0xcf; } /* ---- L2CAP callbacks ---- */ static void rfcomm_l2state_change(struct sock *sk) { BT_DBG("%p state %d", sk, sk->sk_state); rfcomm_schedule(); } static void rfcomm_l2data_ready(struct sock *sk) { trace_sk_data_ready(sk); BT_DBG("%p", sk); rfcomm_schedule(); } static int rfcomm_l2sock_create(struct socket **sock) { int err; BT_DBG(""); err = sock_create_kern(&init_net, PF_BLUETOOTH, SOCK_SEQPACKET, BTPROTO_L2CAP, sock); if (!err) { struct sock *sk = (*sock)->sk; sk->sk_data_ready = rfcomm_l2data_ready; sk->sk_state_change = rfcomm_l2state_change; } return err; } static int rfcomm_check_security(struct rfcomm_dlc *d) { struct sock *sk = d->session->sock->sk; struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn; __u8 auth_type; switch (d->sec_level) { case BT_SECURITY_HIGH: case BT_SECURITY_FIPS: auth_type = HCI_AT_GENERAL_BONDING_MITM; break; case BT_SECURITY_MEDIUM: auth_type = HCI_AT_GENERAL_BONDING; break; default: auth_type = HCI_AT_NO_BONDING; break; } return hci_conn_security(conn->hcon, d->sec_level, auth_type, d->out); } static void rfcomm_session_timeout(struct timer_list *t) { struct rfcomm_session *s = timer_container_of(s, t, timer); BT_DBG("session %p state %ld", s, s->state); set_bit(RFCOMM_TIMED_OUT, &s->flags); rfcomm_schedule(); } static void rfcomm_session_set_timer(struct rfcomm_session *s, long timeout) { BT_DBG("session %p state %ld timeout %ld", s, s->state, timeout); mod_timer(&s->timer, jiffies + timeout); } static void rfcomm_session_clear_timer(struct rfcomm_session *s) { BT_DBG("session %p state %ld", s, s->state); timer_delete_sync(&s->timer); } /* ---- RFCOMM DLCs ---- */ static void rfcomm_dlc_timeout(struct timer_list *t) { struct rfcomm_dlc *d = timer_container_of(d, t, timer); BT_DBG("dlc %p state %ld", d, d->state); set_bit(RFCOMM_TIMED_OUT, &d->flags); rfcomm_dlc_put(d); rfcomm_schedule(); } static void rfcomm_dlc_set_timer(struct rfcomm_dlc *d, long timeout) { BT_DBG("dlc %p state %ld timeout %ld", d, d->state, timeout); if (!mod_timer(&d->timer, jiffies + timeout)) rfcomm_dlc_hold(d); } static void rfcomm_dlc_clear_timer(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); if (timer_delete(&d->timer)) rfcomm_dlc_put(d); } static void rfcomm_dlc_clear_state(struct rfcomm_dlc *d) { BT_DBG("%p", d); d->state = BT_OPEN; d->flags = 0; d->mscex = 0; d->sec_level = BT_SECURITY_LOW; d->mtu = RFCOMM_DEFAULT_MTU; d->v24_sig = RFCOMM_V24_RTC | RFCOMM_V24_RTR | RFCOMM_V24_DV; d->cfc = RFCOMM_CFC_DISABLED; d->rx_credits = RFCOMM_DEFAULT_CREDITS; } struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio) { struct rfcomm_dlc *d = kzalloc_obj(*d, prio); if (!d) return NULL; timer_setup(&d->timer, rfcomm_dlc_timeout, 0); skb_queue_head_init(&d->tx_queue); mutex_init(&d->lock); refcount_set(&d->refcnt, 1); rfcomm_dlc_clear_state(d); BT_DBG("%p", d); return d; } void rfcomm_dlc_free(struct rfcomm_dlc *d) { BT_DBG("%p", d); skb_queue_purge(&d->tx_queue); kfree(d); } static void rfcomm_dlc_link(struct rfcomm_session *s, struct rfcomm_dlc *d) { BT_DBG("dlc %p session %p", d, s); rfcomm_session_clear_timer(s); rfcomm_dlc_hold(d); list_add(&d->list, &s->dlcs); d->session = s; } static void rfcomm_dlc_unlink(struct rfcomm_dlc *d) { struct rfcomm_session *s = d->session; BT_DBG("dlc %p refcnt %d session %p", d, refcount_read(&d->refcnt), s); list_del(&d->list); d->session = NULL; rfcomm_dlc_put(d); if (list_empty(&s->dlcs)) rfcomm_session_set_timer(s, RFCOMM_IDLE_TIMEOUT); } static struct rfcomm_dlc *rfcomm_dlc_get(struct rfcomm_session *s, u8 dlci) { struct rfcomm_dlc *d; list_for_each_entry(d, &s->dlcs, list) if (d->dlci == dlci) return d; return NULL; } static int rfcomm_check_channel(u8 channel) { return channel < 1 || channel > 30; } static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel) { struct rfcomm_session *s; int err = 0; u8 dlci; BT_DBG("dlc %p state %ld %pMR -> %pMR channel %d", d, d->state, src, dst, channel); if (rfcomm_check_channel(channel)) return -EINVAL; if (d->state != BT_OPEN && d->state != BT_CLOSED) return 0; s = rfcomm_session_get(src, dst); if (!s) { s = rfcomm_session_create(src, dst, d->sec_level, &err); if (!s) return err; } dlci = __dlci(__session_dir(s), channel); /* Check if DLCI already exists */ if (rfcomm_dlc_get(s, dlci)) return -EBUSY; rfcomm_dlc_clear_state(d); d->dlci = dlci; d->addr = __addr(s->initiator, dlci); d->priority = 7; d->state = BT_CONFIG; rfcomm_dlc_link(s, d); d->out = 1; d->mtu = s->mtu; d->cfc = (s->cfc == RFCOMM_CFC_UNKNOWN) ? 0 : s->cfc; if (s->state == BT_CONNECTED) { if (rfcomm_check_security(d)) rfcomm_send_pn(s, 1, d); else set_bit(RFCOMM_AUTH_PENDING, &d->flags); } rfcomm_dlc_set_timer(d, RFCOMM_CONN_TIMEOUT); return 0; } int rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel) { int r; rfcomm_lock(); r = __rfcomm_dlc_open(d, src, dst, channel); rfcomm_unlock(); return r; } static void __rfcomm_dlc_disconn(struct rfcomm_dlc *d) { struct rfcomm_session *s = d->session; d->state = BT_DISCONN; if (skb_queue_empty(&d->tx_queue)) { rfcomm_send_disc(s, d->dlci); rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT); } else { rfcomm_queue_disc(d); rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2); } } static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) { struct rfcomm_session *s = d->session; if (!s) return 0; BT_DBG("dlc %p state %ld dlci %d err %d session %p", d, d->state, d->dlci, err, s); switch (d->state) { case BT_CONNECT: case BT_CONFIG: case BT_OPEN: case BT_CONNECT2: if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { set_bit(RFCOMM_AUTH_REJECT, &d->flags); rfcomm_schedule(); return 0; } } switch (d->state) { case BT_CONNECT: case BT_CONNECTED: __rfcomm_dlc_disconn(d); break; case BT_CONFIG: if (s->state != BT_BOUND) { __rfcomm_dlc_disconn(d); break; } /* if closing a dlc in a session that hasn't been started, * just close and unlink the dlc */ fallthrough; default: rfcomm_dlc_clear_timer(d); rfcomm_dlc_lock(d); d->state = BT_CLOSED; d->state_change(d, err); rfcomm_dlc_unlock(d); skb_queue_purge(&d->tx_queue); rfcomm_dlc_unlink(d); } return 0; } int rfcomm_dlc_close(struct rfcomm_dlc *d, int err) { int r = 0; struct rfcomm_dlc *d_list; struct rfcomm_session *s, *s_list; BT_DBG("dlc %p state %ld dlci %d err %d", d, d->state, d->dlci, err); rfcomm_lock(); s = d->session; if (!s) goto no_session; /* after waiting on the mutex check the session still exists * then check the dlc still exists */ list_for_each_entry(s_list, &session_list, list) { if (s_list == s) { list_for_each_entry(d_list, &s->dlcs, list) { if (d_list == d) { r = __rfcomm_dlc_close(d, err); break; } } break; } } no_session: rfcomm_unlock(); return r; } struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel) { struct rfcomm_session *s; struct rfcomm_dlc *dlc = NULL; u8 dlci; if (rfcomm_check_channel(channel)) return ERR_PTR(-EINVAL); rfcomm_lock(); s = rfcomm_session_get(src, dst); if (s) { dlci = __dlci(__session_dir(s), channel); dlc = rfcomm_dlc_get(s, dlci); } rfcomm_unlock(); return dlc; } static int rfcomm_dlc_send_frag(struct rfcomm_dlc *d, struct sk_buff *frag) { int len = frag->len; BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); if (len > d->mtu) return -EINVAL; rfcomm_make_uih(frag, d->addr); __skb_queue_tail(&d->tx_queue, frag); return len; } int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) { unsigned long flags; struct sk_buff *frag, *next; int len; if (d->state != BT_CONNECTED) return -ENOTCONN; frag = skb_shinfo(skb)->frag_list; skb_shinfo(skb)->frag_list = NULL; /* Queue all fragments atomically. */ spin_lock_irqsave(&d->tx_queue.lock, flags); len = rfcomm_dlc_send_frag(d, skb); if (len < 0 || !frag) goto unlock; for (; frag; frag = next) { int ret; next = frag->next; ret = rfcomm_dlc_send_frag(d, frag); if (ret < 0) { dev_kfree_skb_irq(frag); goto unlock; } len += ret; } unlock: spin_unlock_irqrestore(&d->tx_queue.lock, flags); if (len > 0 && !test_bit(RFCOMM_TX_THROTTLED, &d->flags)) rfcomm_schedule(); return len; } void rfcomm_dlc_send_noerror(struct rfcomm_dlc *d, struct sk_buff *skb) { int len = skb->len; BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); rfcomm_make_uih(skb, d->addr); skb_queue_tail(&d->tx_queue, skb); if (d->state == BT_CONNECTED && !test_bit(RFCOMM_TX_THROTTLED, &d->flags)) rfcomm_schedule(); } void __rfcomm_dlc_throttle(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); if (!d->cfc) { d->v24_sig |= RFCOMM_V24_FC; set_bit(RFCOMM_MSC_PENDING, &d->flags); } rfcomm_schedule(); } void __rfcomm_dlc_unthrottle(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); if (!d->cfc) { d->v24_sig &= ~RFCOMM_V24_FC; set_bit(RFCOMM_MSC_PENDING, &d->flags); } rfcomm_schedule(); } /* Set/get modem status functions use _local_ status i.e. what we report to the other side. Remote status is provided by dlc->modem_status() callback. */ int rfcomm_dlc_set_modem_status(struct rfcomm_dlc *d, u8 v24_sig) { BT_DBG("dlc %p state %ld v24_sig 0x%x", d, d->state, v24_sig); if (test_bit(RFCOMM_RX_THROTTLED, &d->flags)) v24_sig |= RFCOMM_V24_FC; else v24_sig &= ~RFCOMM_V24_FC; d->v24_sig = v24_sig; if (!test_and_set_bit(RFCOMM_MSC_PENDING, &d->flags)) rfcomm_schedule(); return 0; } int rfcomm_dlc_get_modem_status(struct rfcomm_dlc *d, u8 *v24_sig) { BT_DBG("dlc %p state %ld v24_sig 0x%x", d, d->state, d->v24_sig); *v24_sig = d->v24_sig; return 0; } /* ---- RFCOMM sessions ---- */ static struct rfcomm_session *rfcomm_session_add(struct socket *sock, int state) { struct rfcomm_session *s = kzalloc_obj(*s); if (!s) return NULL; BT_DBG("session %p sock %p", s, sock); timer_setup(&s->timer, rfcomm_session_timeout, 0); INIT_LIST_HEAD(&s->dlcs); s->state = state; s->sock = sock; s->mtu = RFCOMM_DEFAULT_MTU; s->cfc = disable_cfc ? RFCOMM_CFC_DISABLED : RFCOMM_CFC_UNKNOWN; /* Do not increment module usage count for listening sessions. * Otherwise we won't be able to unload the module. */ if (state != BT_LISTEN) if (!try_module_get(THIS_MODULE)) { kfree(s); return NULL; } list_add(&s->list, &session_list); return s; } static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s) { int state = s->state; BT_DBG("session %p state %ld", s, s->state); list_del(&s->list); rfcomm_session_clear_timer(s); sock_release(s->sock); kfree(s); if (state != BT_LISTEN) module_put(THIS_MODULE); return NULL; } static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst) { struct rfcomm_session *s, *n; struct l2cap_chan *chan; list_for_each_entry_safe(s, n, &session_list, list) { chan = l2cap_pi(s->sock->sk)->chan; if ((!bacmp(src, BDADDR_ANY) || !bacmp(&chan->src, src)) && !bacmp(&chan->dst, dst)) return s; } return NULL; } static struct rfcomm_session *rfcomm_session_close(struct rfcomm_session *s, int err) { struct rfcomm_dlc *d, *n; s->state = BT_CLOSED; BT_DBG("session %p state %ld err %d", s, s->state, err); /* Close all dlcs */ list_for_each_entry_safe(d, n, &s->dlcs, list) { d->state = BT_CLOSED; __rfcomm_dlc_close(d, err); } rfcomm_session_clear_timer(s); return rfcomm_session_del(s); } static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst, u8 sec_level, int *err) { struct rfcomm_session *s = NULL; struct sockaddr_l2 addr; struct socket *sock; struct sock *sk; BT_DBG("%pMR -> %pMR", src, dst); *err = rfcomm_l2sock_create(&sock); if (*err < 0) return NULL; bacpy(&addr.l2_bdaddr, src); addr.l2_family = AF_BLUETOOTH; addr.l2_psm = 0; addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; *err = kernel_bind(sock, (struct sockaddr_unsized *)&addr, sizeof(addr)); if (*err < 0) goto failed; /* Set L2CAP options */ sk = sock->sk; lock_sock(sk); /* Set MTU to 0 so L2CAP can auto select the MTU */ l2cap_pi(sk)->chan->imtu = 0; l2cap_pi(sk)->chan->sec_level = sec_level; if (l2cap_ertm) l2cap_pi(sk)->chan->mode = L2CAP_MODE_ERTM; release_sock(sk); s = rfcomm_session_add(sock, BT_BOUND); if (!s) { *err = -ENOMEM; goto failed; } s->initiator = 1; bacpy(&addr.l2_bdaddr, dst); addr.l2_family = AF_BLUETOOTH; addr.l2_psm = cpu_to_le16(L2CAP_PSM_RFCOMM); addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; *err = kernel_connect(sock, (struct sockaddr_unsized *)&addr, sizeof(addr), O_NONBLOCK); if (*err == 0 || *err == -EINPROGRESS) return s; return rfcomm_session_del(s); failed: sock_release(sock); return NULL; } void rfcomm_session_getaddr(struct rfcomm_session *s, bdaddr_t *src, bdaddr_t *dst) { struct l2cap_chan *chan = l2cap_pi(s->sock->sk)->chan; if (src) bacpy(src, &chan->src); if (dst) bacpy(dst, &chan->dst); } /* ---- RFCOMM frame sending ---- */ static int rfcomm_send_frame(struct rfcomm_session *s, u8 *data, int len) { struct kvec iv = { data, len }; struct msghdr msg; BT_DBG("session %p len %d", s, len); memset(&msg, 0, sizeof(msg)); return kernel_sendmsg(s->sock, &msg, &iv, 1, len); } static int rfcomm_send_cmd(struct rfcomm_session *s, struct rfcomm_cmd *cmd) { BT_DBG("%p cmd %u", s, cmd->ctrl); return rfcomm_send_frame(s, (void *) cmd, sizeof(*cmd)); } static int rfcomm_send_sabm(struct rfcomm_session *s, u8 dlci) { struct rfcomm_cmd cmd; BT_DBG("%p dlci %d", s, dlci); cmd.addr = __addr(s->initiator, dlci); cmd.ctrl = __ctrl(RFCOMM_SABM, 1); cmd.len = __len8(0); cmd.fcs = __fcs2((u8 *) &cmd); return rfcomm_send_cmd(s, &cmd); } static int rfcomm_send_ua(struct rfcomm_session *s, u8 dlci) { struct rfcomm_cmd cmd; BT_DBG("%p dlci %d", s, dlci); cmd.addr = __addr(!s->initiator, dlci); cmd.ctrl = __ctrl(RFCOMM_UA, 1); cmd.len = __len8(0); cmd.fcs = __fcs2((u8 *) &cmd); return rfcomm_send_cmd(s, &cmd); } static int rfcomm_send_disc(struct rfcomm_session *s, u8 dlci) { struct rfcomm_cmd cmd; BT_DBG("%p dlci %d", s, dlci); cmd.addr = __addr(s->initiator, dlci); cmd.ctrl = __ctrl(RFCOMM_DISC, 1); cmd.len = __len8(0); cmd.fcs = __fcs2((u8 *) &cmd); return rfcomm_send_cmd(s, &cmd); } static int rfcomm_queue_disc(struct rfcomm_dlc *d) { struct rfcomm_cmd *cmd; struct sk_buff *skb; BT_DBG("dlc %p dlci %d", d, d->dlci); skb = alloc_skb(sizeof(*cmd), GFP_KERNEL); if (!skb) return -ENOMEM; cmd = __skb_put(skb, sizeof(*cmd)); cmd->addr = d->addr; cmd->ctrl = __ctrl(RFCOMM_DISC, 1); cmd->len = __len8(0); cmd->fcs = __fcs2((u8 *) cmd); skb_queue_tail(&d->tx_queue, skb); rfcomm_schedule(); return 0; } static int rfcomm_send_dm(struct rfcomm_session *s, u8 dlci) { struct rfcomm_cmd cmd; BT_DBG("%p dlci %d", s, dlci); cmd.addr = __addr(!s->initiator, dlci); cmd.ctrl = __ctrl(RFCOMM_DM, 1); cmd.len = __len8(0); cmd.fcs = __fcs2((u8 *) &cmd); return rfcomm_send_cmd(s, &cmd); } static int rfcomm_send_nsc(struct rfcomm_session *s, int cr, u8 type) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d type %d", s, cr, type); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc) + 1); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(0, RFCOMM_NSC); mcc->len = __len8(1); /* Type that we didn't like */ *ptr = __mcc_type(cr, type); ptr++; *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } static int rfcomm_send_pn(struct rfcomm_session *s, int cr, struct rfcomm_dlc *d) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; struct rfcomm_pn *pn; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d dlci %d mtu %d", s, cr, d->dlci, d->mtu); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc) + sizeof(*pn)); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(cr, RFCOMM_PN); mcc->len = __len8(sizeof(*pn)); pn = (void *) ptr; ptr += sizeof(*pn); pn->dlci = d->dlci; pn->priority = d->priority; pn->ack_timer = 0; pn->max_retrans = 0; if (s->cfc) { pn->flow_ctrl = cr ? 