| 991 991 988 991 988 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/common.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/string_helpers.h> #include "common.h" /* String table for operation mode. */ const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = { [TOMOYO_CONFIG_DISABLED] = "disabled", [TOMOYO_CONFIG_LEARNING] = "learning", [TOMOYO_CONFIG_PERMISSIVE] = "permissive", [TOMOYO_CONFIG_ENFORCING] = "enforcing" }; /* String table for /sys/kernel/security/tomoyo/profile */ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = "execute", [TOMOYO_MAC_FILE_OPEN] = "open", [TOMOYO_MAC_FILE_CREATE] = "create", [TOMOYO_MAC_FILE_UNLINK] = "unlink", [TOMOYO_MAC_FILE_GETATTR] = "getattr", [TOMOYO_MAC_FILE_MKDIR] = "mkdir", [TOMOYO_MAC_FILE_RMDIR] = "rmdir", [TOMOYO_MAC_FILE_MKFIFO] = "mkfifo", [TOMOYO_MAC_FILE_MKSOCK] = "mksock", [TOMOYO_MAC_FILE_TRUNCATE] = "truncate", [TOMOYO_MAC_FILE_SYMLINK] = "symlink", [TOMOYO_MAC_FILE_MKBLOCK] = "mkblock", [TOMOYO_MAC_FILE_MKCHAR] = "mkchar", [TOMOYO_MAC_FILE_LINK] = "link", [TOMOYO_MAC_FILE_RENAME] = "rename", [TOMOYO_MAC_FILE_CHMOD] = "chmod", [TOMOYO_MAC_FILE_CHOWN] = "chown", [TOMOYO_MAC_FILE_CHGRP] = "chgrp", [TOMOYO_MAC_FILE_IOCTL] = "ioctl", [TOMOYO_MAC_FILE_CHROOT] = "chroot", [TOMOYO_MAC_FILE_MOUNT] = "mount", [TOMOYO_MAC_FILE_UMOUNT] = "unmount", [TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root", /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind", [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen", [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect", [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind", [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send", [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind", [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send", [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind", [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen", [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect", /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = "env", /* CONFIG group */ [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* String table for conditions. */ const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = { [TOMOYO_TASK_UID] = "task.uid", [TOMOYO_TASK_EUID] = "task.euid", [TOMOYO_TASK_SUID] = "task.suid", [TOMOYO_TASK_FSUID] = "task.fsuid", [TOMOYO_TASK_GID] = "task.gid", [TOMOYO_TASK_EGID] = "task.egid", [TOMOYO_TASK_SGID] = "task.sgid", [TOMOYO_TASK_FSGID] = "task.fsgid", [TOMOYO_TASK_PID] = "task.pid", [TOMOYO_TASK_PPID] = "task.ppid", [TOMOYO_EXEC_ARGC] = "exec.argc", [TOMOYO_EXEC_ENVC] = "exec.envc", [TOMOYO_TYPE_IS_SOCKET] = "socket", [TOMOYO_TYPE_IS_SYMLINK] = "symlink", [TOMOYO_TYPE_IS_FILE] = "file", [TOMOYO_TYPE_IS_BLOCK_DEV] = "block", [TOMOYO_TYPE_IS_DIRECTORY] = "directory", [TOMOYO_TYPE_IS_CHAR_DEV] = "char", [TOMOYO_TYPE_IS_FIFO] = "fifo", [TOMOYO_MODE_SETUID] = "setuid", [TOMOYO_MODE_SETGID] = "setgid", [TOMOYO_MODE_STICKY] = "sticky", [TOMOYO_MODE_OWNER_READ] = "owner_read", [TOMOYO_MODE_OWNER_WRITE] = "owner_write", [TOMOYO_MODE_OWNER_EXECUTE] = "owner_execute", [TOMOYO_MODE_GROUP_READ] = "group_read", [TOMOYO_MODE_GROUP_WRITE] = "group_write", [TOMOYO_MODE_GROUP_EXECUTE] = "group_execute", [TOMOYO_MODE_OTHERS_READ] = "others_read", [TOMOYO_MODE_OTHERS_WRITE] = "others_write", [TOMOYO_MODE_OTHERS_EXECUTE] = "others_execute", [TOMOYO_EXEC_REALPATH] = "exec.realpath", [TOMOYO_SYMLINK_TARGET] = "symlink.target", [TOMOYO_PATH1_UID] = "path1.uid", [TOMOYO_PATH1_GID] = "path1.gid", [TOMOYO_PATH1_INO] = "path1.ino", [TOMOYO_PATH1_MAJOR] = "path1.major", [TOMOYO_PATH1_MINOR] = "path1.minor", [TOMOYO_PATH1_PERM] = "path1.perm", [TOMOYO_PATH1_TYPE] = "path1.type", [TOMOYO_PATH1_DEV_MAJOR] = "path1.dev_major", [TOMOYO_PATH1_DEV_MINOR] = "path1.dev_minor", [TOMOYO_PATH2_UID] = "path2.uid", [TOMOYO_PATH2_GID] = "path2.gid", [TOMOYO_PATH2_INO] = "path2.ino", [TOMOYO_PATH2_MAJOR] = "path2.major", [TOMOYO_PATH2_MINOR] = "path2.minor", [TOMOYO_PATH2_PERM] = "path2.perm", [TOMOYO_PATH2_TYPE] = "path2.type", [TOMOYO_PATH2_DEV_MAJOR] = "path2.dev_major", [TOMOYO_PATH2_DEV_MINOR] = "path2.dev_minor", [TOMOYO_PATH1_PARENT_UID] = "path1.parent.uid", [TOMOYO_PATH1_PARENT_GID] = "path1.parent.gid", [TOMOYO_PATH1_PARENT_INO] = "path1.parent.ino", [TOMOYO_PATH1_PARENT_PERM] = "path1.parent.perm", [TOMOYO_PATH2_PARENT_UID] = "path2.parent.uid", [TOMOYO_PATH2_PARENT_GID] = "path2.parent.gid", [TOMOYO_PATH2_PARENT_INO] = "path2.parent.ino", [TOMOYO_PATH2_PARENT_PERM] = "path2.parent.perm", }; /* String table for PREFERENCE keyword. */ static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = { [TOMOYO_PREF_MAX_AUDIT_LOG] = "max_audit_log", [TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry", }; /* String table for path operation. */ const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = "execute", [TOMOYO_TYPE_READ] = "read", [TOMOYO_TYPE_WRITE] = "write", [TOMOYO_TYPE_APPEND] = "append", [TOMOYO_TYPE_UNLINK] = "unlink", [TOMOYO_TYPE_GETATTR] = "getattr", [TOMOYO_TYPE_RMDIR] = "rmdir", [TOMOYO_TYPE_TRUNCATE] = "truncate", [TOMOYO_TYPE_SYMLINK] = "symlink", [TOMOYO_TYPE_CHROOT] = "chroot", [TOMOYO_TYPE_UMOUNT] = "unmount", }; /* String table for socket's operation. */ const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = { [TOMOYO_NETWORK_BIND] = "bind", [TOMOYO_NETWORK_LISTEN] = "listen", [TOMOYO_NETWORK_CONNECT] = "connect", [TOMOYO_NETWORK_SEND] = "send", }; /* String table for categories. */ static const char * const tomoyo_category_keywords [TOMOYO_MAX_MAC_CATEGORY_INDEX] = { [TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* Permit policy management by non-root user? */ static bool tomoyo_manage_by_non_root; /* Utility functions. */ /** * tomoyo_addprintf - strncat()-like-snprintf(). * * @buffer: Buffer to write to. Must be '\0'-terminated. * @len: Size of @buffer. * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ __printf(3, 4) static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...) { va_list args; const int pos = strlen(buffer); va_start(args, fmt); vsnprintf(buffer + pos, len - pos - 1, fmt, args); va_end(args); } /** * tomoyo_flush - Flush queued string to userspace's buffer. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if all data was flushed, false otherwise. */ static bool tomoyo_flush(struct tomoyo_io_buffer *head) { while (head->r.w_pos) { const char *w = head->r.w[0]; size_t len = strlen(w); if (len) { if (len > head->read_user_buf_avail) len = head->read_user_buf_avail; if (!len) return false; if (copy_to_user(head->read_user_buf, w, len)) return false; head->read_user_buf_avail -= len; head->read_user_buf += len; w += len; } head->r.w[0] = w; if (*w) return false; /* Add '\0' for audit logs and query. */ if (head->poll) { if (!head->read_user_buf_avail || copy_to_user(head->read_user_buf, "", 1)) return false; head->read_user_buf_avail--; head->read_user_buf++; } head->r.w_pos--; for (len = 0; len < head->r.w_pos; len++) head->r.w[len] = head->r.w[len + 1]; } head->r.avail = 0; return true; } /** * tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @string: String to print. * * Note that @string has to be kept valid until @head is kfree()d. * This means that char[] allocated on stack memory cannot be passed to * this function. Use tomoyo_io_printf() for char[] allocated on stack memory. */ static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string) { if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) { head->r.w[head->r.w_pos++] = string; tomoyo_flush(head); } else WARN_ON(1); } static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) __printf(2, 3); /** * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @fmt: The printf()'s format string, followed by parameters. */ static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) { va_list args; size_t len; size_t pos = head->r.avail; int size = head->readbuf_size - pos; if (size <= 0) return; va_start(args, fmt); len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1; va_end(args); if (pos + len >= head->readbuf_size) { WARN_ON(1); return; } head->r.avail += len; tomoyo_set_string(head, head->read_buf + pos); } /** * tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_space(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, " "); } /** * tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static bool tomoyo_set_lf(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "\n"); return !head->r.w_pos; } /** * tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_slash(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "/"); } /* List of namespaces. */ LIST_HEAD(tomoyo_namespace_list); /* True if namespace other than tomoyo_kernel_namespace is defined. */ static bool tomoyo_namespace_enabled; /** * tomoyo_init_policy_namespace - Initialize namespace. * * @ns: Pointer to "struct tomoyo_policy_namespace". * * Returns nothing. */ void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns) { unsigned int idx; for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++) INIT_LIST_HEAD(&ns->acl_group[idx]); for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++) INIT_LIST_HEAD(&ns->group_list[idx]); for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++) INIT_LIST_HEAD(&ns->policy_list[idx]); ns->profile_version = 20150505; tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list); list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list); } /** * tomoyo_print_namespace - Print namespace header. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_print_namespace(struct tomoyo_io_buffer *head) { if (!tomoyo_namespace_enabled) return; tomoyo_set_string(head, container_of(head->r.ns, struct tomoyo_policy_namespace, namespace_list)->name); tomoyo_set_space(head); } /** * tomoyo_print_name_union - Print a tomoyo_name_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". */ static void tomoyo_print_name_union(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { tomoyo_set_space(head); if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, ptr->filename->name); } } /** * tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, "\""); tomoyo_set_string(head, ptr->filename->name); tomoyo_set_string(head, "\""); } } /** * tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union_nospace (struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { int i; unsigned long min = ptr->values[0]; const unsigned long max = ptr->values[1]; u8 min_type = ptr->value_type[0]; const u8 max_type = ptr->value_type[1]; char buffer[128]; buffer[0] = '\0'; for (i = 0; i < 2; i++) { switch (min_type) { case TOMOYO_VALUE_TYPE_HEXADECIMAL: tomoyo_addprintf(buffer, sizeof(buffer), "0x%lX", min); break; case TOMOYO_VALUE_TYPE_OCTAL: tomoyo_addprintf(buffer, sizeof(buffer), "0%lo", min); break; default: tomoyo_addprintf(buffer, sizeof(buffer), "%lu", min); break; } if (min == max && min_type == max_type) break; tomoyo_addprintf(buffer, sizeof(buffer), "-"); min_type = max_type; min = max; } tomoyo_io_printf(head, "%s", buffer); } } /** * tomoyo_print_number_union - Print a tomoyo_number_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { tomoyo_set_space(head); tomoyo_print_number_union_nospace(head, ptr); } /** * tomoyo_assign_profile - Create a new profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to create. * * Returns pointer to "struct tomoyo_profile" on success, NULL otherwise. */ static struct tomoyo_profile *tomoyo_assign_profile (struct tomoyo_policy_namespace *ns, const unsigned int profile) { struct tomoyo_profile *ptr; struct tomoyo_profile *entry; if (profile >= TOMOYO_MAX_PROFILES) return NULL; ptr = ns->profile_ptr[profile]; if (ptr) return ptr; entry = kzalloc(sizeof(*entry), GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = ns->profile_ptr[profile]; if (!ptr && tomoyo_memory_ok(entry)) { ptr = entry; ptr->default_config = TOMOYO_CONFIG_DISABLED | TOMOYO_CONFIG_WANT_GRANT_LOG | TOMOYO_CONFIG_WANT_REJECT_LOG; memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT, sizeof(ptr->config)); ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG; ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY; mb(); /* Avoid out-of-order execution. */ ns->profile_ptr[profile] = ptr; entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_profile - Find a profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to find. * * Returns pointer to "struct tomoyo_profile". */ struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile) { static struct tomoyo_profile tomoyo_null_profile; struct tomoyo_profile *ptr = ns->profile_ptr[profile]; if (!ptr) ptr = &tomoyo_null_profile; return ptr; } /** * tomoyo_find_yesno - Find values for specified keyword. * * @string: String to check. * @find: Name of keyword. * * Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise. */ static s8 tomoyo_find_yesno(const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) { cp += strlen(find); if (!strncmp(cp, "=yes", 4)) return 1; else if (!strncmp(cp, "=no", 3)) return 0; } return -1; } /** * tomoyo_set_uint - Set value for specified preference. * * @i: Pointer to "unsigned int". * @string: String to check. * @find: Name of keyword. * * Returns nothing. */ static void tomoyo_set_uint(unsigned int *i, const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) sscanf(cp + strlen(find), "=%u", i); } /** * tomoyo_set_mode - Set mode for specified profile. * * @name: Name of functionality. * @value: Mode for @name. * @profile: Pointer to "struct tomoyo_profile". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_set_mode(char *name, const char *value, struct tomoyo_profile *profile) { u8 i; u8 config; if (!strcmp(name, "CONFIG")) { i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; config = profile->default_config; } else if (tomoyo_str_starts(&name, "CONFIG::")) { config = 0; for (i = 0; i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) { int len = 0; if (i < TOMOYO_MAX_MAC_INDEX) { const u8 c = tomoyo_index2category[i]; const char *category = tomoyo_category_keywords[c]; len = strlen(category); if (strncmp(name, category, len) || name[len++] != ':' || name[len++] != ':') continue; } if (strcmp(name + len, tomoyo_mac_keywords[i])) continue; config = profile->config[i]; break; } if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) return -EINVAL; } else { return -EINVAL; } if (strstr(value, "use_default")) { config = TOMOYO_CONFIG_USE_DEFAULT; } else { u8 mode; for (mode = 0; mode < 4; mode++) if (strstr(value, tomoyo_mode[mode])) /* * Update lower 3 bits in order to distinguish * 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'. */ config = (config & ~7) | mode; if (config != TOMOYO_CONFIG_USE_DEFAULT) { switch (tomoyo_find_yesno(value, "grant_log")) { case 1: config |= TOMOYO_CONFIG_WANT_GRANT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG; break; } switch (tomoyo_find_yesno(value, "reject_log")) { case 1: config |= TOMOYO_CONFIG_WANT_REJECT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG; break; } } } if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) profile->config[i] = config; else if (config != TOMOYO_CONFIG_USE_DEFAULT) profile->default_config = config; return 0; } /** * tomoyo_write_profile - Write profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_write_profile(struct tomoyo_io_buffer *head) { char *data = head->write_buf; unsigned int i; char *cp; struct tomoyo_profile *profile; if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version) == 1) return 0; i = simple_strtoul(data, &cp, 10); if (*cp != '-') return -EINVAL; data = cp + 1; profile = tomoyo_assign_profile(head->w.ns, i); if (!profile) return -EINVAL; cp = strchr(data, '='); if (!cp) return -EINVAL; *cp++ = '\0'; if (!strcmp(data, "COMMENT")) { static DEFINE_SPINLOCK(lock); const struct tomoyo_path_info *new_comment = tomoyo_get_name(cp); const struct tomoyo_path_info *old_comment; if (!new_comment) return -ENOMEM; spin_lock(&lock); old_comment = profile->comment; profile->comment = new_comment; spin_unlock(&lock); tomoyo_put_name(old_comment); return 0; } if (!strcmp(data, "PREFERENCE")) { for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_set_uint(&profile->pref[i], cp, tomoyo_pref_keywords[i]); return 0; } return tomoyo_set_mode(data, cp, profile); } /** * tomoyo_print_config - Print mode for specified functionality. * * @head: Pointer to "struct tomoyo_io_buffer". * @config: Mode for that functionality. * * Returns nothing. * * Caller prints functionality's name. */ static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config) { tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n", tomoyo_mode[config & 3], str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG), str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG)); } /** * tomoyo_read_profile - Read profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_profile(struct tomoyo_io_buffer *head) { u8 index; struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); const struct tomoyo_profile *profile; if (head->r.eof) return; next: index = head->r.index; profile = ns->profile_ptr[index]; switch (head->r.step) { case 0: tomoyo_print_namespace(head); tomoyo_io_printf(head, "PROFILE_VERSION=%u\n", ns->profile_version); head->r.step++; break; case 1: for ( ; head->r.index < TOMOYO_MAX_PROFILES; head->r.index++) if (ns->profile_ptr[head->r.index]) break; if (head->r.index == TOMOYO_MAX_PROFILES) { head->r.eof = true; return; } head->r.step++; break; case 2: { u8 i; const struct tomoyo_path_info *comment = profile->comment; tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-COMMENT=", index); tomoyo_set_string(head, comment ? comment->name : ""); tomoyo_set_lf(head); tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-PREFERENCE={ ", index); for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_io_printf(head, "%s=%u ", tomoyo_pref_keywords[i], profile->pref[i]); tomoyo_set_string(head, "}\n"); head->r.step++; } break; case 3: { tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-%s", index, "CONFIG"); tomoyo_print_config(head, profile->default_config); head->r.bit = 0; head->r.step++; } break; case 4: for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) { const u8 i = head->r.bit; const u8 config = profile->config[i]; if (config == TOMOYO_CONFIG_USE_DEFAULT) continue; tomoyo_print_namespace(head); if (i < TOMOYO_MAX_MAC_INDEX) tomoyo_io_printf(head, "%u-CONFIG::%s::%s", index, tomoyo_category_keywords [tomoyo_index2category[i]], tomoyo_mac_keywords[i]); else tomoyo_io_printf(head, "%u-CONFIG::%s", index, tomoyo_mac_keywords[i]); tomoyo_print_config(head, config); head->r.bit++; break; } if (head->r.bit == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) { head->r.index++; head->r.step = 1; } break; } if (tomoyo_flush(head)) goto next; } /** * tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_manager(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { return container_of(a, struct tomoyo_manager, head)->manager == container_of(b, struct tomoyo_manager, head)->manager; } /** * tomoyo_update_manager_entry - Add a manager entry. * * @manager: The path to manager or the domainnamme. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_manager_entry(const char *manager, const bool is_delete) { struct tomoyo_manager e = { }; struct tomoyo_acl_param param = { /* .ns = &tomoyo_kernel_namespace, */ .is_delete = is_delete, .list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], }; int error = is_delete ? -ENOENT : -ENOMEM; if (!tomoyo_correct_domain(manager) && !tomoyo_correct_word(manager)) return -EINVAL; e.manager = tomoyo_get_name(manager); if (e.manager) { error = tomoyo_update_policy(&e.head, sizeof(e), ¶m, tomoyo_same_manager); tomoyo_put_name(e.manager); } return error; } /** * tomoyo_write_manager - Write manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_manager(struct tomoyo_io_buffer *head) { char *data = head->write_buf; if (!strcmp(data, "manage_by_non_root")) { tomoyo_manage_by_non_root = !head->w.is_delete; return 0; } return tomoyo_update_manager_entry(data, head->w.is_delete); } /** * tomoyo_read_manager - Read manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_manager(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) { struct tomoyo_manager *ptr = list_entry(head->r.acl, typeof(*ptr), head.list); if (ptr->head.is_deleted) continue; if (!tomoyo_flush(head)) return; tomoyo_set_string(head, ptr->manager->name); tomoyo_set_lf(head); } head->r.eof = true; } /** * tomoyo_manager - Check whether the current process is a policy manager. * * Returns true if the current process is permitted to modify policy * via /sys/kernel/security/tomoyo/ interface. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_manager(void) { struct tomoyo_manager *ptr; const char *exe; const struct task_struct *task = current; const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname; bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING); if (!tomoyo_policy_loaded) return true; if (!tomoyo_manage_by_non_root && (!uid_eq(task->cred->uid, GLOBAL_ROOT_UID) || !uid_eq(task->cred->euid, GLOBAL_ROOT_UID))) return false; exe = tomoyo_get_exe(); if (!exe) return false; list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { found = true; break; } } if (!found) { /* Reduce error messages. */ static pid_t last_pid; const pid_t pid = current->pid; if (last_pid != pid) { pr_warn("%s ( %s ) is not permitted to update policies.\n", domainname->name, exe); last_pid = pid; } } kfree(exe); return found; } static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial); /** * tomoyo_select_domain - Parse select command. * * @head: Pointer to "struct tomoyo_io_buffer". * @data: String to parse. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, const char *data) { unsigned int pid; struct tomoyo_domain_info *domain = NULL; bool global_pid = false; if (strncmp(data, "select ", 7)) return false; data += 7; if (sscanf(data, "pid=%u", &pid) == 1 || (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) { struct task_struct *p; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) domain = tomoyo_find_domain(data + 7); } else if (sscanf(data, "Q=%u", &pid) == 1) { domain = tomoyo_find_domain_by_qid(pid); } else return false; head->w.domain = domain; /* Accessing read_buf is safe because head->io_sem is held. */ if (!head->read_buf) return true; /* Do nothing if open(O_WRONLY). */ memset(&head->r, 0, sizeof(head->r)); head->r.print_this_domain_only = true; if (domain) head->r.domain = &domain->list; else head->r.eof = true; tomoyo_io_printf(head, "# select %s\n", data); if (domain && domain->is_deleted) tomoyo_io_printf(head, "# This is a deleted domain.\n"); return true; } /** * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head); return p1->domainname == p2->domainname; } /** * tomoyo_write_task - Update task related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_task(struct tomoyo_acl_param *param) { int error = -EINVAL; if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) { struct tomoyo_task_acl e = { .head.type = TOMOYO_TYPE_MANUAL_TASK_ACL, .domainname = tomoyo_get_domainname(param), }; if (e.domainname) error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_task_acl, NULL); tomoyo_put_name(e.domainname); } return error; } /** * tomoyo_delete_domain - Delete a domain. * * @domainname: The name of domain. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_delete_domain(char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; if (domain->is_deleted || tomoyo_pathcmp(domain->domainname, &name)) continue; domain->is_deleted = true; break; } mutex_unlock(&tomoyo_policy_lock); return 0; } /** * tomoyo_write_domain2 - Write domain policy. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @list: Pointer to "struct list_head". * @data: Policy to be interpreted. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns, struct list_head *list, char *data, const bool is_delete) { struct tomoyo_acl_param param = { .ns = ns, .list = list, .data = data, .is_delete = is_delete, }; static const struct { const char *keyword; int (*write)(struct tomoyo_acl_param *param); } tomoyo_callback[5] = { { "file ", tomoyo_write_file }, { "network inet ", tomoyo_write_inet_network }, { "network unix ", tomoyo_write_unix_network }, { "misc ", tomoyo_write_misc }, { "task ", tomoyo_write_task }, }; u8 i; for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) { if (!tomoyo_str_starts(¶m.data, tomoyo_callback[i].keyword)) continue; return tomoyo_callback[i].write(¶m); } return -EINVAL; } /* String table for domain flags. */ const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = { [TOMOYO_DIF_QUOTA_WARNED] = "quota_exceeded\n", [TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n", }; /** * tomoyo_write_domain - Write domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct tomoyo_policy_namespace *ns; struct tomoyo_domain_info *domain = head->w.domain; const bool is_delete = head->w.is_delete; bool is_select = !is_delete && tomoyo_str_starts(&data, "select "); unsigned int idx; if (*data == '<') { int ret = 0; domain = NULL; if (is_delete) ret = tomoyo_delete_domain(data); else if (is_select) domain = tomoyo_find_domain(data); else domain = tomoyo_assign_domain(data, false); head->w.domain = domain; return ret; } if (!domain) return -EINVAL; ns = domain->ns; if (sscanf(data, "use_profile %u", &idx) == 1 && idx < TOMOYO_MAX_PROFILES) { if (!tomoyo_policy_loaded || ns->profile_ptr[idx]) if (!is_delete) domain->profile = (u8) idx; return 0; } if (sscanf(data, "use_group %u\n", &idx) == 1 && idx < TOMOYO_MAX_ACL_GROUPS) { if (!is_delete) set_bit(idx, domain->group); else clear_bit(idx, domain->group); return 0; } for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) { const char *cp = tomoyo_dif[idx]; if (strncmp(data, cp, strlen(cp) - 1)) continue; domain->flags[idx] = !is_delete; return 0; } return tomoyo_write_domain2(ns, &domain->acl_info_list, data, is_delete); } /** * tomoyo_print_condition - Print condition part. * * @head: Pointer to "struct tomoyo_io_buffer". * @cond: Pointer to "struct tomoyo_condition". * * Returns true on success, false otherwise. */ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, const struct tomoyo_condition *cond) { switch (head->r.cond_step) { case 0: head->r.cond_index = 0; head->r.cond_step++; if (cond->transit) { tomoyo_set_space(head); tomoyo_set_string(head, cond->transit->name); } fallthrough; case 1: { const u16 condc = cond->condc; const struct tomoyo_condition_element *condp = (typeof(condp)) (cond + 1); const struct tomoyo_number_union *numbers_p = (typeof(numbers_p)) (condp + condc); const struct tomoyo_name_union *names_p = (typeof(names_p)) (numbers_p + cond->numbers_count); const struct tomoyo_argv *argv = (typeof(argv)) (names_p + cond->names_count); const struct tomoyo_envp *envp = (typeof(envp)) (argv + cond->argc); u16 skip; for (skip = 0; skip < head->r.cond_index; skip++) { const u8 left = condp->left; const u8 right = condp->right; condp++; switch (left) { case TOMOYO_ARGV_ENTRY: argv++; continue; case TOMOYO_ENVP_ENTRY: envp++; continue; case TOMOYO_NUMBER_UNION: numbers_p++; break; } switch (right) { case TOMOYO_NAME_UNION: names_p++; break; case TOMOYO_NUMBER_UNION: numbers_p++; break; } } while (head->r.cond_index < condc) { const u8 match = condp->equals; const u8 left = condp->left; const u8 right = condp->right; if (!tomoyo_flush(head)) return false; condp++; head->r.cond_index++; tomoyo_set_space(head); switch (left) { case TOMOYO_ARGV_ENTRY: tomoyo_io_printf(head, "exec.argv[%lu]%s=\"", argv->index, argv->is_not ? "!" : ""); tomoyo_set_string(head, argv->value->name); tomoyo_set_string(head, "\""); argv++; continue; case TOMOYO_ENVP_ENTRY: tomoyo_set_string(head, "exec.envp[\""); tomoyo_set_string(head, envp->name->name); tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : ""); if (envp->value) { tomoyo_set_string(head, "\""); tomoyo_set_string(head, envp->value->name); tomoyo_set_string(head, "\""); } else { tomoyo_set_string(head, "NULL"); } envp++; continue; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[left]); break; } tomoyo_set_string(head, match ? "=" : "!="); switch (right) { case TOMOYO_NAME_UNION: tomoyo_print_name_union_quoted (head, names_p++); break; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[right]); break; } } } head->r.cond_step++; fallthrough; case 2: if (!tomoyo_flush(head)) break; head->r.cond_step++; fallthrough; case 3: if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) tomoyo_io_printf(head, " grant_log=%s", str_yes_no(cond->grant_log == TOMOYO_GRANTLOG_YES)); tomoyo_set_lf(head); return true; } return false; } /** * tomoyo_set_group - Print "acl_group " header keyword and category name. * * @head: Pointer to "struct tomoyo_io_buffer". * @category: Category name. * * Returns nothing. */ static void tomoyo_set_group(struct tomoyo_io_buffer *head, const char *category) { if (head->type == TOMOYO_EXCEPTIONPOLICY) { tomoyo_print_namespace(head); tomoyo_io_printf(head, "acl_group %u ", head->r.acl_group_index); } tomoyo_set_string(head, category); } /** * tomoyo_print_entry - Print an ACL entry. * * @head: Pointer to "struct tomoyo_io_buffer". * @acl: Pointer to an ACL entry. * * Returns true on success, false otherwise. */ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, struct tomoyo_acl_info *acl) { const u8 acl_type = acl->type; bool first = true; u8 bit; if (head->r.print_cond_part) goto print_cond_part; if (acl->is_deleted) return true; if (!tomoyo_flush(head)) return false; else if (acl_type == TOMOYO_TYPE_PATH_ACL) { struct tomoyo_path_acl *ptr = container_of(acl, typeof(*ptr), head); const u16 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (head->r.print_transition_related_only && bit != TOMOYO_TYPE_EXECUTE) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_path_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) { struct tomoyo_task_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "task "); tomoyo_set_string(head, "manual_domain_transition "); tomoyo_set_string(head, ptr->domainname->name); } else if (head->r.print_transition_related_only) { return true; } else if (acl_type == TOMOYO_TYPE_PATH2_ACL) { struct tomoyo_path2_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pp2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name1); tomoyo_print_name_union(head, &ptr->name2); } else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) { struct tomoyo_path_number_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->number); } else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) { struct tomoyo_mkdev_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pnnn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->mode); tomoyo_print_number_union(head, &ptr->major); tomoyo_print_number_union(head, &ptr->minor); } else if (acl_type == TOMOYO_TYPE_INET_ACL) { struct tomoyo_inet_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network inet "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_set_space(head); if (ptr->address.group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->address.group->group_name ->name); } else { char buf[128]; tomoyo_print_ip(buf, sizeof(buf), &ptr->address); tomoyo_io_printf(head, "%s", buf); } tomoyo_print_number_union(head, &ptr->port); } else if (acl_type == TOMOYO_TYPE_UNIX_ACL) { struct tomoyo_unix_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network unix "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) { struct tomoyo_mount_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "file mount"); tomoyo_print_name_union(head, &ptr->dev_name); tomoyo_print_name_union(head, &ptr->dir_name); tomoyo_print_name_union(head, &ptr->fs_type); tomoyo_print_number_union(head, &ptr->flags); } else if (acl_type == TOMOYO_TYPE_ENV_ACL) { struct tomoyo_env_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "misc env "); tomoyo_set_string(head, ptr->env->name); } if (acl->cond) { head->r.print_cond_part = true; head->r.cond_step = 0; if (!tomoyo_flush(head)) return false; print_cond_part: if (!tomoyo_print_condition(head, acl->cond)) return false; head->r.print_cond_part = false; } else { tomoyo_set_lf(head); } return true; } /** * tomoyo_read_domain2 - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * @list: Pointer to "struct list_head". * * Caller holds tomoyo_read_lock(). * * Returns true on success, false otherwise. */ static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head, struct list_head *list) { list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_info *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (!tomoyo_print_entry(head, ptr)) return false; } head->r.acl = NULL; return true; } /** * tomoyo_read_domain - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.domain, &tomoyo_domain_list) { struct tomoyo_domain_info *domain = list_entry(head->r.domain, typeof(*domain), list); u8 i; switch (head->r.step) { case 0: if (domain->is_deleted && !head->r.print_this_domain_only) continue; /* Print domainname and flags. */ tomoyo_set_string(head, domain->domainname->name); tomoyo_set_lf(head); tomoyo_io_printf(head, "use_profile %u\n", domain->profile); for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++) if (domain->flags[i]) tomoyo_set_string(head, tomoyo_dif[i]); head->r.index = 0; head->r.step++; fallthrough; case 1: while (head->r.index < TOMOYO_MAX_ACL_GROUPS) { i = head->r.index++; if (!test_bit(i, domain->group)) continue; tomoyo_io_printf(head, "use_group %u\n", i); if (!tomoyo_flush(head)) return; } head->r.index = 0; head->r.step++; tomoyo_set_lf(head); fallthrough; case 2: if (!tomoyo_read_domain2(head, &domain->acl_info_list)) return; head->r.step++; if (!tomoyo_set_lf(head)) return; fallthrough; case 3: head->r.step = 0; if (head->r.print_this_domain_only) goto done; } } done: head->r.eof = true; } /** * tomoyo_write_pid: Specify PID to obtain domainname. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_pid(struct tomoyo_io_buffer *head) { head->r.eof = false; return 0; } /** * tomoyo_read_pid - Get domainname of the specified PID. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns the domainname which the specified PID is in on success, * empty string otherwise. * The PID is specified by tomoyo_write_pid() so that the user can obtain * using read()/write() interface rather than sysctl() interface. */ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) { char *buf = head->write_buf; bool global_pid = false; unsigned int pid; struct task_struct *p; struct tomoyo_domain_info *domain = NULL; /* Accessing write_buf is safe because head->io_sem is held. */ if (!buf) { head->r.eof = true; return; /* Do nothing if open(O_RDONLY). */ } if (head->r.w_pos || head->r.eof) return; head->r.eof = true; if (tomoyo_str_starts(&buf, "global-pid ")) global_pid = true; if (kstrtouint(buf, 10, &pid)) return; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); if (!domain) return; tomoyo_io_printf(head, "%u %u ", pid, domain->profile); tomoyo_set_string(head, domain->domainname->name); } /* String table for domain transition control keywords. */ static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = { [TOMOYO_TRANSITION_CONTROL_NO_RESET] = "no_reset_domain ", [TOMOYO_TRANSITION_CONTROL_RESET] = "reset_domain ", [TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ", [TOMOYO_TRANSITION_CONTROL_INITIALIZE] = "initialize_domain ", [TOMOYO_TRANSITION_CONTROL_NO_KEEP] = "no_keep_domain ", [TOMOYO_TRANSITION_CONTROL_KEEP] = "keep_domain ", }; /* String table for grouping keywords. */ static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = { [TOMOYO_PATH_GROUP] = "path_group ", [TOMOYO_NUMBER_GROUP] = "number_group ", [TOMOYO_ADDRESS_GROUP] = "address_group ", }; /** * tomoyo_write_exception - Write exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_exception(struct tomoyo_io_buffer *head) { const bool is_delete = head->w.is_delete; struct tomoyo_acl_param param = { .ns = head->w.ns, .is_delete = is_delete, .data = head->write_buf, }; u8 i; if (tomoyo_str_starts(¶m.data, "aggregator ")) return tomoyo_write_aggregator(¶m); for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++) if (tomoyo_str_starts(¶m.data, tomoyo_transition_type[i])) return tomoyo_write_transition_control(¶m, i); for (i = 0; i < TOMOYO_MAX_GROUP; i++) if (tomoyo_str_starts(¶m.data, tomoyo_group_name[i])) return tomoyo_write_group(¶m, i); if (tomoyo_str_starts(¶m.data, "acl_group ")) { unsigned int group; char *data; group = simple_strtoul(param.data, &data, 10); if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ') return tomoyo_write_domain2 (head->w.ns, &head->w.ns->acl_group[group], data, is_delete); } return -EINVAL; } /** * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->group_list[idx]; list_for_each_cookie(head->r.group, list) { struct tomoyo_group *group = list_entry(head->r.group, typeof(*group), head.list); list_for_each_cookie(head->r.acl, &group->member_list) { struct tomoyo_acl_head *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (ptr->is_deleted) continue; if (!tomoyo_flush(head)) return false; tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_group_name[idx]); tomoyo_set_string(head, group->group_name->name); if (idx == TOMOYO_PATH_GROUP) { tomoyo_set_space(head); tomoyo_set_string(head, container_of (ptr, struct tomoyo_path_group, head)->member_name->name); } else if (idx == TOMOYO_NUMBER_GROUP) { tomoyo_print_number_union(head, &container_of (ptr, struct tomoyo_number_group, head)->number); } else if (idx == TOMOYO_ADDRESS_GROUP) { char buffer[128]; struct tomoyo_address_group *member = container_of(ptr, typeof(*member), head); tomoyo_print_ip(buffer, sizeof(buffer), &member->address); tomoyo_io_printf(head, " %s", buffer); } tomoyo_set_lf(head); } head->r.acl = NULL; } head->r.group = NULL; return true; } /** * tomoyo_read_policy - Read "struct tomoyo_..._entry" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->policy_list[idx]; list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_head *acl = container_of(head->r.acl, typeof(*acl), list); if (acl->is_deleted) continue; if (!tomoyo_flush(head)) return false; switch (idx) { case TOMOYO_ID_TRANSITION_CONTROL: { struct tomoyo_transition_control *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_transition_type [ptr->type]); tomoyo_set_string(head, ptr->program ? ptr->program->name : "any"); tomoyo_set_string(head, " from "); tomoyo_set_string(head, ptr->domainname ? ptr->domainname->name : "any"); } break; case TOMOYO_ID_AGGREGATOR: { struct tomoyo_aggregator *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, "aggregator "); tomoyo_set_string(head, ptr->original_name->name); tomoyo_set_space(head); tomoyo_set_string(head, ptr->aggregated_name->name); } break; default: continue; } tomoyo_set_lf(head); } head->r.acl = NULL; return true; } /** * tomoyo_read_exception - Read exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_exception(struct tomoyo_io_buffer *head) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); if (head->r.eof) return; while (head->r.step < TOMOYO_MAX_POLICY && tomoyo_read_policy(head, head->r.step)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP && tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP + TOMOYO_MAX_ACL_GROUPS) { head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY - TOMOYO_MAX_GROUP; if (!tomoyo_read_domain2(head, &ns->acl_group [head->r.acl_group_index])) return; head->r.step++; } head->r.eof = true; } /* Wait queue for kernel -> userspace notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait); /* Wait queue for userspace -> kernel notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait); /* Structure for query. */ struct tomoyo_query { struct list_head list; struct tomoyo_domain_info *domain; char *query; size_t query_len; unsigned int serial; u8 timer; u8 answer; u8 retry; }; /* The list for "struct tomoyo_query". */ static LIST_HEAD(tomoyo_query_list); /* Lock for manipulating tomoyo_query_list. */ static DEFINE_SPINLOCK(tomoyo_query_list_lock); /* * Number of "struct file" referring /sys/kernel/security/tomoyo/query * interface. */ static atomic_t tomoyo_query_observers = ATOMIC_INIT(0); /** * tomoyo_truncate - Truncate a line. * * @str: String to truncate. * * Returns length of truncated @str. */ static int tomoyo_truncate(char *str) { char *start = str; while (*(unsigned char *) str > (unsigned char) ' ') str++; *str = '\0'; return strlen(start) + 1; } /** * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode. * * @domain: Pointer to "struct tomoyo_domain_info". * @header: Lines containing ACL. * * Returns nothing. */ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) { char *buffer; char *realpath = NULL; char *argv0 = NULL; char *symlink = NULL; char *cp = strchr(header, '\n'); int len; if (!cp) return; cp = strchr(cp + 1, '\n'); if (!cp) return; *cp++ = '\0'; len = strlen(cp) + 1; /* strstr() will return NULL if ordering is wrong. */ if (*cp == 'f') { argv0 = strstr(header, " argv[]={ \""); if (argv0) { argv0 += 10; len += tomoyo_truncate(argv0) + 14; } realpath = strstr(header, " exec={ realpath=\""); if (realpath) { realpath += 8; len += tomoyo_truncate(realpath) + 6; } symlink = strstr(header, " symlink.target=\""); if (symlink) len += tomoyo_truncate(symlink + 1) + 1; } buffer = kmalloc(len, GFP_NOFS); if (!buffer) return; snprintf(buffer, len - 1, "%s", cp); if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0); if (symlink) tomoyo_addprintf(buffer, len, "%s", symlink); tomoyo_normalize_line(buffer); if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer, false)) tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); kfree(buffer); } /** * tomoyo_supervisor - Ask for the supervisor's decision. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns 0 if the supervisor decided to permit the access request which * violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the * supervisor decided to retry the access request which violated the policy in * enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise. */ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int error; int len; static unsigned int tomoyo_serial; struct tomoyo_query entry = { }; bool quota_exceeded = false; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); /* Write /sys/kernel/security/tomoyo/audit. */ va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); /* Nothing more to do if granted. */ if (r->granted) return 0; if (r->mode) tomoyo_update_stat(r->mode); switch (r->mode) { case TOMOYO_CONFIG_ENFORCING: error = -EPERM; if (atomic_read(&tomoyo_query_observers)) break; goto out; case TOMOYO_CONFIG_LEARNING: error = 0; /* Check max_learning_entry parameter. */ if (tomoyo_domain_quota_is_ok(r)) break; fallthrough; default: return 0; } /* Get message. */ va_start(args, fmt); entry.query = tomoyo_init_log(r, len, fmt, args); va_end(args); if (!entry.query) goto out; entry.query_len = strlen(entry.query) + 1; if (!error) { tomoyo_add_entry(r->domain, entry.query); goto out; } len = kmalloc_size_roundup(entry.query_len); entry.domain = r->domain; spin_lock(&tomoyo_query_list_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] && tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len >= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) { quota_exceeded = true; } else { entry.serial = tomoyo_serial++; entry.retry = r->retry; tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len; list_add_tail(&entry.list, &tomoyo_query_list); } spin_unlock(&tomoyo_query_list_lock); if (quota_exceeded) goto out; /* Give 10 seconds for supervisor's opinion. */ while (entry.timer < 10) { wake_up_all(&tomoyo_query_wait); if (wait_event_interruptible_timeout (tomoyo_answer_wait, entry.answer || !atomic_read(&tomoyo_query_observers), HZ)) break; entry.timer++; } spin_lock(&tomoyo_query_list_lock); list_del(&entry.list); tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len; spin_unlock(&tomoyo_query_list_lock); switch (entry.answer) { case 3: /* Asked to retry by administrator. */ error = TOMOYO_RETRY_REQUEST; r->retry++; break; case 1: /* Granted by administrator. */ error = 0; break; default: /* Timed out or rejected by administrator. */ break; } out: kfree(entry.query); return error; } /** * tomoyo_find_domain_by_qid - Get domain by query id. * * @serial: Query ID assigned by tomoyo_supervisor(). * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. */ static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial) { struct tomoyo_query *ptr; struct tomoyo_domain_info *domain = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each_entry(ptr, &tomoyo_query_list, list) { if (ptr->serial != serial) continue; domain = ptr->domain; break; } spin_unlock(&tomoyo_query_list_lock); return domain; } /** * tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". * * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise. * * Waits for access requests which violated policy in enforcing mode. */ static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait) { if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_query_wait, wait); if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; return 0; } /** * tomoyo_read_query - Read access requests which violated policy in enforcing mode. * * @head: Pointer to "struct tomoyo_io_buffer". */ static void tomoyo_read_query(struct tomoyo_io_buffer *head) { struct list_head *tmp; unsigned int pos = 0; size_t len = 0; char *buf; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; len = ptr->query_len; break; } spin_unlock(&tomoyo_query_list_lock); if (!len) { head->r.query_index = 0; return; } buf = kzalloc(len + 32, GFP_NOFS); if (!buf) return; pos = 0; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; /* * Some query can be skipped because tomoyo_query_list * can change, but I don't care. */ if (len == ptr->query_len) snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial, ptr->retry, ptr->query); break; } spin_unlock(&tomoyo_query_list_lock); if (buf[0]) { head->read_buf = buf; head->r.w[head->r.w_pos++] = buf; head->r.query_index++; } else { kfree(buf); } } /** * tomoyo_write_answer - Write the supervisor's decision. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, -EINVAL otherwise. */ static int tomoyo_write_answer(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct list_head *tmp; unsigned int serial; unsigned int answer; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); ptr->timer = 0; } spin_unlock(&tomoyo_query_list_lock); if (sscanf(data, "A%u=%u", &serial, &answer) != 2) return -EINVAL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (ptr->serial != serial) continue; ptr->answer = answer; /* Remove from tomoyo_query_list. */ if (ptr->answer) list_del_init(&ptr->list); break; } spin_unlock(&tomoyo_query_list_lock); return 0; } /** * tomoyo_read_version: Get version. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns version information. */ static void tomoyo_read_version(struct tomoyo_io_buffer *head) { if (!head->r.eof) { tomoyo_io_printf(head, "2.6.0"); head->r.eof = true; } } /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = { [TOMOYO_STAT_POLICY_UPDATES] = "update:", [TOMOYO_STAT_POLICY_LEARNING] = "violation in learning mode:", [TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:", [TOMOYO_STAT_POLICY_ENFORCING] = "violation in enforcing mode:", }; /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = { [TOMOYO_MEMORY_POLICY] = "policy:", [TOMOYO_MEMORY_AUDIT] = "audit log:", [TOMOYO_MEMORY_QUERY] = "query message:", }; /* Counter for number of updates. */ static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT]; /* Timestamp counter for last updated. */ static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT]; /** * tomoyo_update_stat - Update statistic counters. * * @index: Index for policy type. * * Returns nothing. */ void tomoyo_update_stat(const u8 index) { atomic_inc(&tomoyo_stat_updated[index]); tomoyo_stat_modified[index] = ktime_get_real_seconds(); } /** * tomoyo_read_stat - Read statistic data. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_stat(struct tomoyo_io_buffer *head) { u8 i; unsigned int total = 0; if (head->r.eof) return; for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) { tomoyo_io_printf(head, "Policy %-30s %10u", tomoyo_policy_headers[i], atomic_read(&tomoyo_stat_updated[i])); if (tomoyo_stat_modified[i]) { struct tomoyo_time stamp; tomoyo_convert_time(tomoyo_stat_modified[i], &stamp); tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec); } tomoyo_set_lf(head); } for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) { unsigned int used = tomoyo_memory_used[i]; total += used; tomoyo_io_printf(head, "Memory used by %-22s %10u", tomoyo_memory_headers[i], used); used = tomoyo_memory_quota[i]; if (used) tomoyo_io_printf(head, " (Quota: %10u)", used); tomoyo_set_lf(head); } tomoyo_io_printf(head, "Total memory used: %10u\n", total); head->r.eof = true; } /** * tomoyo_write_stat - Set memory quota. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_stat(struct tomoyo_io_buffer *head) { char *data = head->write_buf; u8 i; if (tomoyo_str_starts(&data, "Memory used by ")) for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) if (tomoyo_str_starts(&data, tomoyo_memory_headers[i])) sscanf(data, "%u", &tomoyo_memory_quota[i]); return 0; } /** * tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface. * * @type: Type of interface. * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ int tomoyo_open_control(const u8 type, struct file *file) { struct tomoyo_io_buffer *head = kzalloc(sizeof(*head), GFP_NOFS); if (!head) return -ENOMEM; mutex_init(&head->io_sem); head->type = type; switch (type) { case TOMOYO_DOMAINPOLICY: /* /sys/kernel/security/tomoyo/domain_policy */ head->write = tomoyo_write_domain; head->read = tomoyo_read_domain; break; case TOMOYO_EXCEPTIONPOLICY: /* /sys/kernel/security/tomoyo/exception_policy */ head->write = tomoyo_write_exception; head->read = tomoyo_read_exception; break; case TOMOYO_AUDIT: /* /sys/kernel/security/tomoyo/audit */ head->poll = tomoyo_poll_log; head->read = tomoyo_read_log; break; case TOMOYO_PROCESS_STATUS: /* /sys/kernel/security/tomoyo/.process_status */ head->write = tomoyo_write_pid; head->read = tomoyo_read_pid; break; case TOMOYO_VERSION: /* /sys/kernel/security/tomoyo/version */ head->read = tomoyo_read_version; head->readbuf_size = 128; break; case TOMOYO_STAT: /* /sys/kernel/security/tomoyo/stat */ head->write = tomoyo_write_stat; head->read = tomoyo_read_stat; head->readbuf_size = 1024; break; case TOMOYO_PROFILE: /* /sys/kernel/security/tomoyo/profile */ head->write = tomoyo_write_profile; head->read = tomoyo_read_profile; break; case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */ head->poll = tomoyo_poll_query; head->write = tomoyo_write_answer; head->read = tomoyo_read_query; break; case TOMOYO_MANAGER: /* /sys/kernel/security/tomoyo/manager */ head->write = tomoyo_write_manager; head->read = tomoyo_read_manager; break; } if (!(file->f_mode & FMODE_READ)) { /* * No need to allocate read_buf since it is not opened * for reading. */ head->read = NULL; head->poll = NULL; } else if (!head->poll) { /* Don't allocate read_buf for poll() access. */ if (!head->readbuf_size) head->readbuf_size = 4096 * 2; head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS); if (!head->read_buf) { kfree(head); return -ENOMEM; } } if (!(file->f_mode & FMODE_WRITE)) { /* * No need to allocate write_buf since it is not opened * for writing. */ head->write = NULL; } else if (head->write) { head->writebuf_size = 4096 * 2; head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS); if (!head->write_buf) { kfree(head->read_buf); kfree(head); return -ENOMEM; } } /* * If the file is /sys/kernel/security/tomoyo/query , increment the * observer counter. * The obserber counter is used by tomoyo_supervisor() to see if * there is some process monitoring /sys/kernel/security/tomoyo/query. */ if (type == TOMOYO_QUERY) atomic_inc(&tomoyo_query_observers); file->private_data = head; tomoyo_notify_gc(head, true); return 0; } /** * tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, * EPOLLOUT | EPOLLWRNORM otherwise. */ __poll_t tomoyo_poll_control(struct file *file, poll_table *wait) { struct tomoyo_io_buffer *head = file->private_data; if (head->poll) return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM; return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM; } /** * tomoyo_set_namespace_cursor - Set namespace to read. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head) { struct list_head *ns; if (head->type != TOMOYO_EXCEPTIONPOLICY && head->type != TOMOYO_PROFILE) return; /* * If this is the first read, or reading previous namespace finished * and has more namespaces to read, update the namespace cursor. */ ns = head->r.ns; if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) { /* Clearing is OK because tomoyo_flush() returned true. */ memset(&head->r, 0, sizeof(head->r)); head->r.ns = ns ? ns->next : tomoyo_namespace_list.next; } } /** * tomoyo_has_more_namespace - Check for unread namespaces. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if we have more entries to print, false otherwise. */ static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head) { return (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) && head->r.eof && head->r.ns->next != &tomoyo_namespace_list; } /** * tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to write to. * @buffer_len: Size of @buffer. * * Returns bytes read on success, negative value otherwise. */ ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len) { int len; int idx; if (!head->read) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; head->read_user_buf = buffer; head->read_user_buf_avail = buffer_len; idx = tomoyo_read_lock(); if (tomoyo_flush(head)) /* Call the policy handler. */ do { tomoyo_set_namespace_cursor(head); head->read(head); } while (tomoyo_flush(head) && tomoyo_has_more_namespace(head)); tomoyo_read_unlock(idx); len = head->read_user_buf - buffer; mutex_unlock(&head->io_sem); return len; } /** * tomoyo_parse_policy - Parse a policy line. * * @head: Pointer to "struct tomoyo_io_buffer". * @line: Line to parse. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line) { /* Delete request? */ head->w.is_delete = !strncmp(line, "delete ", 7); if (head->w.is_delete) memmove(line, line + 7, strlen(line + 7) + 1); /* Selecting namespace to update. */ if (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) { if (*line == '<') { char *cp = strchr(line, ' '); if (cp) { *cp++ = '\0'; head->w.ns = tomoyo_assign_namespace(line); memmove(line, cp, strlen(cp) + 1); } else head->w.ns = NULL; } else head->w.ns = &tomoyo_kernel_namespace; /* Don't allow updating if namespace is invalid. */ if (!head->w.ns) return -ENOENT; } /* Do the update. */ return head->write(head); } /** * tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to read from. * @buffer_len: Size of @buffer. * * Returns @buffer_len on success, negative value otherwise. */ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len) { int error = buffer_len; size_t avail_len = buffer_len; char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ while (avail_len > 0) { char c; if (head->w.avail >= head->writebuf_size - 1) { const int len = head->writebuf_size * 2; char *cp = kzalloc(len, GFP_NOFS); if (!cp) { error = -ENOMEM; break; } memmove(cp, cp0, head->w.avail); kfree(cp0); head->write_buf = cp; cp0 = cp; head->writebuf_size = len; } if (get_user(c, buffer)) { error = -EFAULT; break; } buffer++; avail_len--; cp0[head->w.avail++] = c; if (c != '\n') continue; cp0[head->w.avail - 1] = '\0'; head->w.avail = 0; tomoyo_normalize_line(cp0); if (!strcmp(cp0, "reset")) { head->w.ns = &tomoyo_kernel_namespace; head->w.domain = NULL; memset(&head->r, 0, sizeof(head->r)); continue; } /* Don't allow updating policies by non manager programs. */ switch (head->type) { case TOMOYO_PROCESS_STATUS: /* This does not write anything. */ break; case TOMOYO_DOMAINPOLICY: if (tomoyo_select_domain(head, cp0)) continue; fallthrough; case TOMOYO_EXCEPTIONPOLICY: if (!strcmp(cp0, "select transition_only")) { head->r.print_transition_related_only = true; continue; } fallthrough; default: if (!tomoyo_manager()) { error = -EPERM; goto out; } } switch (tomoyo_parse_policy(head, cp0)) { case -EPERM: error = -EPERM; goto out; case 0: switch (head->type) { case TOMOYO_DOMAINPOLICY: case TOMOYO_EXCEPTIONPOLICY: case TOMOYO_STAT: case TOMOYO_PROFILE: case TOMOYO_MANAGER: tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); break; default: break; } break; } } out: tomoyo_read_unlock(idx); mutex_unlock(&head->io_sem); return error; } /** * tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". */ void tomoyo_close_control(struct tomoyo_io_buffer *head) { /* * If the file is /sys/kernel/security/tomoyo/query , decrement the * observer counter. */ if (head->type == TOMOYO_QUERY && atomic_dec_and_test(&tomoyo_query_observers)) wake_up_all(&tomoyo_answer_wait); tomoyo_notify_gc(head, false); } /** * tomoyo_check_profile - Check all profiles currently assigned to domains are defined. */ void tomoyo_check_profile(void) { struct tomoyo_domain_info *domain; const int idx = tomoyo_read_lock(); tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; if (ns->profile_version == 20110903) { pr_info_once("Converting profile version from %u to %u.\n", 20110903, 20150505); ns->profile_version = 20150505; } if (ns->profile_version != 20150505) pr_err("Profile version %u is not supported.\n", ns->profile_version); else if (!ns->profile_ptr[profile]) pr_err("Profile %u (used by '%s') is not defined.\n", profile, domain->domainname->name); else continue; pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n"); pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n"); panic("STOP!"); } tomoyo_read_unlock(idx); pr_info("Mandatory Access Control activated.\n"); } /** * tomoyo_load_builtin_policy - Load built-in policy. * * Returns nothing. */ void __init tomoyo_load_builtin_policy(void) { #ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING static char tomoyo_builtin_profile[] __initdata = "PROFILE_VERSION=20150505\n" "0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n"; static char tomoyo_builtin_exception_policy[] __initdata = "aggregator proc:/self/exe /proc/self/exe\n"; static char tomoyo_builtin_domain_policy[] __initdata = ""; static char tomoyo_builtin_manager[] __initdata = ""; static char tomoyo_builtin_stat[] __initdata = ""; #else /* * This include file is manually created and contains built-in policy * named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy", * "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager", * "tomoyo_builtin_stat" in the form of "static char [] __initdata". */ #include "builtin-policy.h" #endif u8 i; const int idx = tomoyo_read_lock(); for (i = 0; i < 5; i++) { struct tomoyo_io_buffer head = { }; char *start = ""; switch (i) { case 0: start = tomoyo_builtin_profile; head.type = TOMOYO_PROFILE; head.write = tomoyo_write_profile; break; case 1: start = tomoyo_builtin_exception_policy; head.type = TOMOYO_EXCEPTIONPOLICY; head.write = tomoyo_write_exception; break; case 2: start = tomoyo_builtin_domain_policy; head.type = TOMOYO_DOMAINPOLICY; head.write = tomoyo_write_domain; break; case 3: start = tomoyo_builtin_manager; head.type = TOMOYO_MANAGER; head.write = tomoyo_write_manager; break; case 4: start = tomoyo_builtin_stat; head.type = TOMOYO_STAT; head.write = tomoyo_write_stat; break; } while (1) { char *end = strchr(start, '\n'); if (!end) break; *end = '\0'; tomoyo_normalize_line(start); head.write_buf = start; tomoyo_parse_policy(&head, start); start = end + 1; } } tomoyo_read_unlock(idx); #ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER tomoyo_check_profile(); #endif } |
| 1097 1097 1097 1099 1096 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #else #error "Unknown SRCU implementation specified to kernel configuration" #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); #ifdef CONFIG_TINY_SRCU #define __srcu_read_lock_lite __srcu_read_lock #define __srcu_read_unlock_lite __srcu_read_unlock #else // #ifdef CONFIG_TINY_SRCU int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp); #endif // #else // #ifdef CONFIG_TINY_SRCU void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 /** * get_completed_synchronize_srcu - Return a pre-completed polled state cookie * * Returns a value that poll_state_synchronize_srcu() will always treat * as a cookie whose grace period has already completed. */ static inline unsigned long get_completed_synchronize_srcu(void) { return SRCU_GET_STATE_COMPLETED; } unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); // Maximum number of unsigned long values corresponding to // not-yet-completed SRCU grace periods. #define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 /** * same_state_synchronize_srcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or * get_completed_synchronize_srcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); #else static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) { return __srcu_read_lock(ssp); } static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) { __srcu_read_unlock(ssp, idx); } #endif /* CONFIG_NEED_SRCU_NMI_SAFE */ void srcu_init(void); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } /* * Annotations provide deadlock detection for SRCU. * * Similar to other lockdep annotations, except there is an additional * srcu_lock_sync(), which is basically an empty *write*-side critical section, * see lock_sync() for more information. */ /* Annotates a srcu_read_lock() */ static inline void srcu_lock_acquire(struct lockdep_map *map) { lock_map_acquire_read(map); } /* Annotates a srcu_read_lock() */ static inline void srcu_lock_release(struct lockdep_map *map) { lock_map_release(map); } /* Annotates a synchronize_srcu() */ static inline void srcu_lock_sync(struct lockdep_map *map) { lock_map_sync(map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #define srcu_lock_acquire(m) do { } while (0) #define srcu_lock_release(m) do { } while (0) #define srcu_lock_sync(m) do { } while (0) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * The return value from srcu_read_lock() must be passed unaltered * to the matching srcu_read_unlock(). Note that srcu_read_lock() and * the matching srcu_read_unlock() must occur in the same context, for * example, it is illegal to invoke srcu_read_unlock() in an irq handler * if the matching srcu_read_lock() was invoked in process context. Or, * for that matter to invoke srcu_read_unlock() from one task and the * matching srcu_read_lock() from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_lite - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but for a light-weight * smp_mb()-free reader. See srcu_read_lock() for more information. * * If srcu_read_lock_lite() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. Note that grace-period auto-expediting is disabled for _lite * srcu_struct structures because auto-expedited grace periods invoke * synchronize_rcu_expedited(), IPIs and all. * * Note that srcu_read_lock_lite() can be invoked only from those contexts * where RCU is watching, that is, from contexts where it would be legal * to invoke rcu_read_lock(). Otherwise, lockdep will complain. */ static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor_lite(ssp); retval = __srcu_read_lock_lite(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. * * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } /** * srcu_down_read - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section. Note that * SRCU read-side critical sections may be nested. However, it is * illegal to call anything that waits on an SRCU grace period for the * same srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). But if you want lockdep to help you * keep this stuff straight, you should instead use srcu_read_lock(). * * The semaphore-like nature of srcu_down_read() means that the matching * srcu_up_read() can be invoked from some other context, for example, * from some other task or from an irq handler. However, neither * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler. * * Calls to srcu_down_read() may be nested, similar to the manner in * which calls to down_read() may be nested. */ static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit a light-weight SRCU read-side critical section. */ static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock_lite(ssp, idx); } /** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but in an NMI-safe manner. */ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * srcu_up_read - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read(). */ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } /** * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock * * Converts the preceding srcu_read_lock into a two-way memory barrier. * * Call this after srcu_read_lock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_lock will appear to happen after * the preceding srcu_read_lock. */ static inline void smp_mb__after_srcu_read_lock(void) { /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ } DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), int idx) #endif |
| 307 309 55 55 150 55 47 165 33 165 194 194 194 194 363 225 184 363 213 194 194 193 363 363 110 305 50 359 4 103 46 63 20 363 126 126 126 1 89 1 1 1 136 136 84 210 44 44 194 178 172 178 178 84 42 25 27 42 42 66 27 79 84 7 7 84 84 84 136 118 19 86 136 136 136 135 27 288 288 204 136 58 92 288 359 360 360 360 360 359 360 360 360 27 360 362 363 363 363 363 363 261 261 261 261 261 261 261 261 261 261 261 260 261 261 261 261 261 261 261 261 261 261 261 261 261 261 261 261 261 1 212 195 13 13 13 13 7 6 6 106 10 44 154 72 22 72 22 23 1 23 12 23 1 23 1 23 23 23 23 1 23 8 23 23 9 23 1 1 23 23 23 1 23 1 1 23 1 23 2 2 2 214 195 156 212 89 156 31 156 156 156 156 156 214 212 4 120 114 10 4 117 55 63 191 191 178 13 7 191 257 125 117 20 106 11 90 37 37 117 117 55 63 117 117 117 117 114 29 135 134 47 47 135 135 106 3 103 103 2 8 8 1 7 7 1 7 13 13 1 13 181 8 13 193 2 127 277 275 320 24 24 23 9 9 8 9 319 318 320 320 309 31 318 298 127 320 320 358 356 62 151 216 357 275 196 356 358 357 294 123 357 59 296 124 123 358 233 16 15 15 6 15 233 233 139 136 15 136 136 31 16 125 45 42 43 41 42 882 883 202 158 56 202 158 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/kmsan.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/memory-tiers.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <linux/sched/sysctl.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #include "swap.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NUMA unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif static vm_fault_t do_fault(struct vm_fault *vmf); static vm_fault_t do_anonymous_page(struct vm_fault *vmf); static bool vmf_pte_changed(struct vm_fault *vmf); /* * Return true if the original pte was a uffd-wp pte marker (so the pte was * wr-protected). */ static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) { if (!userfaultfd_wp(vmf->vma)) return false; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return false; return pte_marker_uffd_wp(vmf->orig_pte); } /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_wants_old_prefaulted_pte static inline bool arch_wants_old_prefaulted_pte(void) { /* * Transitioning a PTE from 'old' to 'young' can be expensive on * some architectures, even if it's performed in hardware. By * default, "false" means prefaulted entries will be 'young'. */ return false; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member) { trace_rss_stat(mm, member); } /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked) { struct unlink_vma_file_batch vb; do { unsigned long addr = vma->vm_start; struct vm_area_struct *next; /* * Note: USER_PGTABLES_CEILING may be passed as ceiling and may * be 0. This will underflow and is okay. */ next = mas_find(mas, ceiling - 1); if (unlikely(xa_is_zero(next))) next = NULL; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ if (mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); if (is_vm_hugetlb_page(vma)) { unlink_file_vma(vma); hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { unlink_file_vma_batch_init(&vb); unlink_file_vma_batch_add(&vb, vma); /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = mas_find(mas, ceiling - 1); if (unlikely(xa_is_zero(next))) next = NULL; if (mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma_batch_add(&vb, vma); } unlink_file_vma_batch_final(&vb); free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } while (vma); } void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte) { spinlock_t *ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ pmd_populate(mm, pmd, *pte); *pte = NULL; } spin_unlock(ptl); } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ smp_wmb(); /* See comment in pmd_install() */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps read_folio:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->read_folio : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The only exception are zeropages, which are * *never* refcounted. * * The disadvantage is that pages are refcounted (which can be slower and * simply not an option for some PFNMAP users). The advantage is that we * don't have to follow the strict linearity rule of PFNMAP mappings in * order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) /* * NOTE: New users of ZONE_DEVICE will not set pte_devmap() * and will have refcounts incremented on their struct pages * when they are inserted into PTEs, thus they are safe to * return here. Legacy ZONE_DEVICE pages that set pte_devmap() * do not have refcounts. Example of legacy ZONE_DEVICE is * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers. */ return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; if (is_zero_pfn(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: VM_WARN_ON_ONCE(is_zero_pfn(pfn)); return pfn_to_page(pfn); } struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { struct page *page = vm_normal_page(vma, addr, pte); if (page) return page_folio(page); return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* Currently it's only used for huge pfnmaps */ if (unlikely(pmd_special(pmd))) return NULL; if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { struct page *page = vm_normal_page_pmd(vma, addr, pmd); if (page) return page_folio(page); return NULL; } #endif static void restore_exclusive_pte(struct vm_area_struct *vma, struct page *page, unsigned long address, pte_t *ptep) { struct folio *folio = page_folio(page); pte_t orig_pte; pte_t pte; swp_entry_t entry; orig_pte = ptep_get(ptep); pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); if (pte_swp_soft_dirty(orig_pte)) pte = pte_mksoft_dirty(pte); entry = pte_to_swp_entry(orig_pte); if (pte_swp_uffd_wp(orig_pte)) pte = pte_mkuffd_wp(pte); else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); VM_BUG_ON_FOLIO(pte_write(pte) && (!folio_test_anon(folio) && PageAnonExclusive(page)), folio); /* * No need to take a page reference as one was already * created when the swap entry was made. */ if (folio_test_anon(folio)) folio_add_anon_rmap_pte(folio, page, vma, address, RMAP_NONE); else /* * Currently device exclusive access only supports anonymous * memory so the entry shouldn't point to a filebacked page. */ WARN_ON_ONCE(1); set_pte_at(vma->vm_mm, address, ptep, pte); /* * No need to invalidate - it was non-present before. However * secondary CPUs may have mappings that need invalidating. */ update_mmu_cache(vma, address, ptep); } /* * Tries to restore an exclusive pte if the page lock can be acquired without * sleeping. */ static int try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr) { swp_entry_t entry = pte_to_swp_entry(ptep_get(src_pte)); struct page *page = pfn_swap_entry_to_page(entry); if (trylock_page(page)) { restore_exclusive_pte(vma, page, addr, src_pte); unlock_page(page); return 0; } return -EBUSY; } /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t orig_pte = ptep_get(src_pte); pte_t pte = orig_pte; struct folio *folio; struct page *page; swp_entry_t entry = pte_to_swp_entry(orig_pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return -EIO; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } /* Mark the swap entry as shared. */ if (pte_swp_exclusive(orig_pte)) { pte = pte_swp_clear_exclusive(orig_pte); set_pte_at(src_mm, addr, src_pte, pte); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { folio = pfn_swap_entry_folio(entry); rss[mm_counter(folio)]++; if (!is_readable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both parent and child * to be set to read. A previously exclusive entry is * now shared. */ entry = make_readable_migration_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(orig_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(orig_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = pfn_swap_entry_to_page(entry); folio = page_folio(page); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ folio_get(folio); rss[mm_counter(folio)]++; /* Cannot fail as these pages cannot get pinned. */ folio_try_dup_anon_rmap_pte(folio, page, src_vma); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_writable_device_private_entry(entry) && is_cow_mapping(vm_flags)) { entry = make_readable_device_private_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(orig_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_exclusive_entry(entry)) { /* * Make device exclusive entries present by restoring the * original entry then copying as for a present pte. Device * exclusive entries currently only support private writable * (ie. COW) mappings. */ VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); if (try_restore_exclusive_pte(src_pte, src_vma, addr)) return -EBUSY; return -ENOENT; } else if (is_pte_marker_entry(entry)) { pte_marker marker = copy_pte_marker(entry, dst_vma); if (marker) set_pte_at(dst_mm, addr, dst_pte, make_pte_marker(marker)); return 0; } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page. * * NOTE! The usual case is that this isn't required; * instead, the caller can just increase the page refcount * and re-use the pte the traditional way. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct folio **prealloc, struct page *page) { struct folio *new_folio; pte_t pte; new_folio = *prealloc; if (!new_folio) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ if (copy_mc_user_highpage(&new_folio->page, page, addr, src_vma)) return -EHWPOISON; *prealloc = NULL; __folio_mark_uptodate(new_folio); folio_add_new_anon_rmap(new_folio, dst_vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, dst_vma); rss[MM_ANONPAGES]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(&new_folio->page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, ptep_get(src_pte))) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_mkuffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, int nr) { struct mm_struct *src_mm = src_vma->vm_mm; /* If it's a COW mapping, write protect it both processes. */ if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) { wrprotect_ptes(src_mm, addr, src_pte, nr); pte = pte_wrprotect(pte); } /* If it's a shared mapping, mark it clean in the child. */ if (src_vma->vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_ptes(dst_vma->vm_mm, addr, dst_pte, pte, nr); } /* * Copy one present PTE, trying to batch-process subsequent PTEs that map * consecutive pages of the same folio by copying them as well. * * Returns -EAGAIN if one preallocated page is required to copy the next PTE. * Otherwise, returns the number of copied PTEs (at least 1). */ static inline int copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, int max_nr, int *rss, struct folio **prealloc) { struct page *page; struct folio *folio; bool any_writable; fpb_t flags = 0; int err, nr; page = vm_normal_page(src_vma, addr, pte); if (unlikely(!page)) goto copy_pte; folio = page_folio(page); /* * If we likely have to copy, just don't bother with batching. Make * sure that the common "small folio" case is as fast as possible * by keeping the batching logic separate. */ if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) { if (src_vma->vm_flags & VM_SHARED) flags |= FPB_IGNORE_DIRTY; if (!vma_soft_dirty_enabled(src_vma)) flags |= FPB_IGNORE_SOFT_DIRTY; nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags, &any_writable, NULL, NULL); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, nr, src_vma))) { folio_ref_sub(folio, nr); return -EAGAIN; } rss[MM_ANONPAGES] += nr; VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); } else { folio_dup_file_rmap_ptes(folio, page, nr); rss[mm_counter_file(folio)] += nr; } if (any_writable) pte = pte_mkwrite(pte, src_vma); __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, nr); return nr; } folio_get(folio); if (folio_test_anon(folio)) { /* * If this page may have been pinned by the parent process, * copy the page immediately for the child so that we'll always * guarantee the pinned page won't be randomly replaced in the * future. */ if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) { /* Page may be pinned, we have to copy. */ folio_put(folio); err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, page); return err ? err : 1; } rss[MM_ANONPAGES]++; VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); } else { folio_dup_file_rmap_pte(folio, page); rss[mm_counter_file(folio)]++; } copy_pte: __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, 1); return 1; } static inline struct folio *folio_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr, bool need_zero) { struct folio *new_folio; if (need_zero) new_folio = vma_alloc_zeroed_movable_folio(vma, addr); else new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (!new_folio) return NULL; if (mem_cgroup_charge(new_folio, src_mm, GFP_KERNEL)) { folio_put(new_folio); return NULL; } folio_throttle_swaprate(new_folio, GFP_KERNEL); return new_folio; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; pmd_t dummy_pmdval; pte_t ptent; spinlock_t *src_ptl, *dst_ptl; int progress, max_nr, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct folio *prealloc = NULL; int nr; again: progress = 0; init_rss_vec(rss); /* * copy_pmd_range()'s prior pmd_none_or_clear_bad(src_pmd), and the * error handling here, assume that exclusive mmap_lock on dst and src * protects anon from unexpected THP transitions; with shmem and file * protected by mmap_lock-less collapse skipping areas with anon_vma * (whereas vma_needs_copy() skips areas without anon_vma). A rework * can remove such assumptions later, but this is good enough for now. */ dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } /* * We already hold the exclusive mmap_lock, the copy_pte_range() and * retract_page_tables() are using vma->anon_vma to be exclusive, so * the PTE page is stable, and there is no need to get pmdval and do * pmd_same() check. */ src_pte = pte_offset_map_rw_nolock(src_mm, src_pmd, addr, &dummy_pmdval, &src_ptl); if (!src_pte) { pte_unmap_unlock(dst_pte, dst_ptl); /* ret == 0 */ goto out; } spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { nr = 1; /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } ptent = ptep_get(src_pte); if (pte_none(ptent)) { progress++; continue; } if (unlikely(!pte_present(ptent))) { ret = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (ret == -EIO) { entry = pte_to_swp_entry(ptep_get(src_pte)); break; } else if (ret == -EBUSY) { break; } else if (!ret) { progress += 8; continue; } ptent = ptep_get(src_pte); VM_WARN_ON_ONCE(!pte_present(ptent)); /* * Device exclusive entry restored, continue by copying * the now present pte. */ WARN_ON_ONCE(ret != -ENOENT); } /* copy_present_ptes() will clear `*prealloc' if consumed */ max_nr = (end - addr) / PAGE_SIZE; ret = copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, ptent, addr, max_nr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. * If copy failed due to hwpoison in source page, break out. */ if (unlikely(ret == -EAGAIN || ret == -EHWPOISON)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ folio_put(prealloc); prealloc = NULL; } nr = ret; progress += 8 * nr; } while (dst_pte += nr, src_pte += nr, addr += PAGE_SIZE * nr, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(orig_src_pte, src_ptl); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (ret == -EIO) { VM_WARN_ON_ONCE(!entry.val); if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret == -EBUSY || unlikely(ret == -EHWPOISON)) { goto out; } else if (ret == -EAGAIN) { prealloc = folio_prealloc(src_mm, src_vma, addr, false); if (!prealloc) return -ENOMEM; } else if (ret < 0) { VM_WARN_ON_ONCE(1); } /* We've captured and resolved the error. Reset, try again. */ ret = 0; if (addr != end) goto again; out: if (unlikely(prealloc)) folio_put(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } /* * Return true if the vma needs to copy the pgtable during this fork(). Return * false when we can speed up fork() by allowing lazy page faults later until * when the child accesses the memory range. */ static bool vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { /* * Always copy pgtables when dst_vma has uffd-wp enabled even if it's * file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable * contains uffd-wp protection information, that's something we can't * retrieve from page cache, and skip copying will lose those info. */ if (userfaultfd_wp(dst_vma)) return true; if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return true; if (src_vma->anon_vma) return true; /* * Don't copy ptes where a page fault will fill them correctly. Fork * becomes much lighter when there are big shared or private readonly * mappings. The tradeoff is that copy_page_range is more efficient * than faulting. */ return false; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; if (!vma_needs_copy(dst_vma, src_vma)) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { untrack_pfn_clear(dst_vma); ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; /* Or, we zap COWed pages only if the caller wants to */ return details->even_cows; } /* Decides whether we should zap this folio with the folio pointer specified */ static inline bool should_zap_folio(struct zap_details *details, struct folio *folio) { /* If we can make a decision without *folio.. */ if (should_zap_cows(details)) return true; /* Otherwise we should only zap non-anon folios */ return !folio_test_anon(folio); } static inline bool zap_drop_markers(struct zap_details *details) { if (!details) return false; return details->zap_flags & ZAP_FLAG_DROP_MARKER; } /* * This function makes sure that we'll replace the none pte with an uffd-wp * swap special pte marker when necessary. Must be with the pgtable lock held. */ static inline void zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, int nr, struct zap_details *details, pte_t pteval) { /* Zap on anonymous always means dropping everything */ if (vma_is_anonymous(vma)) return; if (zap_drop_markers(details)) return; for (;;) { /* the PFN in the PTE is irrelevant. */ pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); if (--nr == 0) break; pte++; addr += PAGE_SIZE; } } static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, struct folio *folio, struct page *page, pte_t *pte, pte_t ptent, unsigned int nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, bool *force_break) { struct mm_struct *mm = tlb->mm; bool delay_rmap = false; if (!folio_test_anon(folio)) { ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); if (pte_dirty(ptent)) { folio_mark_dirty(folio); if (tlb_delay_rmap(tlb)) { delay_rmap = true; *force_flush = true; } } if (pte_young(ptent) && likely(vma_has_recency(vma))) folio_mark_accessed(folio); rss[mm_counter(folio)] -= nr; } else { /* We don't need up-to-date accessed/dirty bits. */ clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); rss[MM_ANONPAGES] -= nr; } /* Checking a single PTE in a batch is sufficient. */ arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entries(tlb, pte, nr, addr); if (unlikely(userfaultfd_pte_wp(vma, ptent))) zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); if (!delay_rmap) { folio_remove_rmap_ptes(folio, page, nr, vma); if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; } } /* * Zap or skip at least one present PTE, trying to batch-process subsequent * PTEs that map consecutive pages of the same folio. * * Returns the number of processed (skipped or zapped) PTEs (at least 1). */ static inline int zap_present_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, bool *force_break) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; struct mm_struct *mm = tlb->mm; struct folio *folio; struct page *page; int nr; page = vm_normal_page(vma, addr, ptent); if (!page) { /* We don't need up-to-date accessed/dirty bits. */ ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entry(tlb, pte, addr); if (userfaultfd_pte_wp(vma, ptent)) zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent); ksm_might_unmap_zero_page(mm, ptent); return 1; } folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) return 1; /* * Make sure that the common "small folio" case is as fast as possible * by keeping the batching logic separate. */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags, NULL, NULL, NULL); zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, force_break); return nr; } zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr, details, rss, force_flush, force_break); return 1; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { bool force_flush = false, force_break = false; struct mm_struct *mm = tlb->mm; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; int nr; tlb_change_page_size(tlb, PAGE_SIZE); init_rss_vec(rss); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return addr; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = ptep_get(pte); struct folio *folio; struct page *page; int max_nr; nr = 1; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { max_nr = (end - addr) / PAGE_SIZE; nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr, details, rss, &force_flush, &force_break); if (unlikely(force_break)) { addr += nr * PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry) || is_device_exclusive_entry(entry)) { page = pfn_swap_entry_to_page(entry); folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) continue; /* * Both device private/exclusive mappings should only * work with anonymous page so far, so we don't need to * consider uffd-wp bit when zap. For more information, * see zap_install_uffd_wp_if_needed(). */ WARN_ON_ONCE(!vma_is_anonymous(vma)); rss[mm_counter(folio)]--; if (is_device_private_entry(entry)) folio_remove_rmap_pte(folio, page, vma); folio_put(folio); } else if (!non_swap_entry(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); /* Genuine swap entries, hence a private anon pages */ if (!should_zap_cows(details)) continue; rss[MM_SWAPENTS] -= nr; free_swap_and_cache_nr(entry, nr); } else if (is_migration_entry(entry)) { folio = pfn_swap_entry_folio(entry); if (!should_zap_folio(details, folio)) continue; rss[mm_counter(folio)]--; } else if (pte_marker_entry_uffd_wp(entry)) { /* * For anon: always drop the marker; for file: only * drop the marker if explicitly requested. */ if (!vma_is_anonymous(vma) && !zap_drop_markers(details)) continue; } else if (is_guard_swp_entry(entry)) { /* * Ordinary zapping should not remove guard PTE * markers. Only do so if we should remove PTE markers * in general. */ if (!zap_drop_markers(details)) continue; } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { if (!should_zap_cows(details)) continue; } else { /* We should have covered all the swap entry types */ pr_alert("unrecognized swap entry 0x%lx\n", entry.val); WARN_ON_ONCE(1); } clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) { tlb_flush_mmu_tlbonly(tlb); tlb_flush_rmaps(tlb, vma); } pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Come back again if we didn't do everything. */ if (force_flush) tlb_flush_mmu(tlb); return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) { addr = next; continue; } /* fall through */ } else if (details && details->single_folio && folio_test_pmd_mappable(details->single_folio) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } if (pmd_none(*pmd)) { addr = next; continue; } addr = zap_pte_range(tlb, vma, pmd, addr, next, details); if (addr != next) pmd--; } while (pmd++, cond_resched(), addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details, bool mm_wr_locked) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0, mm_wr_locked); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { zap_flags_t zap_flags = details ? details->zap_flags : 0; __unmap_hugepage_range(tlb, vma, start, end, NULL, zap_flags); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @mas: the maple state * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * @tree_end: The maximum index to check * @mm_wr_locked: lock flag * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, unsigned long tree_end, bool mm_wr_locked) { struct mmu_notifier_range range; struct zap_details details = { .