0xf0 : 0xe0; pn->credits = RFCOMM_DEFAULT_CREDITS; } else { pn->flow_ctrl = 0; pn->credits = 0; } if (cr && channel_mtu >= 0) pn->mtu = cpu_to_le16(channel_mtu); else pn->mtu = cpu_to_le16(d->mtu); *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci, u8 bit_rate, u8 data_bits, u8 stop_bits, u8 parity, u8 flow_ctrl_settings, u8 xon_char, u8 xoff_char, u16 param_mask) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; struct rfcomm_rpn *rpn; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d dlci %d bit_r 0x%x data_b 0x%x stop_b 0x%x parity 0x%x" " flwc_s 0x%x xon_c 0x%x xoff_c 0x%x p_mask 0x%x", s, cr, dlci, bit_rate, data_bits, stop_bits, parity, flow_ctrl_settings, xon_char, xoff_char, param_mask); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc) + sizeof(*rpn)); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(cr, RFCOMM_RPN); mcc->len = __len8(sizeof(*rpn)); rpn = (void *) ptr; ptr += sizeof(*rpn); rpn->dlci = __addr(1, dlci); rpn->bit_rate = bit_rate; rpn->line_settings = __rpn_line_settings(data_bits, stop_bits, parity); rpn->flow_ctrl = flow_ctrl_settings; rpn->xon_char = xon_char; rpn->xoff_char = xoff_char; rpn->param_mask = cpu_to_le16(param_mask); *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } int rfcomm_dlc_send_rpn(struct rfcomm_dlc *d, u8 bit_rate, u8 data_bits, u8 stop_bits, u8 parity, u8 flow_ctrl_settings, u8 xon_char, u8 xoff_char, u16 param_mask) { int err = -ENOTCONN; rfcomm_lock(); if (d->session) err = rfcomm_send_rpn(d->session, 1, d->dlci, bit_rate, data_bits, stop_bits, parity, flow_ctrl_settings, xon_char, xoff_char, param_mask); rfcomm_unlock(); return err; } static int rfcomm_send_rls(struct rfcomm_session *s, int cr, u8 dlci, u8 status) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; struct rfcomm_rls *rls; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d status 0x%x", s, cr, status); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc) + sizeof(*rls)); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(cr, RFCOMM_RLS); mcc->len = __len8(sizeof(*rls)); rls = (void *) ptr; ptr += sizeof(*rls); rls->dlci = __addr(1, dlci); rls->status = status; *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } static int rfcomm_send_msc(struct rfcomm_session *s, int cr, u8 dlci, u8 v24_sig) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; struct rfcomm_msc *msc; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d v24 0x%x", s, cr, v24_sig); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc) + sizeof(*msc)); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(cr, RFCOMM_MSC); mcc->len = __len8(sizeof(*msc)); msc = (void *) ptr; ptr += sizeof(*msc); msc->dlci = __addr(1, dlci); msc->v24_sig = v24_sig | 0x01; *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } static int rfcomm_send_fcoff(struct rfcomm_session *s, int cr) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d", s, cr); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc)); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(cr, RFCOMM_FCOFF); mcc->len = __len8(0); *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } static int rfcomm_send_fcon(struct rfcomm_session *s, int cr) { struct rfcomm_hdr *hdr; struct rfcomm_mcc *mcc; u8 buf[16], *ptr = buf; BT_DBG("%p cr %d", s, cr); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = __addr(s->initiator, 0); hdr->ctrl = __ctrl(RFCOMM_UIH, 0); hdr->len = __len8(sizeof(*mcc)); mcc = (void *) ptr; ptr += sizeof(*mcc); mcc->type = __mcc_type(cr, RFCOMM_FCON); mcc->len = __len8(0); *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } static int rfcomm_send_test(struct rfcomm_session *s, int cr, u8 *pattern, int len) { struct socket *sock = s->sock; struct kvec iv[3]; struct msghdr msg; unsigned char hdr[5], crc[1]; if (len > 125) return -EINVAL; BT_DBG("%p cr %d", s, cr); hdr[0] = __addr(s->initiator, 0); hdr[1] = __ctrl(RFCOMM_UIH, 0); hdr[2] = 0x01 | ((len + 2) << 1); hdr[3] = 0x01 | ((cr & 0x01) << 1) | (RFCOMM_TEST << 2); hdr[4] = 0x01 | (len << 1); crc[0] = __fcs(hdr); iv[0].iov_base = hdr; iv[0].iov_len = 5; iv[1].iov_base = pattern; iv[1].iov_len = len; iv[2].iov_base = crc; iv[2].iov_len = 1; memset(&msg, 0, sizeof(msg)); return kernel_sendmsg(sock, &msg, iv, 3, 6 + len); } static int rfcomm_send_credits(struct rfcomm_session *s, u8 addr, u8 credits) { struct rfcomm_hdr *hdr; u8 buf[16], *ptr = buf; BT_DBG("%p addr %d credits %d", s, addr, credits); hdr = (void *) ptr; ptr += sizeof(*hdr); hdr->addr = addr; hdr->ctrl = __ctrl(RFCOMM_UIH, 1); hdr->len = __len8(0); *ptr = credits; ptr++; *ptr = __fcs(buf); ptr++; return rfcomm_send_frame(s, buf, ptr - buf); } static void rfcomm_make_uih(struct sk_buff *skb, u8 addr) { struct rfcomm_hdr *hdr; int len = skb->len; u8 *crc; if (len > 127) { hdr = skb_push(skb, 4); put_unaligned(cpu_to_le16(__len16(len)), (__le16 *) &hdr->len); } else { hdr = skb_push(skb, 3); hdr->len = __len8(len); } hdr->addr = addr; hdr->ctrl = __ctrl(RFCOMM_UIH, 0); crc = skb_put(skb, 1); *crc = __fcs((void *) hdr); } /* ---- RFCOMM frame reception ---- */ static struct rfcomm_session *rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) { BT_DBG("session %p state %ld dlci %d", s, s->state, dlci); if (dlci) { /* Data channel */ struct rfcomm_dlc *d = rfcomm_dlc_get(s, dlci); if (!d) { rfcomm_send_dm(s, dlci); return s; } switch (d->state) { case BT_CONNECT: rfcomm_dlc_clear_timer(d); rfcomm_dlc_lock(d); d->state = BT_CONNECTED; d->state_change(d, 0); rfcomm_dlc_unlock(d); rfcomm_send_msc(s, 1, dlci, d->v24_sig); break; case BT_DISCONN: d->state = BT_CLOSED; __rfcomm_dlc_close(d, 0); if (list_empty(&s->dlcs)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); rfcomm_session_clear_timer(s); } break; } } else { /* Control channel */ switch (s->state) { case BT_CONNECT: s->state = BT_CONNECTED; rfcomm_process_connect(s); break; case BT_DISCONN: s = rfcomm_session_close(s, ECONNRESET); break; } } return s; } static struct rfcomm_session *rfcomm_recv_dm(struct rfcomm_session *s, u8 dlci) { int err = 0; BT_DBG("session %p state %ld dlci %d", s, s->state, dlci); if (dlci) { /* Data DLC */ struct rfcomm_dlc *d = rfcomm_dlc_get(s, dlci); if (d) { if (d->state == BT_CONNECT || d->state == BT_CONFIG) err = ECONNREFUSED; else err = ECONNRESET; d->state = BT_CLOSED; __rfcomm_dlc_close(d, err); } } else { if (s->state == BT_CONNECT) err = ECONNREFUSED; else err = ECONNRESET; s = rfcomm_session_close(s, err); } return s; } static struct rfcomm_session *rfcomm_recv_disc(struct rfcomm_session *s, u8 dlci) { int err = 0; BT_DBG("session %p state %ld dlci %d", s, s->state, dlci); if (dlci) { struct rfcomm_dlc *d = rfcomm_dlc_get(s, dlci); if (d) { rfcomm_send_ua(s, dlci); if (d->state == BT_CONNECT || d->state == BT_CONFIG) err = ECONNREFUSED; else err = ECONNRESET; d->state = BT_CLOSED; __rfcomm_dlc_close(d, err); } else rfcomm_send_dm(s, dlci); } else { rfcomm_send_ua(s, 0); if (s->state == BT_CONNECT) err = ECONNREFUSED; else err = ECONNRESET; s = rfcomm_session_close(s, err); } return s; } /* Must be called with rfcomm_mutex held, so that the session cannot be * unlinked from under us. */ static void __rfcomm_dlc_accept(struct rfcomm_dlc *d) { struct sock *sk = d->session->sock->sk; struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn; BT_DBG("dlc %p", d); rfcomm_send_ua(d->session, d->dlci); rfcomm_dlc_clear_timer(d); rfcomm_dlc_lock(d); d->state = BT_CONNECTED; d->state_change(d, 0); rfcomm_dlc_unlock(d); if (d->role_switch) hci_conn_switch_role(conn->hcon, 0x00); rfcomm_send_msc(d->session, 1, d->dlci, d->v24_sig); } void rfcomm_dlc_accept(struct rfcomm_dlc *d) { rfcomm_lock(); /* rfcomm_recv_disc() sets the dlc state to BT_CLOSED before calling * __rfcomm_dlc_close(), so the RFCOMM_DEFER_SETUP handshake there is * skipped and the session can already be unlinked by the time the * deferred accept runs from rfcomm_sock_recvmsg(). */ if (d->session) __rfcomm_dlc_accept(d); rfcomm_unlock(); } static void rfcomm_check_accept(struct rfcomm_dlc *d) { if (rfcomm_check_security(d)) { if (d->defer_setup) { set_bit(RFCOMM_DEFER_SETUP, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); rfcomm_dlc_lock(d); d->state = BT_CONNECT2; d->state_change(d, 0); rfcomm_dlc_unlock(d); } else __rfcomm_dlc_accept(d); } else { set_bit(RFCOMM_AUTH_PENDING, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); } } static int rfcomm_recv_sabm(struct rfcomm_session *s, u8 dlci) { struct rfcomm_dlc *d; u8 channel; BT_DBG("session %p state %ld dlci %d", s, s->state, dlci); if (!dlci) { rfcomm_send_ua(s, 0); if (s->state == BT_OPEN) { s->state = BT_CONNECTED; rfcomm_process_connect(s); } return 0; } /* Check if DLC exists */ d = rfcomm_dlc_get(s, dlci); if (d) { if (d->state == BT_OPEN) { /* DLC was previously opened by PN request */ rfcomm_check_accept(d); } return 0; } /* Notify socket layer about incoming connection */ channel = __srv_channel(dlci); if (rfcomm_connect_ind(s, channel, &d)) { d->dlci = dlci; d->addr = __addr(s->initiator, dlci); rfcomm_dlc_link(s, d); rfcomm_check_accept(d); } else { rfcomm_send_dm(s, dlci); } return 0; } static int rfcomm_apply_pn(struct rfcomm_dlc *d, int cr, struct rfcomm_pn *pn) { struct rfcomm_session *s = d->session; BT_DBG("dlc %p state %ld dlci %d mtu %d fc 0x%x credits %d", d, d->state, d->dlci, pn->mtu, pn->flow_ctrl, pn->credits); if ((pn->flow_ctrl == 0xf0 && s->cfc != RFCOMM_CFC_DISABLED) || pn->flow_ctrl == 0xe0) { d->cfc = RFCOMM_CFC_ENABLED; d->tx_credits = pn->credits; } else { d->cfc = RFCOMM_CFC_DISABLED; set_bit(RFCOMM_TX_THROTTLED, &d->flags); } if (s->cfc == RFCOMM_CFC_UNKNOWN) s->cfc = d->cfc; d->priority = pn->priority; d->mtu = __le16_to_cpu(pn->mtu); /* MTU 0 causes an infinite loop when fragmenting in sendmsg */ if (!d->mtu) d->mtu = RFCOMM_DEFAULT_MTU; if (cr && d->mtu > s->mtu) d->mtu = s->mtu; return 0; } static int rfcomm_recv_pn(struct rfcomm_session *s, int cr, struct sk_buff *skb) { struct rfcomm_pn *pn; struct rfcomm_dlc *d; u8 dlci; pn = skb_pull_data(skb, sizeof(*pn)); if (!pn) return -EILSEQ; dlci = pn->dlci; BT_DBG("session %p state %ld dlci %d", s, s->state, dlci); if (!dlci) return 0; d = rfcomm_dlc_get(s, dlci); if (d) { if (cr) { /* PN request */ rfcomm_apply_pn(d, cr, pn); rfcomm_send_pn(s, 0, d); } else { /* PN response */ switch (d->state) { case BT_CONFIG: rfcomm_apply_pn(d, cr, pn); d->state = BT_CONNECT; rfcomm_send_sabm(s, d->dlci); break; } } } else { u8 channel = __srv_channel(dlci); if (!cr) return 0; /* PN request for non existing DLC. * Assume incoming connection. */ if (rfcomm_connect_ind(s, channel, &d)) { d->dlci = dlci; d->addr = __addr(s->initiator, dlci); rfcomm_dlc_link(s, d); rfcomm_apply_pn(d, cr, pn); d->state = BT_OPEN; rfcomm_send_pn(s, 0, d); } else { rfcomm_send_dm(s, dlci); } } return 0; } static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_buff *skb) { struct rfcomm_rpn *rpn; u8 dlci; u8 bit_rate = 0; u8 data_bits = 0; u8 stop_bits = 0; u8 parity = 0; u8 flow_ctrl = 0; u8 xon_char = 0; u8 xoff_char = 0; u16 rpn_mask = RFCOMM_RPN_PM_ALL; if (len == 1) { rpn = skb_pull_data(skb, 1); if (!rpn) return -EILSEQ; dlci = __get_dlci(rpn->dlci); if (!cr) return 0; bit_rate = RFCOMM_RPN_BR_9600; data_bits = RFCOMM_RPN_DATA_8; stop_bits = RFCOMM_RPN_STOP_1; parity = RFCOMM_RPN_PARITY_NONE; flow_ctrl = RFCOMM_RPN_FLOW_NONE; xon_char = RFCOMM_RPN_XON_CHAR; xoff_char = RFCOMM_RPN_XOFF_CHAR; goto rpn_out; } rpn = skb_pull_data(skb, sizeof(*rpn)); if (!rpn) return -EILSEQ; dlci = __get_dlci(rpn->dlci); BT_DBG("dlci %d cr %d len 0x%x bitr 0x%x line 0x%x flow 0x%x xonc 0x%x xoffc 0x%x pm 0x%x", dlci, cr, len, rpn->bit_rate, rpn->line_settings, rpn->flow_ctrl, rpn->xon_char, rpn->xoff_char, rpn->param_mask); if (!cr) return 0; /* Check for sane values, ignore/accept bit_rate, 8 bits, 1 stop bit, * no parity, no flow control lines, normal XON/XOFF chars */ if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_BITRATE)) { bit_rate = rpn->bit_rate; if (bit_rate > RFCOMM_RPN_BR_230400) { BT_DBG("RPN bit rate mismatch 0x%x", bit_rate); bit_rate = RFCOMM_RPN_BR_9600; rpn_mask ^= RFCOMM_RPN_PM_BITRATE; } } if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_DATA)) { data_bits = __get_rpn_data_bits(rpn->line_settings); if (data_bits != RFCOMM_RPN_DATA_8) { BT_DBG("RPN data bits mismatch 0x%x", data_bits); data_bits = RFCOMM_RPN_DATA_8; rpn_mask ^= RFCOMM_RPN_PM_DATA; } } if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_STOP)) { stop_bits = __get_rpn_stop_bits(rpn->line_settings); if (stop_bits != RFCOMM_RPN_STOP_1) { BT_DBG("RPN stop bits mismatch 0x%x", stop_bits); stop_bits = RFCOMM_RPN_STOP_1; rpn_mask ^= RFCOMM_RPN_PM_STOP; } } if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_PARITY)) { parity = __get_rpn_parity(rpn->line_settings); if (parity != RFCOMM_RPN_PARITY_NONE) { BT_DBG("RPN parity mismatch 0x%x", parity); parity = RFCOMM_RPN_PARITY_NONE; rpn_mask ^= RFCOMM_RPN_PM_PARITY; } } if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_FLOW)) { flow_ctrl = rpn->flow_ctrl; if (flow_ctrl != RFCOMM_RPN_FLOW_NONE) { BT_DBG("RPN flow ctrl mismatch 0x%x", flow_ctrl); flow_ctrl = RFCOMM_RPN_FLOW_NONE; rpn_mask ^= RFCOMM_RPN_PM_FLOW; } } if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_XON)) { xon_char = rpn->xon_char; if (xon_char != RFCOMM_RPN_XON_CHAR) { BT_DBG("RPN XON char mismatch 0x%x", xon_char); xon_char = RFCOMM_RPN_XON_CHAR; rpn_mask ^= RFCOMM_RPN_PM_XON; } } if (rpn->param_mask & cpu_to_le16(RFCOMM_RPN_PM_XOFF)) { xoff_char = rpn->xoff_char; if (xoff_char != RFCOMM_RPN_XOFF_CHAR) { BT_DBG("RPN XOFF char mismatch 0x%x", xoff_char); xoff_char = RFCOMM_RPN_XOFF_CHAR; rpn_mask ^= RFCOMM_RPN_PM_XOFF; } } rpn_out: rfcomm_send_rpn(s, 0, dlci, bit_rate, data_bits, stop_bits, parity, flow_ctrl, xon_char, xoff_char, rpn_mask); return 0; } static int rfcomm_recv_rls(struct rfcomm_session *s, int cr, struct sk_buff *skb) { struct rfcomm_rls *rls; u8 dlci; rls = skb_pull_data(skb, sizeof(*rls)); if (!rls) return -EILSEQ; dlci = __get_dlci(rls->dlci); BT_DBG("dlci %d cr %d status 0x%x", dlci, cr, rls->status); if (!cr) return 0; /* We should probably do something with this information here. But * for now it's sufficient just to reply -- Bluetooth 1.1 says it's * mandatory to recognise and respond to RLS */ rfcomm_send_rls(s, 0, dlci, rls->status); return 0; } static int rfcomm_recv_msc(struct rfcomm_session *s, int cr, struct sk_buff *skb) { struct rfcomm_msc *msc; struct rfcomm_dlc *d; u8 dlci; msc = skb_pull_data(skb, sizeof(*msc)); if (!msc) return -EILSEQ; dlci = __get_dlci(msc->dlci); BT_DBG("dlci %d cr %d v24 0x%x", dlci, cr, msc->v24_sig); d = rfcomm_dlc_get(s, dlci); if (!d) return 0; if (cr) { if (msc->v24_sig & RFCOMM_V24_FC && !d->cfc) set_bit(RFCOMM_TX_THROTTLED, &d->flags); else clear_bit(RFCOMM_TX_THROTTLED, &d->flags); rfcomm_dlc_lock(d); d->remote_v24_sig = msc->v24_sig; if (d->modem_status) d->modem_status(d, msc->v24_sig); rfcomm_dlc_unlock(d); rfcomm_send_msc(s, 0, dlci, msc->v24_sig); d->mscex |= RFCOMM_MSCEX_RX; } else d->mscex |= RFCOMM_MSCEX_TX; return 0; } static int rfcomm_recv_mcc(struct rfcomm_session *s, struct sk_buff *skb) { struct rfcomm_mcc *mcc; u8 type, cr, len; mcc = skb_pull_data(skb, sizeof(*mcc)); if (!mcc) return -EILSEQ; cr = __test_cr(mcc->type); type = __get_mcc_type(mcc->type); len = __get_mcc_len(mcc->len); BT_DBG("%p type 0x%x cr %d", s, type, cr); switch (type) { case RFCOMM_PN: rfcomm_recv_pn(s, cr, skb); break; case RFCOMM_RPN: rfcomm_recv_rpn(s, cr, len, skb); break; case RFCOMM_RLS: rfcomm_recv_rls(s, cr, skb); break; case RFCOMM_MSC: rfcomm_recv_msc(s, cr, skb); break; case RFCOMM_FCOFF: if (cr) { set_bit(RFCOMM_TX_THROTTLED, &s->flags); rfcomm_send_fcoff(s, 0); } break; case RFCOMM_FCON: if (cr) { clear_bit(RFCOMM_TX_THROTTLED, &s->flags); rfcomm_send_fcon(s, 0); } break; case RFCOMM_TEST: if (cr) rfcomm_send_test(s, 0, skb->data, skb->len); break; case RFCOMM_NSC: break; default: BT_ERR("Unknown control type 0x%02x", type); rfcomm_send_nsc(s, cr, type); break; } return 0; } static int rfcomm_recv_data(struct rfcomm_session *s, u8 dlci, int pf, struct sk_buff *skb) { struct rfcomm_dlc *d; BT_DBG("session %p state %ld dlci %d pf %d", s, s->state, dlci, pf); d = rfcomm_dlc_get(s, dlci); if (!d) { rfcomm_send_dm(s, dlci); goto drop; } if (pf && d->cfc) { u8 *credits = skb_pull_data(skb, 1); if (!credits) goto drop; d->tx_credits += *credits; if (d->tx_credits) clear_bit(RFCOMM_TX_THROTTLED, &d->flags); } if (skb->len && d->state == BT_CONNECTED) { rfcomm_dlc_lock(d); d->rx_credits--; d->data_ready(d, skb); rfcomm_dlc_unlock(d); return 0; } drop: kfree_skb(skb); return 0; } static struct rfcomm_session *rfcomm_recv_frame(struct rfcomm_session *s, struct sk_buff *skb) { struct rfcomm_hdr *hdr = (void *) skb->data; u8 type, dlci, fcs; if (!s) { /* no session, so free socket data */ kfree_skb(skb); return s; } if (skb->len < sizeof(*hdr) + 1) { kfree_skb(skb); return s; } dlci = __get_dlci(hdr->addr); type = __get_type(hdr->ctrl); /* Trim FCS */ skb->len--; skb->tail--; fcs = *(u8 *)skb_tail_pointer(skb); if (__check_fcs(skb->data, type, fcs)) { BT_ERR("bad checksum in packet"); kfree_skb(skb); return s; } if (__test_ea(hdr->len)) skb_pull(skb, 3); else skb_pull(skb, 4); switch (type) { case RFCOMM_SABM: if (__test_pf(hdr->ctrl)) rfcomm_recv_sabm(s, dlci); break; case RFCOMM_DISC: if (__test_pf(hdr->ctrl)) s = rfcomm_recv_disc(s, dlci); break; case RFCOMM_UA: if (__test_pf(hdr->ctrl)) s = rfcomm_recv_ua(s, dlci); break; case RFCOMM_DM: s = rfcomm_recv_dm(s, dlci); break; case RFCOMM_UIH: if (dlci) { rfcomm_recv_data(s, dlci, __test_pf(hdr->ctrl), skb); return s; } rfcomm_recv_mcc(s, skb); break; default: BT_ERR("Unknown packet type 0x%02x", type); break; } kfree_skb(skb); return s; } /* ---- Connection and data processing ---- */ static void rfcomm_process_connect(struct rfcomm_session *s) { struct rfcomm_dlc *d, *n; BT_DBG("session %p state %ld", s, s->state); list_for_each_entry_safe(d, n, &s->dlcs, list) { if (d->state == BT_CONFIG) { d->mtu = s->mtu; if (rfcomm_check_security(d)) { rfcomm_send_pn(s, 1, d); } else { set_bit(RFCOMM_AUTH_PENDING, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); } } } } /* Send data queued for the DLC. * Return number of frames left in the queue. */ static int rfcomm_process_tx(struct rfcomm_dlc *d) { struct sk_buff *skb; int err; BT_DBG("dlc %p state %ld cfc %d rx_credits %d tx_credits %d", d, d->state, d->cfc, d->rx_credits, d->tx_credits); /* Send pending MSC */ if (test_and_clear_bit(RFCOMM_MSC_PENDING, &d->flags)) rfcomm_send_msc(d->session, 1, d->dlci, d->v24_sig); if (d->cfc) { /* CFC enabled. * Give them some credits */ if (!test_bit(RFCOMM_RX_THROTTLED, &d->flags) && d->rx_credits <= (d->cfc >> 2)) { rfcomm_send_credits(d->session, d->addr, d->cfc - d->rx_credits); d->rx_credits = d->cfc; } } else { /* CFC disabled. * Give ourselves some credits */ d->tx_credits = 5; } if (test_bit(RFCOMM_TX_THROTTLED, &d->flags)) return skb_queue_len(&d->tx_queue); while (d->tx_credits && (skb = skb_dequeue(&d->tx_queue))) { err = rfcomm_send_frame(d->session, skb->data, skb->len); if (err < 0) { skb_queue_head(&d->tx_queue, skb); break; } kfree_skb(skb); d->tx_credits--; } if (d->cfc && !d->tx_credits) { /* We're out of TX credits. * Set TX_THROTTLED flag to avoid unnesary wakeups by dlc_send. */ set_bit(RFCOMM_TX_THROTTLED, &d->flags); } return skb_queue_len(&d->tx_queue); } static void rfcomm_process_dlcs(struct rfcomm_session *s) { struct rfcomm_dlc *d, *n; BT_DBG("session %p state %ld", s, s->state); list_for_each_entry_safe(d, n, &s->dlcs, list) { if (test_bit(RFCOMM_TIMED_OUT, &d->flags)) { __rfcomm_dlc_close(d, ETIMEDOUT); continue; } if (test_bit(RFCOMM_ENC_DROP, &d->flags)) { __rfcomm_dlc_close(d, ECONNREFUSED); continue; } if (test_and_clear_bit(RFCOMM_AUTH_ACCEPT, &d->flags)) { rfcomm_dlc_clear_timer(d); if (d->out) { rfcomm_send_pn(s, 1, d); rfcomm_dlc_set_timer(d, RFCOMM_CONN_TIMEOUT); } else { if (d->defer_setup) { set_bit(RFCOMM_DEFER_SETUP, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); rfcomm_dlc_lock(d); d->state = BT_CONNECT2; d->state_change(d, 0); rfcomm_dlc_unlock(d); } else __rfcomm_dlc_accept(d); } continue; } else if (test_and_clear_bit(RFCOMM_AUTH_REJECT, &d->flags)) { rfcomm_dlc_clear_timer(d); if (!d->out) rfcomm_send_dm(s, d->dlci); else d->state = BT_CLOSED; __rfcomm_dlc_close(d, ECONNREFUSED); continue; } if (test_bit(RFCOMM_SEC_PENDING, &d->flags)) continue; if (test_bit(RFCOMM_TX_THROTTLED, &s->flags)) continue; if ((d->state == BT_CONNECTED || d->state == BT_DISCONN) && d->mscex == RFCOMM_MSCEX_OK) rfcomm_process_tx(d); } } static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) { struct socket *sock = s->sock; struct sock *sk = sock->sk; struct sk_buff *skb; BT_DBG("session %p state %ld qlen %d", s, s->state, skb_queue_len(&sk->sk_receive_queue)); /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) { s = rfcomm_recv_frame(s, skb); if (!s) break; } else { kfree_skb(skb); } } if (s && (sk->sk_state == BT_CLOSED)) s = rfcomm_session_close(s, sk->sk_err); return s; } static void rfcomm_accept_connection(struct rfcomm_session *s) { struct socket *sock = s->sock, *nsock; int err; /* Fast check for a new connection. * Avoids unnecessary socket allocations. */ if (list_empty(&bt_sk(sock->sk)->accept_q)) return; BT_DBG("session %p", s); err = kernel_accept(sock, &nsock, O_NONBLOCK); if (err < 0) return; /* Set our callbacks */ nsock->sk->sk_data_ready = rfcomm_l2data_ready; nsock->sk->sk_state_change = rfcomm_l2state_change; s = rfcomm_session_add(nsock, BT_OPEN); if (s) { /* We should adjust MTU on incoming sessions. * L2CAP MTU minus UIH header and FCS. */ s->mtu = min(l2cap_pi(nsock->sk)->chan->omtu, l2cap_pi(nsock->sk)->chan->imtu) - 5; rfcomm_schedule(); } else sock_release(nsock); } static struct rfcomm_session *rfcomm_check_connection(struct rfcomm_session *s) { struct sock *sk = s->sock->sk; BT_DBG("%p state %ld", s, s->state); switch (sk->sk_state) { case BT_CONNECTED: s->state = BT_CONNECT; /* We can adjust MTU on outgoing sessions. * L2CAP MTU minus UIH header and FCS. */ s->mtu = min(l2cap_pi(sk)->chan->omtu, l2cap_pi(sk)->chan->imtu) - 5; rfcomm_send_sabm(s, 0); break; case BT_CLOSED: s = rfcomm_session_close(s, sk->sk_err); break; } return s; } static void rfcomm_process_sessions(void) { struct rfcomm_session *s, *n; rfcomm_lock(); list_for_each_entry_safe(s, n, &session_list, list) { if (test_and_clear_bit(RFCOMM_TIMED_OUT, &s->flags)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); continue; } switch (s->state) { case BT_LISTEN: rfcomm_accept_connection(s); continue; case BT_BOUND: s = rfcomm_check_connection(s); break; default: s = rfcomm_process_rx(s); break; } if (s) rfcomm_process_dlcs(s); } rfcomm_unlock(); } static int rfcomm_add_listener(bdaddr_t *ba) { struct sockaddr_l2 addr; struct socket *sock; struct sock *sk; struct rfcomm_session *s; int err = 0; /* Create socket */ err = rfcomm_l2sock_create(&sock); if (err < 0) { BT_ERR("Create socket failed %d", err); return err; } /* Bind socket */ bacpy(&addr.l2_bdaddr, ba); addr.l2_family = AF_BLUETOOTH; addr.l2_psm = cpu_to_le16(L2CAP_PSM_RFCOMM); addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; err = kernel_bind(sock, (struct sockaddr_unsized *)&addr, sizeof(addr)); if (err < 0) { BT_ERR("Bind failed %d", err); goto failed; } /* Set L2CAP options */ sk = sock->sk; lock_sock(sk); /* Set MTU to 0 so L2CAP can auto select the MTU */ l2cap_pi(sk)->chan->imtu = 0; release_sock(sk); /* Start listening on the socket */ err = kernel_listen(sock, 10); if (err) { BT_ERR("Listen failed %d", err); goto failed; } /* Add listening session */ s = rfcomm_session_add(sock, BT_LISTEN); if (!s) { err = -ENOMEM; goto failed; } return 0; failed: sock_release(sock); return err; } static void rfcomm_kill_listener(void) { struct rfcomm_session *s, *n; BT_DBG(""); rfcomm_lock(); list_for_each_entry_safe(s, n, &session_list, list) rfcomm_session_del(s); rfcomm_unlock(); } static int rfcomm_run(void *unused) { DEFINE_WAIT_FUNC(wait, woken_wake_function); BT_DBG(""); set_user_nice(current, -10); rfcomm_add_listener(BDADDR_ANY); add_wait_queue(&rfcomm_wq, &wait); while (!kthread_should_stop()) { /* Process stuff */ rfcomm_process_sessions(); wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); } remove_wait_queue(&rfcomm_wq, &wait); rfcomm_kill_listener(); return 0; } static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) { struct rfcomm_session *s; struct rfcomm_dlc *d, *n; BT_DBG("conn %p status 0x%02x encrypt 0x%02x", conn, status, encrypt); rfcomm_lock(); s = rfcomm_session_get(&conn->hdev->bdaddr, &conn->dst); if (!s) { rfcomm_unlock(); return; } list_for_each_entry_safe(d, n, &s->dlcs, list) { if (test_and_clear_bit(RFCOMM_SEC_PENDING, &d->flags)) { rfcomm_dlc_clear_timer(d); if (status || encrypt == 0x00) { set_bit(RFCOMM_ENC_DROP, &d->flags); continue; } } if (d->state == BT_CONNECTED && !status && encrypt == 0x00) { if (d->sec_level == BT_SECURITY_MEDIUM) { set_bit(RFCOMM_SEC_PENDING, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); continue; } else if (d->sec_level == BT_SECURITY_HIGH || d->sec_level == BT_SECURITY_FIPS) { set_bit(RFCOMM_ENC_DROP, &d->flags); continue; } } if (!test_and_clear_bit(RFCOMM_AUTH_PENDING, &d->flags)) continue; if (!status && hci_conn_check_secure(conn, d->sec_level)) set_bit(RFCOMM_AUTH_ACCEPT, &d->flags); else set_bit(RFCOMM_AUTH_REJECT, &d->flags); } rfcomm_unlock(); rfcomm_schedule(); } static struct hci_cb rfcomm_cb = { .name = "RFCOMM", .security_cfm = rfcomm_security_cfm }; static int rfcomm_dlc_debugfs_show(struct seq_file *f, void *x) { struct rfcomm_session *s; rfcomm_lock(); list_for_each_entry(s, &session_list, list) { struct l2cap_chan *chan = l2cap_pi(s->sock->sk)->chan; struct rfcomm_dlc *d; list_for_each_entry(d, &s->dlcs, list) { seq_printf(f, "%pMR %pMR %ld %d %d %d %d\n", &chan->src, &chan->dst, d->state, d->dlci, d->mtu, d->rx_credits, d->tx_credits); } } rfcomm_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(rfcomm_dlc_debugfs); static struct dentry *rfcomm_dlc_debugfs; /* ---- Initialization ---- */ static int __init rfcomm_init(void) { int err; hci_register_cb(&rfcomm_cb); rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd"); if (IS_ERR(rfcomm_thread)) { err = PTR_ERR(rfcomm_thread); goto unregister; } err = rfcomm_init_ttys(); if (err < 0) goto stop; err = rfcomm_init_sockets(); if (err < 0) goto cleanup; BT_INFO("RFCOMM ver %s", VERSION); if (IS_ERR_OR_NULL(bt_debugfs)) return 0; rfcomm_dlc_debugfs = debugfs_create_file("rfcomm_dlc", 0444, bt_debugfs, NULL, &rfcomm_dlc_debugfs_fops); return 0; cleanup: rfcomm_cleanup_ttys(); stop: kthread_stop(rfcomm_thread); unregister: hci_unregister_cb(&rfcomm_cb); return err; } static void __exit rfcomm_exit(void) { debugfs_remove(rfcomm_dlc_debugfs); hci_unregister_cb(&rfcomm_cb); kthread_stop(rfcomm_thread); rfcomm_cleanup_ttys(); rfcomm_cleanup_sockets(); } module_init(rfcomm_init); module_exit(rfcomm_exit); module_param(disable_cfc, bool, 0644); MODULE_PARM_DESC(disable_cfc, "Disable credit based flow control"); module_param(channel_mtu, int, 0644); MODULE_PARM_DESC(channel_mtu, "Default MTU for the RFCOMM channel"); module_param(l2cap_ertm, bool, 0644); MODULE_PARM_DESC(l2cap_ertm, "Use L2CAP ERTM mode for connection"); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth RFCOMM ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS("bt-proto-3"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/utsname.h> #include <net/cfg80211.h> #include "core.h" #include "rdev-ops.h" void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct device *pdev = wiphy_dev(wdev->wiphy); if (pdev->driver) strscpy(info->driver, pdev->driver->name, sizeof(info->driver)); else strscpy(info->driver, "N/A", sizeof(info->driver)); strscpy(info->version, init_utsname()->release, sizeof(info->version)); if (wdev->wiphy->fw_version[0]) strscpy(info->fw_version, wdev->wiphy->fw_version, sizeof(info->fw_version)); else strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); strscpy(info->bus_info, dev_name(pdev), sizeof(info->bus_info)); } EXPORT_SYMBOL(cfg80211_get_drvinfo); |
| 45 20 95 | 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 * * FUSE: Filesystem in Userspace * Copyright (c) 2023-2024 DataDirect Networks. */ #ifndef _FS_FUSE_DEV_URING_I_H #define _FS_FUSE_DEV_URING_I_H #include <linux/uio.h> #include "fuse_dev_i.h" #ifdef CONFIG_FUSE_IO_URING #define FUSE_URING_TEARDOWN_TIMEOUT (5 * HZ) #define FUSE_URING_TEARDOWN_INTERVAL (HZ/20) enum fuse_ring_req_state { FRRS_INVALID = 0, /* The ring entry received from userspace and it is being processed */ FRRS_COMMIT, /* The ring entry is waiting for new fuse requests */ FRRS_AVAILABLE, /* The ring entry got assigned a fuse req */ FRRS_FUSE_REQ, /* The ring entry is in or on the way to user space */ FRRS_USERSPACE, /* The ring entry is in teardown */ FRRS_TEARDOWN, /* The ring entry is released, but not freed yet */ FRRS_RELEASED, }; /* how a queue's payload buffers are provided */ enum fuse_queue_payload_mode { /* not yet committed (a bufpool may still be added) */ FUSE_PAYLOAD_UNSET = 0, /* each entry registers its own payload buffer */ FUSE_PAYLOAD_PER_ENT, /* each entry's payload buffer is assigned from a bufpool */ FUSE_PAYLOAD_BUFPOOL, }; struct fuse_bufpool { bool registered; /* * io_uring registered buffer table index for this pool, bound at * ADD_BUFPOOL time. Only valid if the bufpool is registered */ u16 registered_index; /* starting uaddr of the bufpool */ uintptr_t base_uaddr; /* size of each buffer in the pool */ size_t buf_size; /* total number of buffers in the pool */ unsigned int nr_bufs; /* bitmap tracking which buffers are free */ unsigned long free_map[]; }; /** A fuse ring entry, part of the ring queue */ struct fuse_ring_ent { /* userspace buffer */ struct fuse_uring_req_header __user *headers; struct iovec payload; /* buffer id in the pool, if bufpools are used. ignored otherwise */ unsigned int buf_id; /* true if the request's pages are being zero-copied */ bool zero_copied; unsigned int zero_copy_index; /* the ring queue that owns the request */ struct fuse_ring_queue *queue; /* fields below are protected by queue->lock */ struct io_uring_cmd *cmd; struct list_head list; enum fuse_ring_req_state state; struct fuse_req *fuse_req; }; struct fuse_ring_queue { /* * back pointer to the main fuse uring structure that holds this * queue */ struct fuse_ring *ring; /* queue id, corresponds to the cpu core */ unsigned int qid; /* * queue lock, taken when any value in the queue changes _and_ also * a ring entry state changes. */ spinlock_t lock; /* available ring entries (struct fuse_ring_ent) */ struct list_head ent_avail_queue; /* * entries in the process of being committed or in the process * to be sent to userspace */ struct list_head ent_w_req_queue; struct list_head ent_commit_queue; /* entries in userspace */ struct list_head ent_in_userspace; /* entries that are released */ struct list_head ent_released; /* fuse requests waiting for an entry slot */ struct list_head fuse_req_queue; /* background fuse requests */ struct list_head fuse_req_bg_queue; struct fuse_pqueue fpq; unsigned int active_background; bool stopped; /* how this queue's payload buffers are provided */ enum fuse_queue_payload_mode payload_mode; /* only allocated when payload_mode == FUSE_PAYLOAD_BUFPOOL */ struct fuse_bufpool *bufpool; bool zero_copy; }; /* * Describes if uring is for communication and holds alls the data needed * for uring communication */ struct fuse_ring { /* back pointer */ struct fuse_chan *chan; /* number of ring queues */ size_t nr_queues; /* maximum payload/arg size */ size_t max_payload_sz; struct fuse_ring_queue **queues; /* * Log ring entry states on stop when entries cannot be released */ unsigned int stop_debug_log : 1; wait_queue_head_t stop_waitq; /* async tear down */ struct delayed_work async_teardown_work; /* log */ unsigned long teardown_time; atomic_t queue_refs; bool ready; }; void fuse_uring_conn_init(struct fuse_chan *fch); void fuse_uring_stop_queues(struct fuse_ring *ring); void fuse_uring_abort_end_requests(struct fuse_ring *ring); int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req); bool fuse_uring_queue_bq_req(struct fuse_req *req); bool fuse_uring_remove_pending_req(struct fuse_req *req); bool fuse_uring_request_expired(struct fuse_chan *fch); static inline void fuse_uring_abort(struct fuse_chan *fch) { struct fuse_ring *ring = fch->ring; if (ring == NULL) return; fuse_uring_abort_end_requests(ring); if (atomic_read(&ring->queue_refs) > 0) fuse_uring_stop_queues(ring); } static inline void fuse_uring_wait_stopped_queues(struct fuse_chan *fch) { struct fuse_ring *ring = fch->ring; if (ring) wait_event(ring->stop_waitq, atomic_read(&ring->queue_refs) == 0); } static inline bool fuse_uring_ready(struct fuse_chan *fch) { struct fuse_ring *ring = READ_ONCE(fch->ring); return ring && smp_load_acquire(&ring->ready); } #else /* CONFIG_FUSE_IO_URING */ static inline void fuse_uring_conn_init(struct fuse_chan *fch) { } static inline void fuse_uring_abort(struct fuse_chan *fch) { } static inline void fuse_uring_wait_stopped_queues(struct fuse_chan *fch) { } static inline bool fuse_uring_ready(struct fuse_chan *fch) { return false; } static inline bool fuse_uring_remove_pending_req(struct fuse_req *req) { return false; } static inline bool fuse_uring_request_expired(struct fuse_chan *fch) { return false; } #endif /* CONFIG_FUSE_IO_URING */ #endif /* _FS_FUSE_DEV_URING_I_H */ |