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP, /* Careful - we need to zap private pages too! */ .even_cows = true, }; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); do { unsigned long start = start_addr; unsigned long end = end_addr; hugetlb_zap_begin(vma, &start, &end); unmap_single_vma(tlb, vma, start, end, &details, mm_wr_locked); hugetlb_zap_end(vma, &details); vma = mas_find(mas, tree_end - 1); } while (vma && likely(!xa_is_zero(vma))); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { const unsigned long end = address + size; struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); hugetlb_zap_begin(vma, &range.start, &range.end); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); /* * unmap 'address-end' not 'range.start-range.end' as range * could have been expanded for hugetlb pmd sharing. */ unmap_single_vma(&tlb, vma, address, end, details, false); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); hugetlb_zap_end(vma, details); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (!range_in_vma(vma, address, address + size) || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static bool vm_mixed_zeropage_allowed(struct vm_area_struct *vma) { VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP); /* * Whoever wants to forbid the zeropage after some zeropages * might already have been mapped has to scan the page tables and * bail out on any zeropages. Zeropages in COW mappings can * be unshared using FAULT_FLAG_UNSHARE faults. */ if (mm_forbids_zeropage(vma->vm_mm)) return false; /* zeropages in COW mappings are common and unproblematic. */ if (is_cow_mapping(vma->vm_flags)) return true; /* Mappings that do not allow for writable PTEs are unproblematic. */ if (!(vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) return true; /* * Why not allow any VMA that has vm_ops->pfn_mkwrite? GUP could * find the shared zeropage and longterm-pin it, which would * be problematic as soon as the zeropage gets replaced by a different * page due to vma->vm_ops->pfn_mkwrite, because what's mapped would * now differ to what GUP looked up. FSDAX is incompatible to * FOLL_LONGTERM and VM_IO is incompatible to GUP completely (see * check_vma_flags). */ return vma->vm_ops && vma->vm_ops->pfn_mkwrite && (vma_is_fsdax(vma) || vma->vm_flags & VM_IO); } static int validate_page_before_insert(struct vm_area_struct *vma, struct page *page) { struct folio *folio = page_folio(page); if (!folio_ref_count(folio)) return -EINVAL; if (unlikely(is_zero_folio(folio))) { if (!vm_mixed_zeropage_allowed(vma)) return -EINVAL; return 0; } if (folio_test_anon(folio) || folio_test_slab(folio) || page_has_type(page)) return -EINVAL; flush_dcache_folio(folio); return 0; } static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { struct folio *folio = page_folio(page); pte_t pteval; if (!pte_none(ptep_get(pte))) return -EBUSY; /* Ok, finally just insert the thing.. */ pteval = mk_pte(page, prot); if (unlikely(is_zero_folio(folio))) { pteval = pte_mkspecial(pteval); } else { folio_get(folio); inc_mm_counter(vma->vm_mm, mm_counter_file(folio)); folio_add_file_rmap_pte(folio, page, vma); } set_pte_at(vma->vm_mm, addr, pte, pteval); return 0; } static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(vma, page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(vma->vm_mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(vma, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; err = validate_page_before_insert(vma, page); if (err) return err; return insert_page_into_pte_locked(vma, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); if (!start_pte) { ret = -EFAULT; goto out; } for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(vma, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. The zeropage is supported in some VMAs, * see vm_mixed_zeropage_allowed(). * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * The zeropage is supported in some VMAs, see * vm_mixed_zeropage_allowed(). * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; entry = ptep_get(pte); if (!pte_none(entry)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(entry) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry))); goto out_unlock; } entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * pgprot typically only differs from @vma->vm_page_prot when drivers set * caching- and encryption bits different than those of @vma->vm_page_prot, * because the caching- or encryption mode may not be known at mmap() time. * * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite) { if (unlikely(is_zero_pfn(pfn_t_to_pfn(pfn))) && (mkwrite || !vm_mixed_zeropage_allowed(vma))) return false; /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, bool mkwrite) { pgprot_t pgprot = vma->vm_page_prot; int err; if (!vm_mixed_ok(vma, pfn, mkwrite)) return VM_FAULT_SIGBUS; if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, true); } /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(ptep_get(pte))); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pgd++, addr = next, addr != end); return 0; } /* * Variant of remap_pfn_range that does not call track_pfn_remap. The caller * must have pre-validated the caching bits of the pgprot_t. */ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); if (!error) return 0; /* * A partial pfn range mapping is dangerous: it does not * maintain page reference counts, and callers may free * pages due to the error. So zap it early. */ zap_page_range_single(vma, addr, size, NULL); return error; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int err; err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (err) untrack_pfn(vma, pfn, PAGE_ALIGN(size), true); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte, *mapped_pte; int err = 0; spinlock_t *ptl; if (create) { mapped_pte = pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { mapped_pte = pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return -EINVAL; } arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(ptep_get(pte))) { err = fn(pte++, addr, data); if (err) break; } } while (addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(mapped_pte, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_leaf(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (pmd_none(*pmd) && !create) continue; if (WARN_ON_ONCE(pmd_leaf(*pmd))) return -EINVAL; if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) { if (!create) continue; pmd_clear_bad(pmd); } err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (pud_none(*pud) && !create) continue; if (WARN_ON_ONCE(pud_leaf(*pud))) return -EINVAL; if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) { if (!create) continue; pud_clear_bad(pud); } err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (p4d_none(*p4d) && !create) continue; if (WARN_ON_ONCE(p4d_leaf(*p4d))) return -EINVAL; if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) { if (!create) continue; p4d_clear_bad(p4d); } err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none(*pgd) && !create) continue; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return -EINVAL; if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create) continue; pgd_clear_bad(pgd); } err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct vm_fault *vmf) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spin_lock(vmf->ptl); same = pte_same(ptep_get(vmf->pte), vmf->orig_pte); spin_unlock(vmf->ptl); } #endif pte_unmap(vmf->pte); vmf->pte = NULL; return same; } /* * Return: * 0: copied succeeded * -EHWPOISON: copy failed due to hwpoison in source page * -EAGAIN: copied failed (some other reason) */ static inline int __wp_page_copy_user(struct page *dst, struct page *src, struct vm_fault *vmf) { int ret; void *kaddr; void __user *uaddr; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { if (copy_mc_user_highpage(dst, src, addr, vma)) return -EHWPOISON; return 0; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_local_page(dst); pagefault_disable(); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ vmf->pte = NULL; if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ if (vmf->pte) update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache_range(vmf, vma, addr, vmf->pte, 1); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (vmf->pte) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ if (vmf->pte) update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = 0; pte_unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); pagefault_enable(); kunmap_local(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf, struct folio *folio) { vm_fault_t ret; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { folio_lock(folio); if (!folio->mapping) { folio_unlock(folio); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct folio *folio = page_folio(vmf->page); bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = folio_mark_dirty(folio); VM_BUG_ON_FOLIO(folio_test_anon(folio), folio); /* * Take a local copy of the address_space - folio.mapping may be zeroed * by truncate after folio_unlock(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on folio_unlock()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = folio_raw_mapping(folio); folio_unlock(folio); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_COMPLETED; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; pte_t entry; VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); VM_WARN_ON(is_zero_pfn(pte_pfn(vmf->orig_pte))); if (folio) { VM_BUG_ON(folio_test_anon(folio) && !PageAnonExclusive(vmf->page)); /* * Clear the folio's cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * We could add a bitflag somewhere, but for now, we know that all * vm_ops that have a ->map_pages have been audited and don't need * the mmap_lock to be held. */ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK)) return 0; vma_end_read(vma); return VM_FAULT_RETRY; } /** * __vmf_anon_prepare - Prepare to handle an anonymous fault. * @vmf: The vm_fault descriptor passed from the fault handler. * * When preparing to insert an anonymous page into a VMA from a * fault handler, call this function rather than anon_vma_prepare(). * If this vma does not already have an associated anon_vma and we are * only protected by the per-VMA lock, the caller must retry with the * mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to * determine if this VMA can share its anon_vma, and that's not safe to * do with only the per-VMA lock held for this VMA. * * Return: 0 if fault handling can proceed. Any other value should be * returned to the caller. */ vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; if (likely(vma->anon_vma)) return 0; if (vmf->flags & FAULT_FLAG_VMA_LOCK) { if (!mmap_read_trylock(vma->vm_mm)) return VM_FAULT_RETRY; } if (__anon_vma_prepare(vma)) ret = VM_FAULT_OOM; if (vmf->flags & FAULT_FLAG_VMA_LOCK) mmap_read_unlock(vma->vm_mm); return ret; } /* * Handle the case of a page which we actually need to copy to a new page, * either due to COW or unsharing. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct folio *old_folio = NULL; struct folio *new_folio = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; vm_fault_t ret; bool pfn_is_zero; delayacct_wpcopy_start(); if (vmf->page) old_folio = page_folio(vmf->page); ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte)); new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero); if (!new_folio) goto oom; if (!pfn_is_zero) { int err; err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); if (err) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. * The -EHWPOISON case will not be retried. */ folio_put(new_folio); if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0; } kmsan_copy_page_meta(&new_folio->page, vmf->page); } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { if (old_folio) { if (!folio_test_anon(old_folio)) { dec_mm_counter(mm, mm_counter_file(old_folio)); inc_mm_counter(mm, MM_ANONPAGES); } } else { ksm_might_unmap_zero_page(mm, vmf->orig_pte); inc_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(&new_folio->page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (unlikely(unshare)) { if (pte_soft_dirty(vmf->orig_pte)) entry = pte_mksoft_dirty(entry); if (pte_uffd_wp(vmf->orig_pte)) entry = pte_mkuffd_wp(entry); } else { entry = maybe_mkwrite(pte_mkdirty(entry), vma); } /* * Clear the pte entry and flush it first, before updating the * pte with the new entry, to keep TLBs on different CPUs in * sync. This code used to set the new PTE then flush TLBs, but * that left a window where the new PTE could be loaded into * some TLBs while the old PTE remains in others. */ ptep_clear_flush(vma, vmf->address, vmf->pte); folio_add_new_anon_rmap(new_folio, vma, vmf->address, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, vma); BUG_ON(unshare && pte_write(entry)); set_pte_at(mm, vmf->address, vmf->pte, entry); update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); if (old_folio) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * folio_remove_rmap_pte() with the ptp_clear_flush * above. Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in folio_remove_rmap_pte(); * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ folio_remove_rmap_pte(old_folio, vmf->page, vma); } /* Free the old page.. */ new_folio = old_folio; page_copied = 1; pte_unmap_unlock(vmf->pte, vmf->ptl); } else if (vmf->pte) { update_mmu_tlb(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); } mmu_notifier_invalidate_range_end(&range); if (new_folio) folio_put(new_folio); if (old_folio) { if (page_copied) free_swap_cache(old_folio); folio_put(old_folio); } delayacct_wpcopy_end(); return 0; oom: ret = VM_FAULT_OOM; out: if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); return ret; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * @folio: the folio of vmf->page * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(ptep_get(vmf->pte), vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf, folio); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); ret = vmf_can_call_fault(vmf); if (ret) return ret; vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf, NULL); } wp_page_reuse(vmf, NULL); return 0; } static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; folio_get(folio); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = vmf_can_call_fault(vmf); if (tmp) { folio_put(folio); return tmp; } tmp = do_page_mkwrite(vmf, folio); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { folio_put(folio); return tmp; } tmp = finish_mkwrite_fault(vmf, folio); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { folio_unlock(folio); folio_put(folio); return tmp; } } else { wp_page_reuse(vmf, folio); folio_lock(folio); } ret |= fault_dirty_shared_page(vmf); folio_put(folio); return ret; } static bool wp_can_reuse_anon_folio(struct folio *folio, struct vm_area_struct *vma) { /* * We could currently only reuse a subpage of a large folio if no * other subpages of the large folios are still mapped. However, * let's just consistently not reuse subpages even if we could * reuse in that scenario, and give back a large folio a bit * sooner. */ if (folio_test_large(folio)) return false; /* * We have to verify under folio lock: these early checks are * just an optimization to avoid locking the folio and freeing * the swapcache if there is little hope that we can reuse. * * KSM doesn't necessarily raise the folio refcount. */ if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) return false; if (!folio_test_lru(folio)) /* * We cannot easily detect+handle references from * remote LRU caches or references to LRU folios. */ lru_add_drain(); if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) return false; if (!folio_trylock(folio)) return false; if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { folio_unlock(folio); return false; } /* * Ok, we've got the only folio reference from our mapping * and the folio is locked, it's dark out, and we're wearing * sunglasses. Hit it. */ folio_move_anon_rmap(folio, vma); folio_unlock(folio); return true; } /* * This routine handles present pages, when * * users try to write to a shared page (FAULT_FLAG_WRITE) * * GUP wants to take a R/O pin on a possibly shared anonymous page * (FAULT_FLAG_UNSHARE) * * It is done by copying the page to a new address and decrementing the * shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've * done any necessary COW. * * In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even * though the page will change only once the write actually happens. This * avoids a few races, and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; pte_t pte; if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) { if (!userfaultfd_wp_async(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Nothing needed (cache flush, TLB invalidations, * etc.) because we're only removing the uffd-wp bit, * which is completely invisible to the user. */ pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); /* * Update this to be prepared for following up CoW * handling */ vmf->orig_pte = pte; } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); } vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (vmf->page) folio = page_folio(vmf->page); /* * Shared mapping: we are guaranteed to have VM_WRITE and * FAULT_FLAG_WRITE set at this point. */ if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if (!vmf->page) return wp_pfn_shared(vmf); return wp_page_shared(vmf, folio); } /* * Private mapping: create an exclusive anonymous page copy if reuse * is impossible. We might miss VM_WRITE for FOLL_FORCE handling. * * If we encounter a page that is marked exclusive, we must reuse * the page without further checks. */ if (folio && folio_test_anon(folio) && (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { if (!PageAnonExclusive(vmf->page)) SetPageAnonExclusive(vmf->page); if (unlikely(unshare)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } wp_page_reuse(vmf, folio); return 0; } /* * Ok, we need to copy. Oh, well.. */ if (folio) folio_get(folio); pte_unmap_unlock(vmf->pte, vmf->ptl); #ifdef CONFIG_KSM if (folio && folio_test_ksm(folio)) count_vm_event(COW_KSM); #endif return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, pgoff_t first_index, pgoff_t