| 6 6 6 9 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * * Author: Artem Bityutskiy (Битюцкий Артём) */ /* Here we keep miscellaneous functions which are used all over the UBI code */ #include "ubi.h" /** * ubi_calc_data_len - calculate how much real data is stored in a buffer. * @ubi: UBI device description object * @buf: a buffer with the contents of the physical eraseblock * @length: the buffer length * * This function calculates how much "real data" is stored in @buf and returnes * the length. Continuous 0xFF bytes at the end of the buffer are not * considered as "real data". */ int ubi_calc_data_len(const struct ubi_device *ubi, const void *buf, int length) { int i; ubi_assert(!(length & (ubi->min_io_size - 1))); for (i = length - 1; i >= 0; i--) if (((const uint8_t *)buf)[i] != 0xFF) break; /* The resulting length must be aligned to the minimum flash I/O size */ length = ALIGN(i + 1, ubi->min_io_size); return length; } /** * ubi_check_volume - check the contents of a static volume. * @ubi: UBI device description object * @vol_id: ID of the volume to check * * This function checks if static volume @vol_id is corrupted by fully reading * it and checking data CRC. This function returns %0 if the volume is not * corrupted, %1 if it is corrupted and a negative error code in case of * failure. Dynamic volumes are not checked and zero is returned immediately. */ int ubi_check_volume(struct ubi_device *ubi, int vol_id) { void *buf; int err = 0, i; struct ubi_volume *vol = ubi->volumes[vol_id]; if (vol->vol_type != UBI_STATIC_VOLUME) return 0; buf = vmalloc(vol->usable_leb_size); if (!buf) return -ENOMEM; for (i = 0; i < vol->used_ebs; i++) { int size; cond_resched(); if (i == vol->used_ebs - 1) size = vol->last_eb_bytes; else size = vol->usable_leb_size; err = ubi_eba_read_leb(ubi, vol, i, buf, 0, size, 1); if (err) { if (mtd_is_eccerr(err)) err = 1; break; } } vfree(buf); return err; } /** * ubi_update_reserved - update bad eraseblock handling accounting data. * @ubi: UBI device description object * * This function calculates the gap between current number of PEBs reserved for * bad eraseblock handling and the required level of PEBs that must be * reserved, and if necessary, reserves more PEBs to fill that gap, according * to availability. Should be called with ubi->volumes_lock held. */ void ubi_update_reserved(struct ubi_device *ubi) { int need = ubi->beb_rsvd_level - ubi->beb_rsvd_pebs; if (need <= 0 || ubi->avail_pebs == 0) return; need = min_t(int, need, ubi->avail_pebs); ubi->avail_pebs -= need; ubi->rsvd_pebs += need; ubi->beb_rsvd_pebs += need; ubi_msg(ubi, "reserved more %d PEBs for bad PEB handling", need); } /** * ubi_calculate_reserved - calculate how many PEBs must be reserved for bad * eraseblock handling. * @ubi: UBI device description object */ void ubi_calculate_reserved(struct ubi_device *ubi) { /* * Calculate the actual number of PEBs currently needed to be reserved * for future bad eraseblock handling. */ ubi->beb_rsvd_level = ubi->bad_peb_limit - ubi->bad_peb_count; if (ubi->beb_rsvd_level < 0) { ubi->beb_rsvd_level = 0; ubi_warn(ubi, "number of bad PEBs (%d) is above the expected limit (%d), not reserving any PEBs for bad PEB handling, will use available PEBs (if any)", ubi->bad_peb_count, ubi->bad_peb_limit); } } /** * ubi_check_pattern - check if buffer contains only a certain byte pattern. * @buf: buffer to check * @patt: the pattern to check * @size: buffer size in bytes * * This function returns %1 in there are only @patt bytes in @buf, and %0 if * something else was also found. */ int ubi_check_pattern(const void *buf, uint8_t patt, int size) { int i; for (i = 0; i < size; i++) if (((const uint8_t *)buf)[i] != patt) return 0; return 1; } /* Normal UBI messages */ void ubi_msg(const struct ubi_device *ubi, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_notice(UBI_NAME_STR "%d: %pV\n", ubi->ubi_num, &vaf); va_end(args); } /* UBI warning messages */ void ubi_warn(const struct ubi_device *ubi, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_warn(UBI_NAME_STR "%d warning: %ps: %pV\n", ubi->ubi_num, __builtin_return_address(0), &vaf); va_end(args); } /* UBI error messages */ void ubi_err(const struct ubi_device *ubi, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_err(UBI_NAME_STR "%d error: %ps: %pV\n", ubi->ubi_num, __builtin_return_address(0), &vaf); va_end(args); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common USB debugging functions * * Copyright (C) 2010-2011 Texas Instruments Incorporated - https://www.ti.com * * Authors: Felipe Balbi <balbi@ti.com>, * Sebastian Andrzej Siewior <bigeasy@linutronix.de> */ #include <linux/kernel.h> #include <linux/usb/ch9.h> static void usb_decode_get_status(__u8 bRequestType, __u16 wIndex, __u16 wLength, char *str, size_t size) { switch (bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: snprintf(str, size, "Get Device Status(Length = %d)", wLength); break; case USB_RECIP_INTERFACE: snprintf(str, size, "Get Interface Status(Intf = %d, Length = %d)", wIndex, wLength); break; case USB_RECIP_ENDPOINT: snprintf(str, size, "Get Endpoint Status(ep%d%s)", wIndex & ~USB_DIR_IN, wIndex & USB_DIR_IN ? "in" : "out"); break; } } static const char *usb_decode_device_feature(u16 wValue) { switch (wValue) { case USB_DEVICE_SELF_POWERED: return "Self Powered"; case USB_DEVICE_REMOTE_WAKEUP: return "Remote Wakeup"; case USB_DEVICE_TEST_MODE: return "Test Mode"; case USB_DEVICE_U1_ENABLE: return "U1 Enable"; case USB_DEVICE_U2_ENABLE: return "U2 Enable"; case USB_DEVICE_LTM_ENABLE: return "LTM Enable"; default: return "UNKNOWN"; } } static const char *usb_decode_test_mode(u16 wIndex) { switch (wIndex) { case USB_TEST_J: return ": TEST_J"; case USB_TEST_K: return ": TEST_K"; case USB_TEST_SE0_NAK: return ": TEST_SE0_NAK"; case USB_TEST_PACKET: return ": TEST_PACKET"; case USB_TEST_FORCE_ENABLE: return ": TEST_FORCE_EN"; default: return ": UNKNOWN"; } } static void usb_decode_set_clear_feature(__u8 bRequestType, __u8 bRequest, __u16 wValue, __u16 wIndex, char *str, size_t size) { switch (bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: snprintf(str, size, "%s Device Feature(%s%s)", bRequest == USB_REQ_CLEAR_FEATURE ? "Clear" : "Set", usb_decode_device_feature(wValue), wValue == USB_DEVICE_TEST_MODE ? usb_decode_test_mode(wIndex) : ""); break; case USB_RECIP_INTERFACE: snprintf(str, size, "%s Interface Feature(%s)", bRequest == USB_REQ_CLEAR_FEATURE ? "Clear" : "Set", wValue == USB_INTRF_FUNC_SUSPEND ? "Function Suspend" : "UNKNOWN"); break; case USB_RECIP_ENDPOINT: snprintf(str, size, "%s Endpoint Feature(%s ep%d%s)", bRequest == USB_REQ_CLEAR_FEATURE ? "Clear" : "Set", wValue == USB_ENDPOINT_HALT ? "Halt" : "UNKNOWN", wIndex & ~USB_DIR_IN, wIndex & USB_DIR_IN ? "in" : "out"); break; } } static void usb_decode_set_address(__u16 wValue, char *str, size_t size) { snprintf(str, size, "Set Address(Addr = %02x)", wValue); } static void usb_decode_get_set_descriptor(__u8 bRequestType, __u8 bRequest, __u16 wValue, __u16 wIndex, __u16 wLength, char *str, size_t size) { char *s; switch (wValue >> 8) { case USB_DT_DEVICE: s = "Device"; break; case USB_DT_CONFIG: s = "Configuration"; break; case USB_DT_STRING: s = "String"; break; case USB_DT_INTERFACE: s = "Interface"; break; case USB_DT_ENDPOINT: s = "Endpoint"; break; case USB_DT_DEVICE_QUALIFIER: s = "Device Qualifier"; break; case USB_DT_OTHER_SPEED_CONFIG: s = "Other Speed Config"; break; case USB_DT_INTERFACE_POWER: s = "Interface Power"; break; case USB_DT_OTG: s = "OTG"; break; case USB_DT_DEBUG: s = "Debug"; break; case USB_DT_INTERFACE_ASSOCIATION: s = "Interface Association"; break; case USB_DT_BOS: s = "BOS"; break; case USB_DT_DEVICE_CAPABILITY: s = "Device Capability"; break; case USB_DT_PIPE_USAGE: s = "Pipe Usage"; break; case USB_DT_SS_ENDPOINT_COMP: s = "SS Endpoint Companion"; break; case USB_DT_SSP_ISOC_ENDPOINT_COMP: s = "SSP Isochronous Endpoint Companion"; break; default: s = "UNKNOWN"; break; } snprintf(str, size, "%s %s Descriptor(Index = %d, Length = %d)", bRequest == USB_REQ_GET_DESCRIPTOR ? "Get" : "Set", s, wValue & 0xff, wLength); } static void usb_decode_get_configuration(__u16 wLength, char *str, size_t size) { snprintf(str, size, "Get Configuration(Length = %d)", wLength); } static void usb_decode_set_configuration(__u8 wValue, char *str, size_t size) { snprintf(str, size, "Set Configuration(Config = %d)", wValue); } static void usb_decode_get_intf(__u16 wIndex, __u16 wLength, char *str, size_t size) { snprintf(str, size, "Get Interface(Intf = %d, Length = %d)", wIndex, wLength); } static void usb_decode_set_intf(__u8 wValue, __u16 wIndex, char *str, size_t size) { snprintf(str, size, "Set Interface(Intf = %d, Alt.Setting = %d)", wIndex, wValue); } static void usb_decode_synch_frame(__u16 wIndex, __u16 wLength, char *str, size_t size) { snprintf(str, size, "Synch Frame(Endpoint = %d, Length = %d)", wIndex, wLength); } static void usb_decode_set_sel(__u16 wLength, char *str, size_t size) { snprintf(str, size, "Set SEL(Length = %d)", wLength); } static void usb_decode_set_isoch_delay(__u8 wValue, char *str, size_t size) { snprintf(str, size, "Set Isochronous Delay(Delay = %d ns)", wValue); } static void usb_decode_ctrl_generic(char *str, size_t size, __u8 bRequestType, __u8 bRequest, __u16 wValue, __u16 wIndex, __u16 wLength) { u8 recip = bRequestType & USB_RECIP_MASK; u8 type = bRequestType & USB_TYPE_MASK; snprintf(str, size, "Type=%s Recipient=%s Dir=%s bRequest=%u wValue=%u wIndex=%u wLength=%u", (type == USB_TYPE_STANDARD) ? "Standard" : (type == USB_TYPE_VENDOR) ? "Vendor" : (type == USB_TYPE_CLASS) ? "Class" : "Unknown", (recip == USB_RECIP_DEVICE) ? "Device" : (recip == USB_RECIP_INTERFACE) ? "Interface" : (recip == USB_RECIP_ENDPOINT) ? "Endpoint" : "Unknown", (bRequestType & USB_DIR_IN) ? "IN" : "OUT", bRequest, wValue, wIndex, wLength); } static void usb_decode_ctrl_standard(char *str, size_t size, __u8 bRequestType, __u8 bRequest, __u16 wValue, __u16 wIndex, __u16 wLength) { switch (bRequest) { case USB_REQ_GET_STATUS: usb_decode_get_status(bRequestType, wIndex, wLength, str, size); break; case USB_REQ_CLEAR_FEATURE: case USB_REQ_SET_FEATURE: usb_decode_set_clear_feature(bRequestType, bRequest, wValue, wIndex, str, size); break; case USB_REQ_SET_ADDRESS: usb_decode_set_address(wValue, str, size); break; case USB_REQ_GET_DESCRIPTOR: case USB_REQ_SET_DESCRIPTOR: usb_decode_get_set_descriptor(bRequestType, bRequest, wValue, wIndex, wLength, str, size); break; case USB_REQ_GET_CONFIGURATION: usb_decode_get_configuration(wLength, str, size); break; case USB_REQ_SET_CONFIGURATION: usb_decode_set_configuration(wValue, str, size); break; case USB_REQ_GET_INTERFACE: usb_decode_get_intf(wIndex, wLength, str, size); break; case USB_REQ_SET_INTERFACE: usb_decode_set_intf(wValue, wIndex, str, size); break; case USB_REQ_SYNCH_FRAME: usb_decode_synch_frame(wIndex, wLength, str, size); break; case USB_REQ_SET_SEL: usb_decode_set_sel(wLength, str, size); break; case USB_REQ_SET_ISOCH_DELAY: usb_decode_set_isoch_delay(wValue, str, size); break; default: usb_decode_ctrl_generic(str, size, bRequestType, bRequest, wValue, wIndex, wLength); break; } } /** * usb_decode_ctrl - Returns human readable representation of control request. * @str: buffer to return a human-readable representation of control request. * This buffer should have about 200 bytes. * @size: size of str buffer. * @bRequestType: matches the USB bmRequestType field * @bRequest: matches the USB bRequest field * @wValue: matches the USB wValue field (CPU byte order) * @wIndex: matches the USB wIndex field (CPU byte order) * @wLength: matches the USB wLength field (CPU byte order) * * Function returns decoded, formatted and human-readable description of * control request packet. * * The usage scenario for this is for tracepoints, so function as a return * use the same value as in parameters. This approach allows to use this * function in TP_printk * * Important: wValue, wIndex, wLength parameters before invoking this function * should be processed by le16_to_cpu macro. */ const char *usb_decode_ctrl(char *str, size_t size, __u8 bRequestType, __u8 bRequest, __u16 wValue, __u16 wIndex, __u16 wLength) { switch (bRequestType & USB_TYPE_MASK) { case USB_TYPE_STANDARD: usb_decode_ctrl_standard(str, size, bRequestType, bRequest, wValue, wIndex, wLength); break; case USB_TYPE_VENDOR: case USB_TYPE_CLASS: default: usb_decode_ctrl_generic(str, size, bRequestType, bRequest, wValue, wIndex, wLength); break; } return str; } EXPORT_SYMBOL_GPL(usb_decode_ctrl); |
| 34 19 16 9 5 7 3 9 8 4 4 11 9 3 5 6 6 6 12 12 12 9 6 3 3 5 5 5 5 5 5 4 4 3 3 3 3 3 1 1 2 3 1 1 1 4 2 7 3 4 7 2 1 1 3 1 2 1 1 1 3 3 1 1 2 2 3 2 17 1 12 11 1 12 12 12 8 4 15 15 10 2 5 9 71 3 12 8 30 10 11 2 18 19 50 5 4 2 2 2 6 10 4 7 1 4 3 3 1 5 5 5 1 1 5 11 6 5 5 5 6 6 1 1 1 2 1 7 19 13 1 11 4 4 5 5 7 7 1 1 5 5 1 1 1 114 3 91 15 42 69 1 43 70 106 3 13 15 2 84 1 2 115 1 1 1 109 105 102 94 13 25 103 117 118 9 9 1 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001, 2002 Sistina Software (UK) Limited. * Copyright (C) 2004 - 2006 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ #include "dm-core.h" #include "dm-ima.h" #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/miscdevice.h> #include <linux/sched/mm.h> #include <linux/init.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/dm-ioctl.h> #include <linux/hdreg.h> #include <linux/compat.h> #include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/ima.h> #define DM_MSG_PREFIX "ioctl" #define DM_DRIVER_EMAIL "dm-devel@lists.linux.dev" struct dm_file { /* * poll will wait until the global event number is greater than * this value. */ volatile unsigned int global_event_nr; }; /* *--------------------------------------------------------------- * The ioctl interface needs to be able to look up devices by * name or uuid. *--------------------------------------------------------------- */ struct hash_cell { struct rb_node name_node; struct rb_node uuid_node; bool name_set; bool uuid_set; char *name; char *uuid; struct mapped_device *md; struct dm_table *new_map; }; struct vers_iter { struct dm_target_versions *vers, *old_vers; char *end; }; static struct rb_root name_rb_tree = RB_ROOT; static struct rb_root uuid_rb_tree = RB_ROOT; #define DM_REMOVE_KEEP_OPEN_DEVICES 1 #define DM_REMOVE_MARK_DEFERRED 2 #define DM_REMOVE_ONLY_DEFERRED 4 #define DM_REMOVE_INTERRUPTIBLE 8 static int dm_hash_remove_all(unsigned flags); /* * Guards access to both hash tables. */ static DECLARE_RWSEM(_hash_lock); /* * Protects use of mdptr to obtain hash cell name and uuid from mapped device. */ static DEFINE_MUTEX(dm_hash_cells_mutex); static void dm_hash_exit(void) { dm_hash_remove_all(0); } /* *--------------------------------------------------------------- * Code for looking up a device by name *--------------------------------------------------------------- */ static struct hash_cell *__get_name_cell(const char *str) { struct rb_node *n = name_rb_tree.rb_node; while (n) { struct hash_cell *hc = container_of(n, struct hash_cell, name_node); int c; c = strcmp(hc->name, str); if (!c) { dm_get(hc->md); return hc; } n = c >= 0 ? n->rb_left : n->rb_right; } return NULL; } static struct hash_cell *__get_uuid_cell(const char *str) { struct rb_node *n = uuid_rb_tree.rb_node; while (n) { struct hash_cell *hc = container_of(n, struct hash_cell, uuid_node); int c; c = strcmp(hc->uuid, str); if (!c) { dm_get(hc->md); return hc; } n = c >= 0 ? n->rb_left : n->rb_right; } return NULL; } static void __unlink_name(struct hash_cell *hc) { if (hc->name_set) { hc->name_set = false; rb_erase(&hc->name_node, &name_rb_tree); } } static void __unlink_uuid(struct hash_cell *hc) { if (hc->uuid_set) { hc->uuid_set = false; rb_erase(&hc->uuid_node, &uuid_rb_tree); } } static void __link_name(struct hash_cell *new_hc) { struct rb_node **n, *parent; __unlink_name(new_hc); new_hc->name_set = true; n = &name_rb_tree.rb_node; parent = NULL; while (*n) { struct hash_cell *hc = container_of(*n, struct hash_cell, name_node); int c; c = strcmp(hc->name, new_hc->name); BUG_ON(!c); parent = *n; n = c >= 0 ? &hc->name_node.rb_left : &hc->name_node.rb_right; } rb_link_node(&new_hc->name_node, parent, n); rb_insert_color(&new_hc->name_node, &name_rb_tree); } static void __link_uuid(struct hash_cell *new_hc) { struct rb_node **n, *parent; __unlink_uuid(new_hc); new_hc->uuid_set = true; n = &uuid_rb_tree.rb_node; parent = NULL; while (*n) { struct hash_cell *hc = container_of(*n, struct hash_cell, uuid_node); int c; c = strcmp(hc->uuid, new_hc->uuid); BUG_ON(!c); parent = *n; n = c > 0 ? &hc->uuid_node.rb_left : &hc->uuid_node.rb_right; } rb_link_node(&new_hc->uuid_node, parent, n); rb_insert_color(&new_hc->uuid_node, &uuid_rb_tree); } static struct hash_cell *__get_dev_cell(uint64_t dev) { struct mapped_device *md; struct hash_cell *hc; md = dm_get_md(huge_decode_dev(dev)); if (!md) return NULL; hc = dm_get_mdptr(md); if (!hc) { dm_put(md); return NULL; } return hc; } /* *--------------------------------------------------------------- * Inserting, removing and renaming a device. *--------------------------------------------------------------- */ static struct hash_cell *alloc_cell(const char *name, const char *uuid, struct mapped_device *md) { struct hash_cell *hc; hc = kmalloc_obj(*hc); if (!hc) return NULL; hc->name = kstrdup(name, GFP_KERNEL); if (!hc->name) { kfree(hc); return NULL; } if (!uuid) hc->uuid = NULL; else { hc->uuid = kstrdup(uuid, GFP_KERNEL); if (!hc->uuid) { kfree(hc->name); kfree(hc); return NULL; } } hc->name_set = hc->uuid_set = false; hc->md = md; hc->new_map = NULL; return hc; } static void free_cell(struct hash_cell *hc) { if (hc) { kfree(hc->name); kfree(hc->uuid); kfree(hc); } } #ifdef CONFIG_IMA /* * Called while holding to _hash_lock, to guarantee the ordering of the * following dm_ima_measure_on_* functions, which should be called * right after dropping the _hash_lock */ static unsigned int dm_ima_init_context(struct hash_cell *hc, struct dm_ima_context *context, bool need_idx) { lockdep_assert_held(&_hash_lock); if (unlikely(!context)) return need_idx ? hc->md->ima.update_idx++ : 0; context->update_idx = hc->md->ima.update_idx++; strcpy(context->dev_name, hc->name); strcpy(context->dev_uuid, hc->uuid ? : ""); return context->update_idx; } /* * Called by do_resume() to guarantee correct ordering, since do_resume() * does not grab the _hash_lock when the table is not getting swapped or * when actually swapping the active table */ static bool dm_ima_need_measure(struct mapped_device *md, struct dm_table *table, struct dm_ima_context *context) { int srcu_idx; struct hash_cell *hc; bool need_measure = false; if (unlikely(!context)) return false; down_write(&_hash_lock); /* Check if the device has been removed */ hc = dm_get_mdptr(md); if (hc) { /* * If we have a table, we need to make sure that it's the * active table. Otherwise we raced with another process * setting the active table and it will do the measurement */ if (!table || dm_get_live_table(md, &srcu_idx) == table) { dm_ima_init_context(hc, context, false); need_measure = true; } if (table) dm_put_live_table(md, srcu_idx); } up_write(&_hash_lock); return need_measure; } #else static inline unsigned int dm_ima_init_context(struct hash_cell *hc, struct dm_ima_context *context, bool neex_idx) { return 0; } static inline bool dm_ima_need_measure(struct mapped_device *md, struct dm_table *table, struct dm_ima_context *context) { return false; } #endif /* * The kdev_t and uuid of a device can never change once it is * initially inserted. */ static int dm_hash_insert(const char *name, const char *uuid, struct mapped_device *md) { struct hash_cell *cell, *hc; /* * Allocate the new cells. */ cell = alloc_cell(name, uuid, md); if (!cell) return -ENOMEM; /* * Insert the cell into both hash tables. */ down_write(&_hash_lock); hc = __get_name_cell(name); if (hc) { dm_put(hc->md); goto bad; } __link_name(cell); if (uuid) { hc = __get_uuid_cell(uuid); if (hc) { __unlink_name(cell); dm_put(hc->md); goto bad; } __link_uuid(cell); } dm_get(md); mutex_lock(&dm_hash_cells_mutex); dm_set_mdptr(md, cell); mutex_unlock(&dm_hash_cells_mutex); up_write(&_hash_lock); return 0; bad: up_write(&_hash_lock); free_cell(cell); return -EBUSY; } static struct dm_table *__hash_remove(struct hash_cell *hc) { struct dm_table *table; int srcu_idx; lockdep_assert_held(&_hash_lock); /* remove from the dev trees */ __unlink_name(hc); __unlink_uuid(hc); mutex_lock(&dm_hash_cells_mutex); dm_set_mdptr(hc->md, NULL); mutex_unlock(&dm_hash_cells_mutex); table = dm_get_live_table(hc->md, &srcu_idx); if (table) dm_table_event(table); dm_put_live_table(hc->md, srcu_idx); table = NULL; if (hc->new_map) table = hc->new_map; dm_put(hc->md); free_cell(hc); return table; } static int dm_hash_remove_all(unsigned flags) { int dev_skipped; struct rb_node *n; struct hash_cell *hc; struct mapped_device *md; struct dm_table *t; struct dm_ima_context *ima_context = NULL; unsigned int ima_idx; dm_ima_alloc_context(&ima_context, true); retry: dev_skipped = 0; down_write(&_hash_lock); for (n = rb_first(&name_rb_tree); n; n = rb_next(n)) { if (flags & DM_REMOVE_INTERRUPTIBLE && fatal_signal_pending(current)) { up_write(&_hash_lock); dm_ima_free_context(ima_context); return -EINTR; } hc = container_of(n, struct hash_cell, name_node); md = hc->md; dm_get(md); if (flags & DM_REMOVE_KEEP_OPEN_DEVICES && dm_lock_for_deletion(md, !!(flags & DM_REMOVE_MARK_DEFERRED), !!(flags & DM_REMOVE_ONLY_DEFERRED))) { dm_put(md); dev_skipped++; continue; } ima_idx = dm_ima_init_context(hc, ima_context, true); t = __hash_remove(hc); up_write(&_hash_lock); if (t) { dm_sync_table(md); dm_table_destroy(t); } dm_ima_measure_on_device_remove(md, true, ima_context, ima_idx); dm_put(md); if (likely(flags & DM_REMOVE_KEEP_OPEN_DEVICES)) dm_destroy(md); else dm_destroy_immediate(md); /* * Some mapped devices may be using other mapped * devices, so repeat until we make no further * progress. If a new mapped device is created * here it will also get removed. */ goto retry; } up_write(&_hash_lock); if (dev_skipped && !(flags & DM_REMOVE_ONLY_DEFERRED)) DMWARN("remove_all left %d open device(s)", dev_skipped); dm_ima_free_context(ima_context); return 0; } /* * Set the uuid of a hash_cell that isn't already set. */ static void __set_cell_uuid(struct hash_cell *hc, char *new_uuid) { mutex_lock(&dm_hash_cells_mutex); hc->uuid = new_uuid; mutex_unlock(&dm_hash_cells_mutex); __link_uuid(hc); } /* * Changes the name of a hash_cell and returns the old name for * the caller to free. */ static char *__change_cell_name(struct hash_cell *hc, char *new_name) { char *old_name; /* * Rename and move the name cell. */ __unlink_name(hc); old_name = hc->name; mutex_lock(&dm_hash_cells_mutex); hc->name = new_name; mutex_unlock(&dm_hash_cells_mutex); __link_name(hc); return old_name; } static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, const char *new) { char *new_data, *old_name = NULL; struct hash_cell *hc; struct dm_table *table; struct mapped_device *md; unsigned int change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; int srcu_idx; struct dm_ima_context *ima_context = NULL; /* * duplicate new. */ new_data = kstrdup(new, GFP_KERNEL); if (!new_data) return ERR_PTR(-ENOMEM); dm_ima_alloc_context(&ima_context, true); down_write(&_hash_lock); /* * Is new free ? */ if (change_uuid) hc = __get_uuid_cell(new); else hc = __get_name_cell(new); if (hc) { DMERR("Unable to change %s on mapped device %s to one that already exists: %s", change_uuid ? "uuid" : "name", param->name, new); dm_put(hc->md); up_write(&_hash_lock); dm_ima_free_context(ima_context); kfree(new_data); return ERR_PTR(-EBUSY); } /* * Is there such a device as 'old' ? */ hc = __get_name_cell(param->name); if (!hc) { DMERR("Unable to rename non-existent device, %s to %s%s", param->name, change_uuid ? "uuid " : "", new); up_write(&_hash_lock); dm_ima_free_context(ima_context); kfree(new_data); return ERR_PTR(-ENXIO); } /* * Does this device already have a uuid? */ if (change_uuid && hc->uuid) { DMERR("Unable to change uuid of mapped device %s to %s " "because uuid is already set to %s", param->name, new, hc->uuid); dm_put(hc->md); up_write(&_hash_lock); dm_ima_free_context(ima_context); kfree(new_data); return ERR_PTR(-EINVAL); } if (change_uuid) __set_cell_uuid(hc, new_data); else old_name = __change_cell_name(hc, new_data); /* * Wake up any dm event waiters. */ table = dm_get_live_table(hc->md, &srcu_idx); if (table) dm_table_event(table); dm_put_live_table(hc->md, srcu_idx); if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, param->event_nr, false)) param->flags |= DM_UEVENT_GENERATED_FLAG; md = hc->md; dm_ima_init_context(hc, ima_context, false); up_write(&_hash_lock); dm_ima_measure_on_device_rename(md, ima_context); dm_ima_free_context(ima_context); kfree(old_name); return md; } void dm_deferred_remove(void) { dm_hash_remove_all(DM_REMOVE_KEEP_OPEN_DEVICES | DM_REMOVE_ONLY_DEFERRED); } /* *--------------------------------------------------------------- * Implementation of the ioctl commands *--------------------------------------------------------------- */ /* * All the ioctl commands get dispatched to functions with this * prototype. */ typedef int (*ioctl_fn)(struct file *filp, struct dm_ioctl *param, size_t param_size); static int remove_all(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r; int flags = DM_REMOVE_KEEP_OPEN_DEVICES | DM_REMOVE_INTERRUPTIBLE; if (param->flags & DM_DEFERRED_REMOVE) flags |= DM_REMOVE_MARK_DEFERRED; r = dm_hash_remove_all(flags); param->data_size = 0; return r; } /* * Round up the ptr to an 8-byte boundary. */ #define ALIGN_MASK 7 static inline size_t align_val(size_t val) { return (val + ALIGN_MASK) & ~ALIGN_MASK; } static inline void *align_ptr(void *ptr) { return (void *)align_val((size_t)ptr); } /* * Retrieves the data payload buffer from an already allocated * struct dm_ioctl. */ static void *get_result_buffer(struct dm_ioctl *param, size_t param_size, size_t *len) { param->data_start = align_ptr(param + 1) - (void *) param; if (param->data_start < param_size) *len = param_size - param->data_start; else *len = 0; return ((void *) param) + param->data_start; } static bool filter_device(struct hash_cell *hc, const char *pfx_name, const char *pfx_uuid) { const char *val; size_t val_len, pfx_len; val = hc->name; val_len = strlen(val); pfx_len = strnlen(pfx_name, DM_NAME_LEN); if (pfx_len > val_len) return false; if (memcmp(val, pfx_name, pfx_len)) return false; val = hc->uuid ? hc->uuid : ""; val_len = strlen(val); pfx_len = strnlen(pfx_uuid, DM_UUID_LEN); if (pfx_len > val_len) return false; if (memcmp(val, pfx_uuid, pfx_len)) return false; return true; } static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct rb_node *n; struct hash_cell *hc; size_t len; struct dm_name_list *nl, *old_nl = NULL; void *result_start, *result_limit; uint32_t *event_nr; /* * Grab our output buffer. */ nl = result_start = get_result_buffer(param, param_size, &len); result_limit = result_start + len; if (len >= sizeof(*nl)) nl->dev = 0; /* Flags no data */ down_write(&_hash_lock); /* * Loop through filling out the names. */ for (n = rb_first(&name_rb_tree); n; n = rb_next(n)) { void *next_nl; hc = container_of(n, struct hash_cell, name_node); if (!filter_device(hc, param->name, param->uuid)) continue; len = strlen(hc->name); event_nr = align_ptr(nl->name + len + 1); next_nl = event_nr + 2; if (next_nl > result_limit) break; ((u64 *)event_nr)[-1] = 0; memcpy(nl->name, hc->name, len); nl->dev = huge_encode_dev(disk_devt(dm_disk(hc->md))); event_nr[0] = dm_get_event_nr(hc->md); event_nr[1] = 0; if (param->flags & DM_UUID_FLAG) { if (hc->uuid) { len = strlen(hc->uuid); next_nl = align_ptr(next_nl + len + 1); if (next_nl > result_limit) break; event_nr[1] |= DM_NAME_LIST_FLAG_HAS_UUID; ((u64 *)next_nl)[-1] = 0; memcpy(event_nr + 2, hc->uuid, len); } else { event_nr[1] |= DM_NAME_LIST_FLAG_DOESNT_HAVE_UUID; } } nl->next = next_nl - (void *)nl; old_nl = nl; nl = next_nl; } if (old_nl) old_nl->next = 0; if (n) param->flags |= DM_BUFFER_FULL_FLAG; else param->data_size = param->data_start + ((void *)nl - result_start); up_write(&_hash_lock); return 0; } static void list_version_get_info(struct target_type *tt, void *param) { struct vers_iter *info = param; struct dm_target_versions *vers = info->vers; size_t name_len = strlen(tt->name); if (!vers) return; info->old_vers = vers; info->vers = align_ptr((void *)(info->vers + 1) + name_len + 1); /* Check space */ if ((char *)info->vers > info->end) { info->vers = NULL; return; } /* Zero padding and terminate vers->name[] */ ((u64 *)info->vers)[-1] = 0; vers->next = (char *)info->vers - (char *)vers; vers->version[0] = tt->version[0]; vers->version[1] = tt->version[1]; vers->version[2] = tt->version[2]; memcpy(vers->name, tt->name, name_len); } static int __list_versions(struct dm_ioctl *param, size_t param_size, const char *name) { size_t len; struct dm_target_versions *vers; struct vers_iter iter_info; struct target_type *tt = NULL; if (name) { tt = dm_get_target_type(name); if (!tt) return -EINVAL; } /* * Grab our output buffer. */ vers = get_result_buffer(param, param_size, &len); iter_info.old_vers = NULL; iter_info.vers = vers; iter_info.end = (char *)vers + len; /* * Loop through filling out the names & versions. */ if (!tt) dm_target_iterate(list_version_get_info, &iter_info); else list_version_get_info(tt, &iter_info); if (iter_info.vers) { if (iter_info.old_vers) iter_info.old_vers->next = 0; param->data_size = param->data_start + ((char *)iter_info.vers - (char *)vers); } else { param->flags |= DM_BUFFER_FULL_FLAG; } if (tt) dm_put_target_type(tt); return 0; } static int list_versions(struct file *filp, struct dm_ioctl *param, size_t param_size) { return __list_versions(param, param_size, NULL); } static int get_target_version(struct file *filp, struct dm_ioctl *param, size_t param_size) { return __list_versions(param, param_size, param->name); } static int check_name(const char *name) { if (strchr(name, '/')) { DMERR("device name cannot contain '/'"); return -EINVAL; } if (strcmp(name, DM_CONTROL_NODE) == 0 || strcmp(name, ".") == 0 || strcmp(name, "..") == 0) { DMERR("device name cannot be \"%s\", \".\", or \"..\"", DM_CONTROL_NODE); return -EINVAL; } return 0; } /* * On successful return, the caller must not attempt to acquire * _hash_lock without first calling dm_put_live_table, because dm_table_destroy * waits for this dm_put_live_table and could be called under this lock. */ static struct dm_table *dm_get_inactive_table(struct mapped_device *md, int *srcu_idx) { struct hash_cell *hc; struct dm_table *table = NULL; /* increment rcu count, we don't care about the table pointer */ dm_get_live_table(md, srcu_idx); down_read(&_hash_lock); hc = dm_get_mdptr(md); if (!hc) { DMERR("device has been removed from the dev hash table."); goto out; } table = hc->new_map; out: up_read(&_hash_lock); return table; } static struct dm_table *dm_get_live_or_inactive_table(struct mapped_device *md, struct dm_ioctl *param, int *srcu_idx) { return (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) ? dm_get_inactive_table(md, srcu_idx) : dm_get_live_table(md, srcu_idx); } /* * Fills in a dm_ioctl structure, ready for sending back to * userland. */ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param) { struct gendisk *disk = dm_disk(md); struct dm_table *table; int srcu_idx; param->flags &= ~(DM_SUSPEND_FLAG | DM_READONLY_FLAG | DM_ACTIVE_PRESENT_FLAG | DM_INTERNAL_SUSPEND_FLAG); if (dm_suspended_md(md)) param->flags |= DM_SUSPEND_FLAG; if (dm_suspended_internally_md(md)) param->flags |= DM_INTERNAL_SUSPEND_FLAG; if (dm_test_deferred_remove_flag(md)) param->flags |= DM_DEFERRED_REMOVE; param->dev = huge_encode_dev(disk_devt(disk)); /* * Yes, this will be out of date by the time it gets back * to userland, but it is still very useful for * debugging. */ param->open_count = dm_open_count(md); param->event_nr = dm_get_event_nr(md); param->target_count = 0; table = dm_get_live_table(md, &srcu_idx); if (table) { if (!(param->flags & DM_QUERY_INACTIVE_TABLE_FLAG)) { if (get_disk_ro(disk)) param->flags |= DM_READONLY_FLAG; param->target_count = table->num_targets; } param->flags |= DM_ACTIVE_PRESENT_FLAG; } dm_put_live_table(md, srcu_idx); if (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) { int srcu_idx; table = dm_get_inactive_table(md, &srcu_idx); if (table) { if (!(dm_table_get_mode(table) & BLK_OPEN_WRITE)) param->flags |= DM_READONLY_FLAG; param->target_count = table->num_targets; } dm_put_live_table(md, srcu_idx); } } static int dev_create(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r, m = DM_ANY_MINOR; struct mapped_device *md; r = check_name(param->name); if (r) return r; if (param->flags & DM_PERSISTENT_DEV_FLAG) m = MINOR(huge_decode_dev(param->dev)); r = dm_create(m, &md); if (r) return r; r = dm_hash_insert(param->name, *param->uuid ? param->uuid : NULL, md); if (r) { dm_put(md); dm_destroy(md); return r; } param->flags &= ~DM_INACTIVE_PRESENT_FLAG; __dev_status(md, param); dm_put(md); return 0; } /* * Always use UUID for lookups if it's present, otherwise use name or dev. */ static struct hash_cell *__find_device_hash_cell(struct dm_ioctl *param) { struct hash_cell *hc = NULL; if (*param->uuid) { if (*param->name || param->dev) { DMERR("Invalid ioctl structure: uuid %s, name %s, dev %llx", param->uuid, param->name, (unsigned long long)param->dev); return NULL; } hc = __get_uuid_cell(param->uuid); if (!hc) return NULL; } else if (*param->name) { if (param->dev) { DMERR("Invalid ioctl structure: name %s, dev %llx", param->name, (unsigned long long)param->dev); return NULL; } hc = __get_name_cell(param->name); if (!hc) return NULL; } else if (param->dev) { hc = __get_dev_cell(param->dev); if (!hc) return NULL; } else return NULL; /* * Sneakily write in both the name and the uuid * while we have the cell. */ strscpy(param->name, hc->name, sizeof(param->name)); if (hc->uuid) strscpy(param->uuid, hc->uuid, sizeof(param->uuid)); else param->uuid[0] = '\0'; if (hc->new_map) param->flags |= DM_INACTIVE_PRESENT_FLAG; else param->flags &= ~DM_INACTIVE_PRESENT_FLAG; return hc; } static struct mapped_device *find_device(struct dm_ioctl *param) { struct hash_cell *hc; struct mapped_device *md = NULL; down_read(&_hash_lock); hc = __find_device_hash_cell(param); if (hc) md = hc->md; up_read(&_hash_lock); return md; } static int dev_remove(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct hash_cell *hc; struct mapped_device *md; int r; struct dm_table *t; struct dm_ima_context *ima_context = NULL; unsigned int ima_idx; dm_ima_alloc_context(&ima_context, true); down_write(&_hash_lock); hc = __find_device_hash_cell(param); if (!hc) { DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table."); up_write(&_hash_lock); dm_ima_free_context(ima_context); return -ENXIO; } md = hc->md; /* * Ensure the device is not open and nothing further can open it. */ r = dm_lock_for_deletion(md, !!(param->flags & DM_DEFERRED_REMOVE), false); if (r) { if (r == -EBUSY && param->flags & DM_DEFERRED_REMOVE) { up_write(&_hash_lock); dm_put(md); dm_ima_free_context(ima_context); return 0; } DMDEBUG_LIMIT("unable to remove open device %s", hc->name); up_write(&_hash_lock); dm_put(md); dm_ima_free_context(ima_context); return r; } ima_idx = dm_ima_init_context(hc, ima_context, true); t = __hash_remove(hc); up_write(&_hash_lock); if (t) { dm_sync_table(md); dm_table_destroy(t); } param->flags &= ~DM_DEFERRED_REMOVE; dm_ima_measure_on_device_remove(md, false, ima_context, ima_idx); dm_ima_free_context(ima_context); if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr, false)) param->flags |= DM_UEVENT_GENERATED_FLAG; dm_put(md); dm_destroy(md); return 0; } /* * Check a string doesn't overrun the chunk of * memory we copied from userland. */ static int invalid_str(char *str, void *end) { while ((void *) str < end) if (!*str++) return 0; return -EINVAL; } static int dev_rename(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r; char *new_data = (char *) param + param->data_start; struct mapped_device *md; unsigned int change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0; if (new_data < param->data || invalid_str(new_data, (void *) param + param_size) || !*new_data || strlen(new_data) > (change_uuid ? DM_UUID_LEN - 1 : DM_NAME_LEN - 1)) { DMERR("Invalid new mapped device name or uuid string supplied."); return -EINVAL; } if (!change_uuid) { r = check_name(new_data); if (r) return r; } md = dm_hash_rename(param, new_data); if (IS_ERR(md)) return PTR_ERR(md); __dev_status(md, param); dm_put(md); return 0; } static int dev_set_geometry(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r = -EINVAL, x; struct mapped_device *md; struct hd_geometry geometry; unsigned long indata[4]; char *geostr = (char *) param + param->data_start; char dummy; md = find_device(param); if (!md) return -ENXIO; if (geostr < param->data || invalid_str(geostr, (void *) param + param_size)) { DMERR("Invalid geometry supplied."); goto out; } x = sscanf(geostr, "%lu %lu %lu %lu%c", indata, indata + 1, indata + 2, indata + 3, &dummy); if (x != 4) { DMERR("Unable to interpret geometry settings."); goto out; } if (indata[0] > 65535 || indata[1] > 255 || indata[2] > 255) { DMERR("Geometry exceeds range limits."); goto out; } geometry.cylinders = indata[0]; geometry.heads = indata[1]; geometry.sectors = indata[2]; geometry.start = indata[3]; r = dm_set_geometry(md, &geometry); param->data_size = 0; out: dm_put(md); return r; } static int do_suspend(struct dm_ioctl *param) { int r = 0; unsigned int suspend_flags = DM_SUSPEND_LOCKFS_FLAG; struct mapped_device *md; md = find_device(param); if (!md) return -ENXIO; if (param->flags & DM_SKIP_LOCKFS_FLAG) suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; if (!dm_suspended_md(md)) { r = dm_suspend(md, suspend_flags); if (r) goto out; } __dev_status(md, param); out: dm_put(md); return r; } static int do_resume(struct dm_ioctl *param) { int r = 0; unsigned int suspend_flags = DM_SUSPEND_LOCKFS_FLAG; struct hash_cell *hc; struct mapped_device *md; struct dm_table *new_map, *old_map = NULL; bool need_resize_uevent = false; struct dm_ima_context *ima_context = NULL; dm_ima_alloc_context(&ima_context, true); down_write(&_hash_lock); hc = __find_device_hash_cell(param); if (!hc) { DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table."); up_write(&_hash_lock); dm_ima_free_context(ima_context); return -ENXIO; } md = hc->md; new_map = hc->new_map; hc->new_map = NULL; param->flags &= ~DM_INACTIVE_PRESENT_FLAG; if (new_map) dm_ima_init_context(hc, ima_context, false); up_write(&_hash_lock); /* Do we need to load a new map ? */ if (new_map) { sector_t old_size, new_size; dm_ima_context_table_op(md, ima_context, DM_IMA_TABLE_SAVE); /* Suspend if it isn't already suspended */ if (param->flags & DM_SKIP_LOCKFS_FLAG) suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; if (!dm_suspended_md(md)) { r = dm_suspend(md, suspend_flags); if (r) { down_write(&_hash_lock); hc = dm_get_mdptr(md); if (hc && !hc->new_map) { hc->new_map = new_map; new_map = NULL; dm_ima_init_context(hc, ima_context, false); } else { r = -ENXIO; } up_write(&_hash_lock); if (new_map) { dm_sync_table(md); dm_table_destroy(new_map); } else dm_ima_context_table_op(md, ima_context, DM_IMA_TABLE_RESTORE); dm_ima_free_context(ima_context); dm_put(md); return r; } } old_size = dm_get_size(md); old_map = dm_swap_table(md, new_map); if (IS_ERR(old_map)) { dm_sync_table(md); dm_table_destroy(new_map); dm_ima_free_context(ima_context); dm_put(md); return PTR_ERR(old_map); } if (dm_ima_need_measure(md, new_map, ima_context)) dm_ima_measure_on_device_resume(md, true, ima_context); new_size = dm_get_size(md); if (old_size && new_size && old_size != new_size) need_resize_uevent = true; if (dm_table_get_mode(new_map) & BLK_OPEN_WRITE) set_disk_ro(dm_disk(md), 0); else set_disk_ro(dm_disk(md), 1); } if (dm_suspended_md(md)) { r = dm_resume(md); if (!r) { if (!new_map && dm_ima_need_measure(md, NULL, ima_context)) dm_ima_measure_on_device_resume(md, false, ima_context); if (!dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr, need_resize_uevent)) param->flags |= DM_UEVENT_GENERATED_FLAG; } } /* * Since dm_swap_table synchronizes RCU, nobody should be in * read-side critical section already. */ if (old_map) dm_table_destroy(old_map); if (!r) __dev_status(md, param); dm_ima_free_context(ima_context); dm_put(md); return r; } /* * Set or unset the suspension state of a device. * If the device already is in the requested state we just return its status. */ static int dev_suspend(struct file *filp, struct dm_ioctl *param, size_t param_size) { if (param->flags & DM_SUSPEND_FLAG) return do_suspend(param); return do_resume(param); } /* * Copies device info back to user space, used by * the create and info ioctls. */ static int dev_status(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct mapped_device *md; md = find_device(param); if (!md) return -ENXIO; __dev_status(md, param); dm_put(md); return 0; } /* * Build up the status struct for each target */ static void retrieve_status(struct dm_table *table, struct dm_ioctl *param, size_t param_size) { unsigned int i, num_targets; struct dm_target_spec *spec; char *outbuf, *outptr; status_type_t type; size_t remaining, len, used = 0; unsigned int status_flags = 0; outptr = outbuf = get_result_buffer(param, param_size, &len); if (param->flags & DM_STATUS_TABLE_FLAG) type = STATUSTYPE_TABLE; else if (param->flags & DM_IMA_MEASUREMENT_FLAG) type = STATUSTYPE_IMA; else type = STATUSTYPE_INFO; /* Get all the target info */ num_targets = table->num_targets; for (i = 0; i < num_targets; i++) { struct dm_target *ti = dm_table_get_target(table, i); size_t l; remaining = len - (outptr - outbuf); if (remaining <= sizeof(struct dm_target_spec)) { param->flags |= DM_BUFFER_FULL_FLAG; break; } spec = (struct dm_target_spec *) outptr; spec->status = 0; spec->sector_start = ti->begin; spec->length = ti->len; strscpy_pad(spec->target_type, ti->type->name, sizeof(spec->target_type)); outptr += sizeof(struct dm_target_spec); remaining = len - (outptr - outbuf); /* Get the status/table string from the target driver */ if (ti->type->status) { if (param->flags & DM_NOFLUSH_FLAG) status_flags |= DM_STATUS_NOFLUSH_FLAG; ti->type->status(ti, type, status_flags, outptr, remaining); } else outptr[0] = '\0'; l = strlen(outptr) + 1; if (l == remaining) { param->flags |= DM_BUFFER_FULL_FLAG; break; } outptr += l; used = param->data_start + (outptr - outbuf); outptr = align_ptr(outptr); if (!outptr || outptr > outbuf + len) { param->flags |= DM_BUFFER_FULL_FLAG; break; } spec->next = outptr - outbuf; } if (used) param->data_size = used; param->target_count = num_targets; } /* * Wait for a device to report an event */ static int dev_wait(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r = 0; struct mapped_device *md; struct dm_table *table; int srcu_idx; md = find_device(param); if (!md) return -ENXIO; /* * Wait for a notification event */ if (dm_wait_event(md, param->event_nr)) { r = -ERESTARTSYS; goto out; } /* * The userland program is going to want to know what * changed to trigger the event, so we may as well tell * him and save an ioctl. */ __dev_status(md, param); table = dm_get_live_or_inactive_table(md, param, &srcu_idx); if (table) retrieve_status(table, param, param_size); dm_put_live_table(md, srcu_idx); out: dm_put(md); return r; } /* * Remember the global event number and make it possible to poll * for further events. */ static int dev_arm_poll(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct dm_file *priv = filp->private_data; priv->global_event_nr = atomic_read(&dm_global_event_nr); return 0; } static inline blk_mode_t get_mode(struct dm_ioctl *param) { blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE; if (param->flags & DM_READONLY_FLAG) mode = BLK_OPEN_READ; return mode; } static int next_target(struct dm_target_spec *last, uint32_t next, const char *end, struct dm_target_spec **spec, char **target_params) { static_assert(__alignof__(struct dm_target_spec) <= 8, "struct dm_target_spec must not require more than 8-byte alignment"); /* * Number of bytes remaining, starting with last. This is always * sizeof(struct dm_target_spec) or more, as otherwise *last was * out of bounds already. */ size_t remaining = end - (char *)last; /* * There must be room for both the next target spec and the * NUL-terminator of the target itself. */ if (remaining - sizeof(struct dm_target_spec) <= next) { DMERR("Target spec extends beyond end of parameters"); return -EINVAL; } if (next % __alignof__(struct dm_target_spec)) { DMERR("Next dm_target_spec (offset %u) is not %zu-byte aligned", next, __alignof__(struct dm_target_spec)); return -EINVAL; } *spec = (struct dm_target_spec *) ((unsigned char *) last + next); *target_params = (char *) (*spec + 1); return 0; } static int populate_table(struct dm_table *table, struct dm_ioctl *param, size_t param_size) { int r; unsigned int i = 0; struct dm_target_spec *spec = (struct dm_target_spec *) param; uint32_t next = param->data_start; const char *const end = (const char *) param + param_size; char *target_params; size_t min_size = sizeof(struct dm_ioctl); if (!param->target_count) { DMERR("%s: no targets specified", __func__); return -EINVAL; } for (i = 0; i < param->target_count; i++) { const char *nul_terminator; if (next < min_size) { DMERR("%s: next target spec (offset %u) overlaps %s", __func__, next, i ? "previous target" : "'struct dm_ioctl'"); return -EINVAL; } r = next_target(spec, next, end, &spec, &target_params); if (r) { DMERR("unable to find target"); return r; } nul_terminator = memchr(target_params, 0, (size_t)(end - target_params)); if (nul_terminator == NULL) { DMERR("%s: target parameters not NUL-terminated", __func__); return -EINVAL; } /* Add 1 for NUL terminator */ min_size = (size_t)(nul_terminator - (const char *)spec) + 1; r = dm_table_add_target(table, spec->target_type, (sector_t) spec->sector_start, (sector_t) spec->length, target_params); if (r) { DMERR("error adding target to table"); return r; } next = spec->next; } return dm_table_complete(table); } static bool is_valid_type(enum dm_queue_mode cur, enum dm_queue_mode new) { if (cur == new || (cur == DM_TYPE_BIO_BASED && new == DM_TYPE_DAX_BIO_BASED)) return true; return false; } static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r, srcu_idx; struct hash_cell *hc; struct dm_table *t, *old_map = NULL; struct mapped_device *md; struct target_type *immutable_target_type; struct dm_ima_context *ima_context = NULL; md = find_device(param); if (!md) return -ENXIO; r = dm_table_create(&t, get_mode(param), param->target_count, md); if (r) goto err; /* Protect md->type and md->queue against concurrent table loads. */ dm_lock_md_type(md); r = populate_table(t, param, param_size); if (r) goto err_unlock_md_type; immutable_target_type = dm_get_immutable_target_type(md); if (immutable_target_type && (immutable_target_type != dm_table_get_immutable_target_type(t)) && !dm_table_get_wildcard_target(t)) { DMERR("can't replace immutable target type %s", immutable_target_type->name); r = -EINVAL; goto err_unlock_md_type; } if (dm_get_md_type(md) == DM_TYPE_NONE) { /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { DMERR("unable to set up device queue for new table."); goto err_unlock_md_type; } } else if (!is_valid_type(dm_get_md_type(md), dm_table_get_type(t))) { DMERR("can't change device type (old=%u vs new=%u) after initial table load.", dm_get_md_type(md), dm_table_get_type(t)); r = -EINVAL; goto err_unlock_md_type; } dm_unlock_md_type(md); dm_ima_alloc_context(&ima_context, false); /* stage inactive table */ down_write(&_hash_lock); hc = dm_get_mdptr(md); if (!hc) { DMERR("device has been removed from the dev hash table."); up_write(&_hash_lock); dm_ima_free_context(ima_context); r = -ENXIO; goto err_destroy_table; } if (hc->new_map) old_map = hc->new_map; hc->new_map = t; dm_ima_init_context(hc, ima_context, false); /* Make sure new_map doesn't get freed before we measure it*/ dm_get_live_table(md, &srcu_idx); up_write(&_hash_lock); dm_ima_measure_on_table_load(t, ima_context); dm_ima_free_context(ima_context); dm_put_live_table(md, srcu_idx); param->flags |= DM_INACTIVE_PRESENT_FLAG; __dev_status(md, param); if (old_map) { dm_sync_table(md); dm_table_destroy(old_map); } dm_put(md); return 0; err_unlock_md_type: dm_unlock_md_type(md); err_destroy_table: dm_table_destroy(t); err: dm_put(md); return r; } static int table_clear(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct hash_cell *hc; struct mapped_device *md; struct dm_table *old_map = NULL; struct dm_ima_context *ima_context = NULL; dm_ima_alloc_context(&ima_context, true); down_write(&_hash_lock); hc = __find_device_hash_cell(param); if (!hc) { DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table."); up_write(&_hash_lock); dm_ima_free_context(ima_context); return -ENXIO; } if (hc->new_map) { old_map = hc->new_map; hc->new_map = NULL; } dm_ima_init_context(hc, ima_context, false); md = hc->md; up_write(&_hash_lock); dm_ima_measure_on_table_clear(md, ima_context); dm_ima_free_context(ima_context); param->flags &= ~DM_INACTIVE_PRESENT_FLAG; __dev_status(md, param); if (old_map) { dm_sync_table(md); dm_table_destroy(old_map); } dm_put(md); return 0; } /* * Retrieves a list of devices used by a particular dm device. */ static void retrieve_deps(struct dm_table *table, struct dm_ioctl *param, size_t param_size) { unsigned int count = 0; struct list_head *tmp; size_t len, needed; struct dm_dev_internal *dd; struct dm_target_deps *deps; deps = get_result_buffer(param, param_size, &len); /* * Count the devices. */ list_for_each(tmp, dm_table_get_devices(table)) count++; /* * Check we have enough space. */ needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; return; } /* * Fill in the devices. */ deps->count = count; count = 0; list_for_each_entry(dd, dm_table_get_devices(table), list) deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev); param->data_size = param->data_start + needed; } static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct mapped_device *md; struct dm_table *table; int srcu_idx; md = find_device(param); if (!md) return -ENXIO; __dev_status(md, param); table = dm_get_live_or_inactive_table(md, param, &srcu_idx); if (table) retrieve_deps(table, param, param_size); dm_put_live_table(md, srcu_idx); dm_put(md); return 0; } /* * Return the status of a device as a text string for each * target. */ static int table_status(struct file *filp, struct dm_ioctl *param, size_t param_size) { struct mapped_device *md; struct dm_table *table; int srcu_idx; md = find_device(param); if (!md) return -ENXIO; __dev_status(md, param); table = dm_get_live_or_inactive_table(md, param, &srcu_idx); if (table) retrieve_status(table, param, param_size); dm_put_live_table(md, srcu_idx); dm_put(md); return 0; } /* * Process device-mapper dependent messages. Messages prefixed with '@' * are processed by the DM core. All others are delivered to the target. * Returns a number <= 1 if message was processed by device mapper. * Returns 2 if message should be delivered to the target. */ static int message_for_md(struct mapped_device *md, unsigned int argc, char **argv, char *result, unsigned int maxlen) { int r; if (**argv != '@') return 2; /* no '@' prefix, deliver to target */ if (!strcasecmp(argv[0], "@cancel_deferred_remove")) { if (argc != 1) { DMERR("Invalid arguments for @cancel_deferred_remove"); return -EINVAL; } return dm_cancel_deferred_remove(md); } r = dm_stats_message(md, argc, argv, result, maxlen); if (r < 2) return r; DMERR("Unsupported message sent to DM core: %s", argv[0]); return -EINVAL; } /* * Pass a message to the target that's at the supplied device offset. */ static int target_message(struct file *filp, struct dm_ioctl *param, size_t param_size) { int r, argc; char **argv; struct mapped_device *md; struct dm_table *table; struct dm_target *ti; struct dm_target_msg *tmsg = (void *) param + param->data_start; size_t maxlen; char *result = get_result_buffer(param, param_size, &maxlen); int srcu_idx; md = find_device(param); if (!md) return -ENXIO; if (tmsg < (struct dm_target_msg *) param->data || invalid_str(tmsg->message, (void *) param + param_size)) { DMERR("Invalid target message parameters."); r = -EINVAL; goto out; } r = dm_split_args(&argc, &argv, tmsg->message); if (r) { DMERR("Failed to split target message parameters"); goto out; } if (!argc) { DMERR("Empty message received."); r = -EINVAL; goto out_argv; } r = message_for_md(md, argc, argv, result, maxlen); if (r <= 1) goto out_argv; table = dm_get_live_table(md, &srcu_idx); if (!table) { DMERR("The device has no table."); r = -EINVAL; goto out_table; } if (dm_deleting_md(md)) { r = -ENXIO; goto out_table; } ti = dm_table_find_target(table, tmsg->sector); if (!ti) { DMERR("Target message sector outside device."); r = -EINVAL; } else if (ti->type->message) r = ti->type->message(ti, argc, argv, result, maxlen); else { DMERR("Target type does not support messages"); r = -EINVAL; } out_table: dm_put_live_table(md, srcu_idx); out_argv: kfree(argv); out: if (r >= 0) __dev_status(md, param); if (r == 1) { param->flags |= DM_DATA_OUT_FLAG; if (dm_message_test_buffer_overflow(result, maxlen)) param->flags |= DM_BUFFER_FULL_FLAG; else param->data_size = param->data_start + strlen(result) + 1; r = 0; } dm_put(md); return r; } /* * The ioctl parameter block consists of two parts, a dm_ioctl struct * followed by a data buffer. This flag is set if the second part, * which has a variable size, is not used by the function processing * the ioctl. */ #define IOCTL_FLAGS_NO_PARAMS 1 #define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT 2 /* *--------------------------------------------------------------- * Implementation of open/close/ioctl on the special char device. *--------------------------------------------------------------- */ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) { static const struct { int flags; ioctl_fn fn; } _ioctls[] = { [DM_VERSION_CMD] = {0, NULL}, /* version is dealt with elsewhere */ [DM_REMOVE_ALL_CMD] = {IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, remove_all}, [DM_LIST_DEVICES_CMD] = {0, list_devices}, [DM_DEV_CREATE_CMD] = {IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_create}, [DM_DEV_REMOVE_CMD] = {IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_remove}, [DM_DEV_RENAME_CMD] = {IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_rename}, [DM_DEV_SUSPEND_CMD] = {IOCTL_FLAGS_NO_PARAMS, dev_suspend}, [DM_DEV_STATUS_CMD] = {IOCTL_FLAGS_NO_PARAMS, dev_status}, [DM_DEV_WAIT_CMD] = {0, dev_wait}, [DM_TABLE_LOAD_CMD] = {0, table_load}, [DM_TABLE_CLEAR_CMD] = {IOCTL_FLAGS_NO_PARAMS, table_clear}, [DM_TABLE_DEPS_CMD] = {0, table_deps}, [DM_TABLE_STATUS_CMD] = {0, table_status}, [DM_LIST_VERSIONS_CMD] = {0, list_versions}, [DM_TARGET_MSG_CMD] = {0, target_message}, [DM_DEV_SET_GEOMETRY_CMD] = {0, dev_set_geometry}, [DM_DEV_ARM_POLL_CMD] = {IOCTL_FLAGS_NO_PARAMS, dev_arm_poll}, [DM_GET_TARGET_VERSION_CMD] = {0, get_target_version}, [DM_MPATH_PROBE_PATHS_CMD] = {0, NULL}, /* block device ioctl */ }; if (unlikely(cmd >= ARRAY_SIZE(_ioctls))) return NULL; cmd = array_index_nospec(cmd, ARRAY_SIZE(_ioctls)); *ioctl_flags = _ioctls[cmd].flags; return _ioctls[cmd].fn; } /* * As well as checking the version compatibility this always * copies the kernel interface version out. */ static int check_version(unsigned int cmd, struct dm_ioctl __user *user, struct dm_ioctl *kernel_params) { int r = 0; /* Make certain version is first member of dm_ioctl struct */ BUILD_BUG_ON(offsetof(struct dm_ioctl, version) != 0); if (copy_from_user(kernel_params->version, user->version, sizeof(kernel_params->version))) return -EFAULT; if ((kernel_params->version[0] != DM_VERSION_MAJOR) || (kernel_params->version[1] > DM_VERSION_MINOR)) { DMERR_LIMIT("ioctl interface mismatch: kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)", DM_VERSION_MAJOR, DM_VERSION_MINOR, DM_VERSION_PATCHLEVEL, kernel_params->version[0], kernel_params->version[1], kernel_params->version[2], cmd); r = -EINVAL; } /* * Fill in the kernel version. */ kernel_params->version[0] = DM_VERSION_MAJOR; kernel_params->version[1] = DM_VERSION_MINOR; kernel_params->version[2] = DM_VERSION_PATCHLEVEL; if (copy_to_user(user->version, kernel_params->version, sizeof(kernel_params->version))) return -EFAULT; return r; } #define DM_PARAMS_MALLOC 0x0001 /* Params allocated with kvmalloc() */ #define DM_WIPE_BUFFER 0x0010 /* Wipe input buffer before returning from ioctl */ static void free_params(struct dm_ioctl *param, size_t param_size, int param_flags) { if (param_flags & DM_WIPE_BUFFER) memset(param, 0, param_size); if (param_flags & DM_PARAMS_MALLOC) kvfree(param); } static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kernel, int ioctl_flags, struct dm_ioctl **param, int *param_flags) { struct dm_ioctl *dmi; int secure_data; const size_t minimum_data_size = offsetof(struct dm_ioctl, data); /* check_version() already copied version from userspace, avoid TOCTOU */ if (copy_from_user((char *)param_kernel + sizeof(param_kernel->version), (char __user *)user + sizeof(param_kernel->version), minimum_data_size - sizeof(param_kernel->version))) return -EFAULT; if (unlikely(param_kernel->data_size < minimum_data_size) || unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) { DMERR_LIMIT("Invalid data size in the ioctl structure: %u", param_kernel->data_size); return -EINVAL; } secure_data = param_kernel->flags & DM_SECURE_DATA_FLAG; *param_flags = secure_data ? DM_WIPE_BUFFER : 0; if (ioctl_flags & IOCTL_FLAGS_NO_PARAMS) { dmi = param_kernel; dmi->data_size = minimum_data_size; goto data_copied; } /* * Use __GFP_HIGH to avoid low memory issues when a device is * suspended and the ioctl is needed to resume it. * Use kmalloc() rather than vmalloc() when we can. */ dmi = NULL; dmi = kvmalloc(param_kernel->data_size, GFP_NOIO | __GFP_HIGH); if (!dmi) { if (secure_data && clear_user(user, param_kernel->data_size)) return -EFAULT; return -ENOMEM; } *param_flags |= DM_PARAMS_MALLOC; /* Copy from param_kernel (which was already copied from user) */ memcpy(dmi, param_kernel, minimum_data_size); if (copy_from_user(&dmi->data, (char __user *)user + minimum_data_size, param_kernel->data_size - minimum_data_size)) goto bad; data_copied: /* Wipe the user buffer so we do not return it to userspace */ if (secure_data && clear_user(user, param_kernel->data_size)) goto bad; *param = dmi; return 0; bad: free_params(dmi, param_kernel->data_size, *param_flags); return -EFAULT; } static int validate_params(uint cmd, struct dm_ioctl *param) { /* Always clear this flag */ param->flags &= ~DM_BUFFER_FULL_FLAG; param->flags &= ~DM_UEVENT_GENERATED_FLAG; param->flags &= ~DM_SECURE_DATA_FLAG; param->flags &= ~DM_DATA_OUT_FLAG; /* Ignores parameters */ if (cmd == DM_REMOVE_ALL_CMD || cmd == DM_LIST_DEVICES_CMD || cmd == DM_LIST_VERSIONS_CMD) return 0; if (cmd == DM_DEV_CREATE_CMD) { if (!*param->name) { DMERR("name not supplied when creating device"); return -EINVAL; } } else if (*param->uuid && *param->name) { DMERR("only supply one of name or uuid, cmd(%u)", cmd); return -EINVAL; } /* Ensure strings are terminated */ param->name[DM_NAME_LEN - 1] = '\0'; param->uuid[DM_UUID_LEN - 1] = '\0'; return 0; } static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *user) { int r = 0; int ioctl_flags; int param_flags; unsigned int cmd; struct dm_ioctl *param; ioctl_fn fn = NULL; size_t input_param_size; struct dm_ioctl param_kernel; /* only root can play with this */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (_IOC_TYPE(command) != DM_IOCTL) return -ENOTTY; cmd = _IOC_NR(command); /* * Check the interface version passed in. This also * writes out the kernel's interface version. */ r = check_version(cmd, user, ¶m_kernel); if (r) return r; /* * Nothing more to do for the version command. */ if (cmd == DM_VERSION_CMD) return 0; fn = lookup_ioctl(cmd, &ioctl_flags); if (!fn) { DMERR("dm_ctl_ioctl: unknown command 0x%x", command); return -ENOTTY; } /* * Copy the parameters into kernel space. */ r = copy_params(user, ¶m_kernel, ioctl_flags, ¶m, ¶m_flags); if (r) return r; input_param_size = param->data_size; r = validate_params(cmd, param); if (r) goto out; param->data_size = offsetof(struct dm_ioctl, data); r = fn(file, param, input_param_size); if (unlikely(param->flags & DM_BUFFER_FULL_FLAG) && unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS)) DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd); if (!r && ioctl_flags & IOCTL_FLAGS_ISSUE_GLOBAL_EVENT) dm_issue_global_event(); /* * Copy the results back to userland. */ if (!r && copy_to_user(user, param, param->data_size)) r = -EFAULT; out: free_params(param, input_param_size, param_flags); return r; } static long dm_ctl_ioctl(struct file *file, uint command, ulong u) { return (long)ctl_ioctl(file, command, (struct dm_ioctl __user *)u); } #ifdef CONFIG_COMPAT static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u) { return (long)dm_ctl_ioctl(file, command, (ulong) compat_ptr(u)); } #else #define dm_compat_ctl_ioctl NULL #endif static int dm_open(struct inode *inode, struct file *filp) { struct dm_file *priv; nonseekable_open(inode, filp); priv = filp->private_data = kmalloc_obj(struct dm_file); if (!priv) return -ENOMEM; priv->global_event_nr = atomic_read(&dm_global_event_nr); return 0; } static int dm_release(struct inode *inode, struct file *filp) { kfree(filp->private_data); return 0; } static __poll_t dm_poll(struct file *filp, poll_table *wait) { struct dm_file *priv = filp->private_data; __poll_t mask = 0; poll_wait(filp, &dm_global_eventq, wait); if ((int)(atomic_read(&dm_global_event_nr) - priv->global_event_nr) > 0) mask |= EPOLLIN; return mask; } static const struct file_operations _ctl_fops = { .open = dm_open, .release = dm_release, .poll = dm_poll, .unlocked_ioctl = dm_ctl_ioctl, .compat_ioctl = dm_compat_ctl_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice _dm_misc = { .minor = MAPPER_CTRL_MINOR, .name = DM_NAME, .nodename = DM_DIR "/" DM_CONTROL_NODE, .fops = &_ctl_fops }; MODULE_ALIAS_MISCDEV(MAPPER_CTRL_MINOR); MODULE_ALIAS("devname:" DM_DIR "/" DM_CONTROL_NODE); /* * Create misc character device and link to DM_DIR/control. */ int __init dm_interface_init(void) { int r; r = misc_register(&_dm_misc); if (r) { DMERR("misc_register failed for control device"); return r; } DMINFO("%d.%d.%d%s initialised: %s", DM_VERSION_MAJOR, DM_VERSION_MINOR, DM_VERSION_PATCHLEVEL, DM_VERSION_EXTRA, DM_DRIVER_EMAIL); return 0; } void dm_interface_exit(void) { misc_deregister(&_dm_misc); dm_hash_exit(); } /** * dm_copy_name_and_uuid - Copy mapped device name & uuid into supplied buffers * @md: Pointer to mapped_device * @name: Buffer (size DM_NAME_LEN) for name * @uuid: Buffer (size DM_UUID_LEN) for uuid or empty string if uuid not defined */ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid) { int r = 0; struct hash_cell *hc; if (!md) return -ENXIO; mutex_lock(&dm_hash_cells_mutex); hc = dm_get_mdptr(md); if (!hc) { r = -ENXIO; goto out; } if (name) strcpy(name, hc->name); if (uuid) strcpy(uuid, hc->uuid ? : ""); out: mutex_unlock(&dm_hash_cells_mutex); return r; } EXPORT_SYMBOL_GPL(dm_copy_name_and_uuid); /** * dm_early_create - create a mapped device in early boot. * * @dmi: Contains main information of the device mapping to be created. * @spec_array: array of pointers to struct dm_target_spec. Describes the * mapping table of the device. * @target_params_array: array of strings with the parameters to a specific * target. * * Instead of having the struct dm_target_spec and the parameters for every * target embedded at the end of struct dm_ioctl (as performed in a normal * ioctl), pass them as arguments, so the caller doesn't need to serialize them. * The size of the spec_array and target_params_array is given by * @dmi->target_count. * This function is supposed to be called in early boot, so locking mechanisms * to protect against concurrent loads are not required. */ int __init dm_early_create(struct dm_ioctl *dmi, struct dm_target_spec **spec_array, char **target_params_array) { int r, m = DM_ANY_MINOR; struct dm_table *t, *old_map; struct mapped_device *md; unsigned int i; if (!dmi->target_count) return -EINVAL; r = check_name(dmi->name); if (r) return r; if (dmi->flags & DM_PERSISTENT_DEV_FLAG) m = MINOR(huge_decode_dev(dmi->dev)); /* alloc dm device */ r = dm_create(m, &md); if (r) return r; /* hash insert */ r = dm_hash_insert(dmi->name, *dmi->uuid ? dmi->uuid : NULL, md); if (r) goto err_destroy_dm; /* alloc table */ r = dm_table_create(&t, get_mode(dmi), dmi->target_count, md); if (r) goto err_hash_remove; /* add targets */ for (i = 0; i < dmi->target_count; i++) { r = dm_table_add_target(t, spec_array[i]->target_type, (sector_t) spec_array[i]->sector_start, (sector_t) spec_array[i]->length, target_params_array[i]); if (r) { DMERR("error adding target to table"); goto err_destroy_table; } } /* finish table */ r = dm_table_complete(t); if (r) goto err_destroy_table; /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { DMERR("unable to set up device queue for new table."); goto err_destroy_table; } /* Set new map */ dm_suspend(md, 0); old_map = dm_swap_table(md, t); if (IS_ERR(old_map)) { r = PTR_ERR(old_map); goto err_destroy_table; } set_disk_ro(dm_disk(md), !!(dmi->flags & DM_READONLY_FLAG)); /* resume device */ r = dm_resume(md); if (r) goto err_hash_remove; DMINFO("%s (%s) is ready", md->disk->disk_name, dmi->name); dm_put(md); return 0; err_destroy_table: dm_table_destroy(t); err_hash_remove: down_write(&_hash_lock); (void) __hash_remove(__get_name_cell(dmi->name)); up_write(&_hash_lock); /* release reference from __get_name_cell */ dm_put(md); err_destroy_dm: dm_put(md); dm_destroy(md); return r; } |
| 5 5 5 5 2 5 2 5 5 3 5 | 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 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: dscontrol - Support for execution control opcodes - * if/else/while/return * * Copyright (C) 2000 - 2026, Intel Corp. * *****************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #include "amlcode.h" #include "acdispat.h" #include "acinterp.h" #include "acdebug.h" #define _COMPONENT ACPI_DISPATCHER ACPI_MODULE_NAME("dscontrol") /******************************************************************************* * * FUNCTION: acpi_ds_exec_begin_control_op * * PARAMETERS: walk_list - The list that owns the walk stack * op - The control Op * * RETURN: Status * * DESCRIPTION: Handles all control ops encountered during control method * execution. * ******************************************************************************/ acpi_status acpi_ds_exec_begin_control_op(struct acpi_walk_state *walk_state, union acpi_parse_object *op) { acpi_status status = AE_OK; union acpi_generic_state *control_state; ACPI_FUNCTION_NAME(ds_exec_begin_control_op); ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "Op=%p Opcode=%2.2X State=%p\n", op, op->common.aml_opcode, walk_state)); switch (op->common.aml_opcode) { case AML_WHILE_OP: /* * If this is an additional iteration of a while loop, continue. * There is no need to allocate a new control state. */ if (walk_state->control_state) { if (walk_state->control_state->control. aml_predicate_start == (walk_state->parser_state.aml - 1)) { /* Reset the state to start-of-loop */ walk_state->control_state->common.state = ACPI_CONTROL_CONDITIONAL_EXECUTING; break; } } ACPI_FALLTHROUGH; case AML_IF_OP: /* * IF/WHILE: Create a new control state to manage these * constructs. We need to manage these as a stack, in order * to handle nesting. */ control_state = acpi_ut_create_control_state(); if (!control_state) { status = AE_NO_MEMORY; break; } /* * Save a pointer to the predicate for multiple executions * of a loop */ control_state->control.aml_predicate_start = walk_state->parser_state.aml - 1; control_state->control.package_end = walk_state->parser_state.pkg_end; control_state->control.opcode = op->common.aml_opcode; control_state->control.loop_timeout = acpi_os_get_timer() + ((u64)acpi_gbl_max_loop_iterations * ACPI_100NSEC_PER_SEC); /* Push the control state on this walk's control stack */ acpi_ut_push_generic_state(&walk_state->control_state, control_state); break; case AML_ELSE_OP: /* Predicate is in the state object */ /* If predicate is true, the IF was executed, ignore ELSE part */ if (walk_state->last_predicate) { status = AE_CTRL_TRUE; } break; case AML_RETURN_OP: break; default: break; } return (status); } /******************************************************************************* * * FUNCTION: acpi_ds_exec_end_control_op * * PARAMETERS: walk_list - The list that owns the walk stack * op - The control Op * * RETURN: Status * * DESCRIPTION: Handles all control ops encountered during control method * execution. * ******************************************************************************/ acpi_status acpi_ds_exec_end_control_op(struct acpi_walk_state *walk_state, union acpi_parse_object *op) { acpi_status status = AE_OK; union acpi_generic_state *control_state; ACPI_FUNCTION_NAME(ds_exec_end_control_op); switch (op->common.aml_opcode) { case AML_IF_OP: ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "[IF_OP] Op=%p\n", op)); /* * Save the result of the predicate in case there is an * ELSE to come */ walk_state->last_predicate = (u8)walk_state->control_state->common.value; /* * Pop the control state that was created at the start * of the IF and free it */ control_state = acpi_ut_pop_generic_state(&walk_state->control_state); acpi_ut_delete_generic_state(control_state); break; case AML_ELSE_OP: break; case AML_WHILE_OP: ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "[WHILE_OP] Op=%p\n", op)); control_state = walk_state->control_state; if (control_state->common.value) { /* Predicate was true, the body of the loop was just executed */ /* * This infinite loop detection mechanism allows the interpreter * to escape possibly infinite loops. This can occur in poorly * written AML when the hardware does not respond within a while * loop and the loop does not implement a timeout. */ if (ACPI_TIME_AFTER(acpi_os_get_timer(), control_state->control. loop_timeout)) { status = AE_AML_LOOP_TIMEOUT; break; } /* * Go back and evaluate the predicate and maybe execute the loop * another time */ status = AE_CTRL_PENDING; walk_state->aml_last_while = control_state->control.aml_predicate_start; break; } /* Predicate was false, terminate this while loop */ ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "[WHILE_OP] termination! Op=%p\n", op)); /* Pop this control state and free it */ control_state = acpi_ut_pop_generic_state(&walk_state->control_state); acpi_ut_delete_generic_state(control_state); break; case AML_RETURN_OP: ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "[RETURN_OP] Op=%p Arg=%p\n", op, op->common.value.arg)); /* * One optional operand -- the return value * It can be either an immediate operand or a result that * has been bubbled up the tree */ if (op->common.value.arg) { /* Since we have a real Return(), delete any implicit return */ acpi_ds_clear_implicit_return(walk_state); /* Return statement has an immediate operand */ status = acpi_ds_create_operands(walk_state, op->common.value.arg); if (ACPI_FAILURE(status)) { return (status); } /* * If value being returned is a Reference (such as * an arg or local), resolve it now because it may * cease to exist at the end of the method. */ status = acpi_ex_resolve_to_value(&walk_state->operands[0], walk_state); if (ACPI_FAILURE(status)) { return (status); } /* * Get the return value and save as the last result * value. This is the only place where walk_state->return_desc * is set to anything other than zero! */ walk_state->return_desc = walk_state->operands[0]; } else if (walk_state->result_count) { /* Since we have a real Return(), delete any implicit return */ acpi_ds_clear_implicit_return(walk_state); /* * The return value has come from a previous calculation. * * If value being returned is a Reference (such as * an arg or local), resolve it now because it may * cease to exist at the end of the method. * * Allow references created by the Index operator to return * unchanged. */ if ((ACPI_GET_DESCRIPTOR_TYPE (walk_state->results->results.obj_desc[0]) == ACPI_DESC_TYPE_OPERAND) && ((walk_state->results->results.obj_desc[0])-> common.type == ACPI_TYPE_LOCAL_REFERENCE) && ((walk_state->results->results.obj_desc[0])-> reference.class != ACPI_REFCLASS_INDEX)) { status = acpi_ex_resolve_to_value(&walk_state-> results->results. obj_desc[0], walk_state); if (ACPI_FAILURE(status)) { return (status); } } walk_state->return_desc = walk_state->results->results.obj_desc[0]; } else { /* No return operand */ if (walk_state->num_operands) { acpi_ut_remove_reference(walk_state-> operands[0]); } walk_state->operands[0] = NULL; walk_state->num_operands = 0; walk_state->return_desc = NULL; } ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "Completed RETURN_OP State=%p, RetVal=%p\n", walk_state, walk_state->return_desc)); /* End the control method execution right now */ status = AE_CTRL_TERMINATE; break; case AML_NOOP_OP: /* Just do nothing! */ break; case AML_BREAKPOINT_OP: acpi_db_signal_break_point(walk_state); /* Call to the OSL in case OS wants a piece of the action */ status = acpi_os_signal(ACPI_SIGNAL_BREAKPOINT, "Executed AML Breakpoint opcode"); break; case AML_BREAK_OP: case AML_CONTINUE_OP: /* ACPI 2.0 */ /* Pop and delete control states until we find a while */ while (walk_state->control_state && (walk_state->control_state->control.opcode != AML_WHILE_OP)) { control_state = acpi_ut_pop_generic_state(&walk_state-> control_state); acpi_ut_delete_generic_state(control_state); } /* No while found? */ if (!walk_state->control_state) { return (AE_AML_NO_WHILE); } /* Was: walk_state->aml_last_while = walk_state->control_state->Control.aml_predicate_start; */ walk_state->aml_last_while = walk_state->control_state->control.package_end; /* Return status depending on opcode */ if (op->common.aml_opcode == AML_BREAK_OP) { status = AE_CTRL_BREAK; } else { status = AE_CTRL_CONTINUE; } break; default: ACPI_ERROR((AE_INFO, "Unknown control opcode=0x%X Op=%p", op->common.aml_opcode, op)); status = AE_AML_BAD_OPCODE; break; } return (status); } |
| 5 1 2 27 22 5 22 11 8 5 5 5 5 3 2 3 2 3 2 12 12 8 2 12 12 12 3 11 37 41 31 10 2 4 33 2 1 1 1 31 1 29 1 1 3 2 24 4 4 12 15 12 37 43 41 3 37 5 5 2 2 2 2 1 1 10 5 6 42 1 1 1 1 1 1 1 1 1 11 2 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * uprobes-based tracing events * * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ #define pr_fmt(fmt) "trace_uprobe: " fmt #include <linux/bpf-cgroup.h> #include <linux/cleanup.h> #include <linux/ctype.h> #include <linux/filter.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/percpu.h> #include <linux/rculist.h> #include <linux/security.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/uprobes.h> #include "trace.h" #include "trace_dynevent.h" #include "trace_probe.h" #include "trace_probe_tmpl.h" #define UPROBE_EVENT_SYSTEM "uprobes" struct uprobe_trace_entry_head { struct trace_entry ent; unsigned long vaddr[]; }; #define SIZEOF_TRACE_ENTRY(is_return) \ (sizeof(struct uprobe_trace_entry_head) + \ sizeof(unsigned long) * (is_return ? 2 : 1)) #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) static int trace_uprobe_create(const char *raw_command); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); static bool trace_uprobe_is_busy(struct dyn_event *ev); static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations trace_uprobe_ops = { .create = trace_uprobe_create, .show = trace_uprobe_show, .is_busy = trace_uprobe_is_busy, .free = trace_uprobe_release, .match = trace_uprobe_match, }; /* * uprobe event core functions */ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; char *filename; struct uprobe *uprobe; unsigned long offset; unsigned long ref_ctr_offset; unsigned long __percpu *nhits; struct trace_probe tp; }; static bool is_trace_uprobe(struct dyn_event *ev) { return ev->ops == &trace_uprobe_ops; } static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) { return container_of(ev, struct trace_uprobe, devent); } /** * for_each_trace_uprobe - iterate over the trace_uprobe list * @pos: the struct trace_uprobe * for each entry * @dpos: the struct dyn_event * to use as a loop cursor */ #define for_each_trace_uprobe(pos, dpos) \ for_each_dyn_event(dpos) \ if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos))) static int register_uprobe_event(struct trace_uprobe *tu); static int unregister_uprobe_event(struct trace_uprobe *tu); static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs, __u64 *data); static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs, __u64 *data); #ifdef CONFIG_STACK_GROWSUP static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr - (n * sizeof(long)); } #else static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr + (n * sizeof(long)); } #endif static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long ret; unsigned long addr = user_stack_pointer(regs); addr = adjust_stack_addr(addr, n); if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret))) return 0; return ret; } /* * Uprobes-specific fetch functions */ static nokprobe_inline int probe_mem_read(void *dest, void *src, size_t size) { void __user *vaddr = (void __force __user *)src; return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; } static nokprobe_inline int probe_mem_read_user(void *dest, void *src, size_t size) { return probe_mem_read(dest, src, size); } /* * Fetch a null-terminat |