last_index, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, first_index, last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = max(first_index, vba); zea = min(last_index, vea); unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_folio() - Unmap single folio from processes. * @folio: The locked folio to be unmapped. * * Unmap this folio from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a folio, it may find that * the page has been remapped again: and then uses unmap_mapping_folio() * to unmap it finally. */ void unmap_mapping_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; struct zap_details details = { }; pgoff_t first_index; pgoff_t last_index; VM_BUG_ON(!folio_test_locked(folio)); first_index = folio->index; last_index = folio_next_index(folio) - 1; details.even_cows = false; details.single_folio = folio; details.zap_flags = ZAP_FLAG_DROP_MARKER; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, first_index, last_index, &details); i_mmap_unlock_read(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; pgoff_t first_index = start; pgoff_t last_index = start + nr - 1; details.even_cows = even_cows; if (last_index < first_index) last_index = ULONG_MAX; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, first_index, last_index, &details); i_mmap_unlock_read(mapping); } EXPORT_SYMBOL_GPL(unmap_mapping_pages); /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * Restore a potential device exclusive pte to a working pte entry */ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) { struct folio *folio = page_folio(vmf->page); struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; vm_fault_t ret; /* * We need a reference to lock the folio because we don't hold * the PTL so a racing thread can remove the device-exclusive * entry and unmap it. If the folio is free the entry must * have been removed already. If it happens to have already * been re-allocated after being freed all we do is lock and * unlock it. */ if (!folio_try_get(folio)) return 0; ret = folio_lock_or_retry(folio, vmf); if (ret) { folio_put(folio); return ret; } mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); mmu_notifier_invalidate_range_start(&range); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) restore_exclusive_pte(vma, vmf->page, vmf->address, vmf->pte); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); folio_unlock(folio); folio_put(folio); mmu_notifier_invalidate_range_end(&range); return 0; } static inline bool should_try_to_free_swap(struct folio *folio, struct vm_area_struct *vma, unsigned int fault_flags) { if (!folio_test_swapcache(folio)) return false; if (mem_cgroup_swap_full(folio) || (vma->vm_flags & VM_LOCKED) || folio_test_mlocked(folio)) return true; /* * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * user. Try freeing the swapcache to get rid of the swapcache * reference only in case it's likely that we'll be the exlusive user. */ return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && folio_ref_count(folio) == (1 + folio_nr_pages(folio)); } static vm_fault_t pte_marker_clear(struct vm_fault *vmf) { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) return 0; /* * Be careful so that we will only recover a special uffd-wp pte into a * none pte. Otherwise it means the pte could have changed, so retry. * * This should also cover the case where e.g. the pte changed * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_POISONED. * So is_pte_marker() check is not enough to safely drop the pte. */ if (pte_same(vmf->orig_pte, ptep_get(vmf->pte))) pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } static vm_fault_t do_pte_missing(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } /* * This is actually a page-missing access, but with uffd-wp special pte * installed. It means this pte was wr-protected before being unmapped. */ static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) { /* * Just in case there're leftover special ptes even after the region * got unregistered - we can simply clear them. */ if (unlikely(!userfaultfd_wp(vmf->vma))) return pte_marker_clear(vmf); return do_pte_missing(vmf); } static vm_fault_t handle_pte_marker(struct vm_fault *vmf) { swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte); unsigned long marker = pte_marker_get(entry); /* * PTE markers should never be empty. If anything weird happened, * the best thing to do is to kill the process along with its mm. */ if (WARN_ON_ONCE(!marker)) return VM_FAULT_SIGBUS; /* Higher priority than uffd-wp when data corrupted */ if (marker & PTE_MARKER_POISONED) return VM_FAULT_HWPOISON; /* Hitting a guard page is always a fatal condition. */ if (marker & PTE_MARKER_GUARD) return VM_FAULT_SIGSEGV; if (pte_marker_entry_uffd_wp(entry)) return pte_marker_handle_uffd_wp(vmf); /* This is an unknown pte marker */ return VM_FAULT_SIGBUS; } static struct folio *__alloc_swap_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; swp_entry_t entry; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address); if (!folio) return NULL; entry = pte_to_swp_entry(vmf->orig_pte); if (mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, GFP_KERNEL, entry)) { folio_put(folio); return NULL; } return folio; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); int i; /* * While allocating a large folio and doing swap_read_folio, which is * the case the being faulted pte doesn't have swapcache. We need to * ensure all PTEs have no cache as well, otherwise, we might go to * swap devices while the content is in swapcache. */ for (i = 0; i < max_nr; i++) { if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) return i; } return i; } /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. */ static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages) { unsigned long addr; swp_entry_t entry; int idx; pte_t pte; addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); idx = (vmf->address - addr) / PAGE_SIZE; pte = ptep_get(ptep); if (!pte_same(pte, pte_move_swp_offset(vmf->orig_pte, -idx))) return false; entry = pte_to_swp_entry(pte); if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages) return false; /* * swap_read_folio() can't handle the case a large folio is hybridly * from different backends. And they are likely corner cases. Similar * things might be added once zswap support large folios. */ if (unlikely(swap_zeromap_batch(entry, nr_pages, NULL) != nr_pages)) return false; if (unlikely(non_swapcache_batch(entry, nr_pages) != nr_pages)) return false; return true; } static inline unsigned long thp_swap_suitable_orders(pgoff_t swp_offset, unsigned long addr, unsigned long orders) { int order, nr; order = highest_order(orders); /* * To swap in a THP with nr pages, we require that its first swap_offset * is aligned with that number, as it was when the THP was swapped out. * This helps filter out most invalid entries. */ while (orders) { nr = 1 << order; if ((addr >> PAGE_SHIFT) % nr == swp_offset % nr) break; order = next_order(&orders, order); } return orders; } static struct folio *alloc_swap_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long orders; struct folio *folio; unsigned long addr; swp_entry_t entry; spinlock_t *ptl; pte_t *pte; gfp_t gfp; int order; /* * If uffd is active for the vma we need per-page fault fidelity to * maintain the uffd semantics. */ if (unlikely(userfaultfd_armed(vma))) goto fallback; /* * A large swapped out folio could be partially or fully in zswap. We * lack handling for such cases, so fallback to swapping in order-0 * folio. */ if (!zswap_never_enabled()) goto fallback; entry = pte_to_swp_entry(vmf->orig_pte); /* * Get a list of all the (large) orders below PMD_ORDER that are enabled * and suitable for swapping THP. */ orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); orders = thp_swap_suitable_orders(swp_offset(entry), vmf->address, orders); if (!orders) goto fallback; pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address & PMD_MASK, &ptl); if (unlikely(!pte)) goto fallback; /* * For do_swap_page, find the highest order where the aligned range is * completely swap entries with contiguous swap offsets. */ order = highest_order(orders); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); if (can_swapin_thp(vmf, pte + pte_index(addr), 1 << order)) break; order = next_order(&orders, order); } pte_unmap_unlock(pte, ptl); /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr); if (folio) { if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, gfp, entry)) return folio; folio_put(folio); } order = next_order(&orders, order); } fallback: return __alloc_swap_folio(vmf); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static struct folio *alloc_swap_folio(struct vm_fault *vmf) { return __alloc_swap_folio(vmf); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq); /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *swapcache, *folio = NULL; DECLARE_WAITQUEUE(wait, current); struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; bool need_clear_cache = false; bool exclusive = false; swp_entry_t entry; pte_t pte; vm_fault_t ret = 0; void *shadow = NULL; int nr_pages; unsigned long page_idx; unsigned long address; pte_t *ptep; if (!pte_unmap_same(vmf)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_exclusive_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) { /* * migrate_to_ram is not yet ready to operate * under VMA lock. */ vma_end_read(vma); ret = VM_FAULT_RETRY; goto out; } vmf->page = pfn_swap_entry_to_page(entry); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) goto unlock; /* * Get a page reference while we know the page can't be * freed. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else if (is_pte_marker_entry(entry)) { ret = handle_pte_marker(vmf); } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } /* Prevent swapoff from happening to us. */ si = get_swap_device(entry); if (unlikely(!si)) goto out; folio = swap_cache_get_folio(entry, vma, vmf->address); if (folio) page = folio_file_page(folio, swp_offset(entry)); swapcache = folio; if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ folio = alloc_swap_folio(vmf); if (folio) { __folio_set_locked(folio); __folio_set_swapbacked(folio); nr_pages = folio_nr_pages(folio); if (folio_test_large(folio)) entry.val = ALIGN_DOWN(entry.val, nr_pages); /* * Prevent parallel swapin from proceeding with * the cache flag. Otherwise, another thread * may finish swapin first, free the entry, and * swapout reusing the same entry. It's * undetectable as pte_same() returns true due * to entry reuse. */ if (swapcache_prepare(entry, nr_pages)) { /* * Relax a bit to prevent rapid * repeated page faults. */ add_wait_queue(&swapcache_wq, &wait); schedule_timeout_uninterruptible(1); remove_wait_queue(&swapcache_wq, &wait); goto out_page; } need_clear_cache = true; mem_cgroup_swapin_uncharge_swap(entry, nr_pages); shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(folio, shadow); folio_add_lru(folio); /* To provide entry to swap_read_folio() */ folio->swap = entry; swap_read_folio(folio, NULL); folio->private = NULL; } } else { folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = folio; } if (!folio) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) ret = VM_FAULT_OOM; goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); page = folio_file_page(folio, swp_offset(entry)); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; goto out_release; } ret |= folio_lock_or_retry(folio, vmf); if (ret & VM_FAULT_RETRY) goto out_release; if (swapcache) { /* * Make sure folio_free_swap() or swapoff did not release the * swapcache from under us. The page pin, and pte_same test * below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not * changed. */ if (unlikely(!folio_test_swapcache(folio) || page_swap_entry(page).val != entry.val)) goto out_page; /* * KSM sometimes has to copy on read faults, for example, if * page->index of !PageKSM() pages would be nonlinear inside the * anon VMA -- PageKSM() is lost on actual swapout. */ folio = ksm_might_need_to_copy(folio, vma, vmf->address); if (unlikely(!folio)) { ret = VM_FAULT_OOM; folio = swapcache; goto out_page; } else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { ret = VM_FAULT_HWPOISON; folio = swapcache; goto out_page; } if (folio != swapcache) page = folio_page(folio, 0); /* * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * owner. Try removing the extra reference from the local LRU * caches if required. */ if ((vmf->flags & FAULT_FLAG_WRITE) && folio == swapcache && !folio_test_ksm(folio) && !folio_test_lru(folio)) lru_add_drain(); } folio_throttle_swaprate(folio, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) goto out_nomap; if (unlikely(!folio_test_uptodate(folio))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* allocated large folios for SWP_SYNCHRONOUS_IO */ if (folio_test_large(folio) && !folio_test_swapcache(folio)) { unsigned long nr = folio_nr_pages(folio); unsigned long folio_start = ALIGN_DOWN(vmf->address, nr * PAGE_SIZE); unsigned long idx = (vmf->address - folio_start) / PAGE_SIZE; pte_t *folio_ptep = vmf->pte - idx; pte_t folio_pte = ptep_get(folio_ptep); if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || swap_pte_batch(folio_ptep, nr, folio_pte) != nr) goto out_nomap; page_idx = idx; address = folio_start; ptep = folio_ptep; goto check_folio; } nr_pages = 1; page_idx = 0; address = vmf->address; ptep = vmf->pte; if (folio_test_large(folio) && folio_test_swapcache(folio)) { int nr = folio_nr_pages(folio); unsigned long idx = folio_page_idx(folio, page); unsigned long folio_start = address - idx * PAGE_SIZE; unsigned long folio_end = folio_start + nr * PAGE_SIZE; pte_t *folio_ptep; pte_t folio_pte; if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start))) goto check_folio; if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end))) goto check_folio; folio_ptep = vmf->pte - idx; folio_pte = ptep_get(folio_ptep); if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || swap_pte_batch(folio_ptep, nr, folio_pte) != nr) goto check_folio; page_idx = idx; address = folio_start; ptep = folio_ptep; nr_pages = nr; entry = folio->swap; page = &folio->page; } check_folio: /* * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte * must never point at an anonymous page in the swapcache that is * PG_anon_exclusive. Sanity check that this holds and especially, that * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity * check after taking the PT lock and making sure that nobody * concurrently faulted in this page and set PG_anon_exclusive. */ BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio)); BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page)); /* * Check under PT lock (to protect against concurrent fork() sharing * the swap entry concurrently) for certainly exclusive pages. */ if (!folio_test_ksm(folio)) { exclusive = pte_swp_exclusive(vmf->orig_pte); if (folio != swapcache) { /* * We have a fresh page that is not exposed to the * swapcache -> certainly exclusive. */ exclusive = true; } else if (exclusive && folio_test_writeback(folio) && data_race(si->flags & SWP_STABLE_WRITES)) { /* * This is tricky: not all swap backends support * concurrent page modifications while under writeback. * * So if we stumble over such a page in the swapcache * we must not set the page exclusive, otherwise we can * map it writable without further checks and modify it * while still under writeback. * * For these problematic swap backends, simply drop the * exclusive marker: this is perfectly fine as we start * writeback only if we fully unmapped the page and * there are no unexpected references on the page after * unmapping succeeded. After fully unmapped, no * further GUP references (FOLL_GET and FOLL_PIN) can * appear, so dropping the exclusive marker and mapping * it only R/O is fine. */ exclusive = false; } } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); /* * Remove the swap entry and conditionally try to free up the swapcache. * We're already holding a reference on the page but haven't mapped it * yet. */ swap_free_nr(entry, nr_pages); if (should_try_to_free_swap(folio, vma, vmf->flags)) folio_free_swap(folio); add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages); pte = mk_pte(page, vma->vm_page_prot); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) pte = pte_mkuffd_wp(pte); /* * Same logic as in do_wp_page(); however, optimize for pages that are * certainly not shared either because we just allocated them without * exposing them to the swapcache or because the swap entry indicates * exclusivity. */ if (!folio_test_ksm(folio) && (exclusive || folio_ref_count(folio) == 1)) { if ((vma->vm_flags & VM_WRITE) && !userfaultfd_pte_wp(vma, pte) && !pte_needs_soft_dirty_wp(vma, pte)) { pte = pte_mkwrite(pte, vma); if (vmf->flags & FAULT_FLAG_WRITE) { pte = pte_mkdirty(pte); vmf->flags &= ~FAULT_FLAG_WRITE; } } rmap_flags |= RMAP_EXCLUSIVE; } folio_ref_add(folio, nr_pages - 1); flush_icache_pages(vma, page, nr_pages); vmf->orig_pte = pte_advance_pfn(pte, page_idx); /* ksm created a completely new copy */ if (unlikely(folio != swapcache && swapcache)) { folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } else if (!folio_test_anon(folio)) { /* * We currently only expect small !anon folios which are either * fully exclusive or fully shared, or new allocated large * folios which are fully exclusive. If we ever get large * folios within swapcache here, we have to be careful. */ VM_WARN_ON_ONCE(folio_test_large(folio) && folio_test_swapcache(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, address, rmap_flags); } else { folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, address, rmap_flags); } VM_BUG_ON(!folio_test_anon(folio) || (pte_write(pte) && !PageAnonExclusive(page))); set_ptes(vma->vm_mm, address, ptep, pte, nr_pages); arch_do_swap_page_nr(vma->vm_mm, vma, address, pte, pte, nr_pages); folio_unlock(folio); if (folio != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ folio_unlock(swapcache); folio_put(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache_range(vmf, vma, address, ptep, nr_pages); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: /* Clear the swap cache pin for direct swapin after PTL unlock */ if (need_clear_cache) { swapcache_clear(si, entry, nr_pages); if (waitqueue_active(&swapcache_wq)) wake_up(&swapcache_wq); } if (si) put_swap_device(si); return ret; out_nomap: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: folio_unlock(folio); out_release: folio_put(folio); if (folio != swapcache && swapcache) { folio_unlock(swapcache); folio_put(swapcache); } if (need_clear_cache) { swapcache_clear(si, entry, nr_pages); if (waitqueue_active(&swapcache_wq)) wake_up(&swapcache_wq); } if (si) put_swap_device(si); return ret; } static bool pte_range_none(pte_t *pte, int nr_pages) { int i; for (i = 0; i < nr_pages; i++) { if (!pte_none(ptep_get_lockless(pte + i))) return false; } return true; } static struct folio *alloc_anon_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long orders; struct folio *folio; unsigned long addr; pte_t *pte; gfp_t gfp; int order; /* * If uffd is active for the vma we need per-page fault fidelity to * maintain the uffd semantics. */ if (unlikely(userfaultfd_armed(vma))) goto fallback; /* * Get a list of all the (large) orders below PMD_ORDER that are enabled * for this vma. Then filter out the orders that can't be allocated over * the faulting address and still be fully contained in the vma. */ orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); if (!orders) goto fallback; pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK); if (!pte) return ERR_PTR(-EAGAIN); /* * Find the highest order where the aligned range is completely * pte_none(). Note that all remaining orders will be completely * pte_none(). */ order = highest_order(orders); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); if (pte_range_none(pte + pte_index(addr), 1 << order)) break; order = next_order(&orders, order); } pte_unmap(pte); if (!orders) goto fallback; /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr); if (folio) { if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); folio_put(folio); goto next; } folio_throttle_swaprate(folio, gfp); /* * When a folio is not zeroed during allocation * (__GFP_ZERO not used), folio_zero_user() is used * to make sure that the page corresponding to the * faulting address will be hot in the cache after * zeroing. */ if (!alloc_zeroed()) folio_zero_user(folio, vmf->address); return folio; } next: count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); order = next_order(&orders, order); } fallback: #endif return folio_prealloc(vma->vm_mm, vma, vmf->address, true); } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; struct folio *folio; vm_fault_t ret = 0; int nr_pages = 1; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(), so that OOM can * be distinguished from a transient failure of pte_offset_map(). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) goto unlock; if (vmf_pte_changed(vmf)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ ret = vmf_anon_prepare(vmf); if (ret) return ret; /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */ folio = alloc_anon_folio(vmf); if (IS_ERR(folio)) return 0; if (!folio) goto oom; nr_pages = folio_nr_pages(folio); addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); /* * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __folio_mark_uptodate(folio); entry = mk_pte(&folio->page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry), vma); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) goto release; if (nr_pages == 1 && vmf_pte_changed(vmf)) { update_mmu_tlb(vma, addr, vmf->pte); goto release; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); folio_put(folio); return handle_userfault(vmf, VM_UFFD_MISSING); } folio_ref_add(folio, nr_pages - 1); add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); setpte: if (vmf_orig_pte_uffd_wp(vmf)) entry = pte_mkuffd_wp(entry); set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages); /* No need to invalidate - it was non-present before */ update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: folio_put(folio); goto unlock; oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_folio_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; folio = page_folio(vmf->page); if (unlikely(PageHWPoison(vmf->page))) { vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(vmf->page)) unmap_mapping_folio(folio); /* Retry if a clean folio was removed from the cache. */ if (mapping_evict_folio(folio->mapping, folio)) poisonret = VM_FAULT_NOPAGE; folio_unlock(folio); } folio_put(folio); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) folio_lock(folio); else VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page); return ret; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct folio *folio = page_folio(page); struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK; /* * It is too late to allocate a small folio, we already have a large * folio in the pagecache: especially s390 KVM cannot tolerate any * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any * PMD mappings if THPs are disabled. */ if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags)) return ret; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; if (folio_order(folio) != HPAGE_PMD_ORDER) return ret; page = &folio->page; /* * Just backoff if any subpage of a THP is corrupted otherwise * the corrupted page may mapped by PMD silently to escape the * check. This kind of THP just can be PTE mapped. Access to * the corrupted subpage should trigger SIGBUS as expected. */ if (unlikely(folio_test_has_hwpoisoned(folio))) return ret; /* * Archs like ppc64 need additional space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; flush_icache_pages(vma, page, HPAGE_PMD_NR); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR); folio_add_file_rmap_pmd(folio, page, vma); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { return VM_FAULT_FALLBACK; } #endif /** * set_pte_range - Set a range of PTEs to point to pages in a folio. * @vmf: Fault decription. * @folio: The folio that contains @page. * @page: The first page to create a PTE for. * @nr: The number of PTEs to create. * @addr: The first address to create a PTE for. */ void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; flush_icache_pages(vma, page, nr); entry = mk_pte(page, vma->vm_page_prot); if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); else entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (unlikely(vmf_orig_pte_uffd_wp(vmf))) entry = pte_mkuffd_wp(entry); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { VM_BUG_ON_FOLIO(nr != 1, folio); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } else { folio_add_file_rmap_ptes(folio, page, nr, vma); } set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr); } static bool vmf_pte_changed(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) return !pte_same(ptep_get(vmf->pte), vmf->orig_pte); return !pte_none(ptep_get(vmf->pte)); } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; struct folio *folio; vm_fault_t ret; bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); int type, nr_pages; unsigned long addr = vmf->address; /* Did we COW the page? */ if (is_cow) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vma->vm_flags & VM_SHARED)) { ret = check_stable_address_space(vma->vm_mm); if (ret) return ret; } if (pmd_none(*vmf->pmd)) { if (PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (vmf->prealloc_pte) pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) return VM_FAULT_OOM; } folio = page_folio(page); nr_pages = folio_nr_pages(folio); /* * Using per-page fault to maintain the uffd semantics, and same * approach also applies to non-anonymous-shmem faults to avoid * inflating the RSS of the process. */ if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) { nr_pages = 1; } else if (nr_pages > 1) { pgoff_t idx = folio_page_idx(folio, page); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; /* The index of the entry in the pagetable for fault page. */ pgoff_t pte_off = pte_index(vmf->address); /* * Fallback to per-page fault in case the folio size in page * cache beyond the VMA limits and PMD pagetable limits. */ if (unlikely(vma_off < idx || vma_off + (nr_pages - idx) > vma_pages(vma) || pte_off < idx || pte_off + (nr_pages - idx) > PTRS_PER_PTE)) { nr_pages = 1; } else { /* Now we can set mappings for the whole large folio. */ addr = vmf->address - idx * PAGE_SIZE; page = &folio->page; } } vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* Re-check under ptl */ if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) { update_mmu_tlb(vma, addr, vmf->pte); ret = VM_FAULT_NOPAGE; goto unlock; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); ret = VM_FAULT_NOPAGE; goto unlock; } folio_ref_add(folio, nr_pages - 1); set_pte_range(vmf, folio, page, nr_pages, addr); type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); add_mm_counter(vma->vm_mm, type, nr_pages); ret = 0; unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_pages __read_mostly = 65536 >> PAGE_SHIFT; #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_pages << PAGE_SHIFT; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; /* * The minimum value is 1 page, however this results in no fault-around * at all. See should_fault_around(). */ val = max(val, PAGE_SIZE); fault_around_pages = rounddown_pow_of_two(val) >> PAGE_SHIFT; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function doesn't cross VMA or page table boundaries, in order to call * map_pages() and acquire a PTE lock only once. * * fault_around_pages defines how many pages we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_pages * PAGE_SIZE rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { pgoff_t nr_pages = READ_ONCE(fault_around_pages); pgoff_t pte_off = pte_index(vmf->address); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; pgoff_t from_pte, to_pte; vm_fault_t ret; /* The PTE offset of the start address, clamped to the VMA. */ from_pte = max(ALIGN_DOWN(pte_off, nr_pages), pte_off - min(pte_off, vma_off)); /* The PTE offset of the end address, clamped to the VMA and PTE. */ to_pte = min3(from_pte + nr_pages, (pgoff_t)PTRS_PER_PTE, pte_off + vma_pages(vmf->vma) - vma_off) - 1; if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } rcu_read_lock(); ret = vmf->vma->vm_ops->map_pages(vmf, vmf->pgoff + from_pte - pte_off, vmf->pgoff + to_pte - pte_off); rcu_read_unlock(); return ret; } /* Return true if we should do read fault-around, false otherwise */ static inline bool should_fault_around(struct vm_fault *vmf) { /* No ->map_pages? No way to fault around... */ if (!vmf->vma->vm_ops->map_pages) return false; if (uffd_disable_fault_around(vmf->vma)) return false; /* A single page implies no faulting 'around' at all. */ return fault_around_pages > 1; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { vm_fault_t ret = 0; struct folio *folio; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (should_fault_around(vmf)) { ret = do_fault_around(vmf); if (ret) return ret; } ret = vmf_can_call_fault(vmf); if (ret) return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); folio = page_folio(vmf->page); folio_unlock(folio); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) folio_put(folio); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret; ret = vmf_can_call_fault(vmf); if (!ret) ret = vmf_anon_prepare(vmf); if (ret) return ret; folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false); if (!folio) return VM_FAULT_OOM; vmf->cow_page = &folio->page; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; if (copy_mc_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma)) { ret = VM_FAULT_HWPOISON; goto unlock; } __folio_mark_uptodate(folio); ret |= finish_fault(vmf); unlock: unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: folio_put(folio); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; struct folio *folio; ret = vmf_can_call_fault(vmf); if (ret) return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; folio = page_folio(vmf->page); /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { folio_unlock(folio); tmp = do_page_mkwrite(vmf, folio); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { folio_put(folio); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { folio_unlock(folio); folio_put(folio); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) ret = VM_FAULT_SIGBUS; else { /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(ptep_get(vmf->pte)))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid) { struct vm_area_struct *vma = vmf->vma; /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!writable) *flags |= TNF_NO_GROUP; /* * Flag if the folio is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (folio_likely_mapped_shared(folio) && (vma->vm_flags & VM_SHARED)) *flags |= TNF_SHARED; /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ if (folio_use_access_time(folio)) *last_cpupid = (-1 & LAST_CPUPID_MASK); else *last_cpupid = folio_last_cpupid(folio); /* Record the current PID acceesing VMA */ vma_set_access_pid_bit(vma); count_vm_numa_event(NUMA_HINT_FAULTS); #ifdef CONFIG_NUMA_BALANCING count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1); #endif if (folio_nid(folio) == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(folio, vmf, addr); } static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long fault_addr, pte_t *fault_pte, bool writable) { pte_t pte, old_pte; old_pte = ptep_modify_prot_start(vma, fault_addr, fault_pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (writable) pte = pte_mkwrite(pte, vma); ptep_modify_prot_commit(vma, fault_addr, fault_pte, old_pte, pte); update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1); } static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, struct folio *folio, pte_t fault_pte, bool ignore_writable, bool pte_write_upgrade) { int nr = pte_pfn(fault_pte) - folio_pfn(folio); unsigned long start, end, addr = vmf->address; unsigned long addr_start = addr - (nr << PAGE_SHIFT); unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); pte_t *start_ptep; /* Stay within the VMA and within the page table. */ start = max3(addr_start, pt_start, vma->vm_start); end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, vma->vm_end); start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); /* Restore all PTEs' mapping of the large folio */ for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { pte_t ptent = ptep_get(start_ptep); bool writable = false; if (!pte_present(ptent) || !pte_protnone(ptent)) continue; if (pfn_folio(pte_pfn(ptent)) != folio) continue; if (!ignore_writable) { ptent = pte_modify(ptent, vma->vm_page_prot); writable = pte_write(ptent); if (!writable && pte_write_upgrade && can_change_pte_writable(vma, addr, ptent)) writable = true; } numa_rebuild_single_mapping(vmf, vma, addr, start_ptep, writable); } } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; int nid = NUMA_NO_NODE; bool writable = false, ignore_writable = false; bool pte_write_upgrade = vma_wants_manual_pte_write_upgrade(vma); int last_cpupid; int target_nid; pte_t pte, old_pte; int flags = 0, nr_pages; /* * The pte cannot be used safely until we verify, while holding the page * table lock, that its contents have not changed during fault handling. */ spin_lock(vmf->ptl); /* Read the live PTE from the page tables: */ old_pte = ptep_get(vmf->pte); if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); /* * Detect now whether the PTE could be writable; this information * is only valid while holding the PT lock. */ writable = pte_write(pte); if (!writable && pte_write_upgrade && can_change_pte_writable(vma, vmf->address, pte)) writable = true; folio = vm_normal_folio(vma, vmf->address, pte); if (!folio || folio_is_zone_device(folio)) goto out_map; nid = folio_nid(folio); nr_pages = folio_nr_pages(folio); target_nid = numa_migrate_check(folio, vmf, vmf->address, &flags, writable, &last_cpupid); if (target_nid == NUMA_NO_NODE) goto out_map; if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { flags |= TNF_MIGRATE_FAIL; goto out_map; } /* The folio is isolated and isolation code holds a folio reference. */ pte_unmap_unlock(vmf->pte, vmf->ptl); writable = false; ignore_writable = true; /* Migrate to the requested node */ if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } flags |= TNF_MIGRATE_FAIL; vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) return 0; if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } out_map: /* * Make it present again, depending on how arch implements * non-accessible ptes, some can allow access by kernel mode. */ if (folio && folio_test_large(folio)) numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable, pte_write_upgrade); else numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma_is_anonymous(vma)) return do_huge_pmd_anonymous_page(vmf); if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; vm_fault_t ret; if (vma_is_anonymous(vma)) { if (likely(!unshare) && userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) { if (userfaultfd_wp_async(vmf->vma)) goto split; return handle_userfault(vmf, VM_UFFD_WP); } return do_huge_pmd_wp_page(vmf); } if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) return ret; } } split: /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) struct vm_area_struct *vma = vmf->vma; /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PUD_ORDER); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) goto split; if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) return ret; } } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { pmd_t dummy_pmdval; /* * A regular pmd is established and it can't morph into a huge * pmd by anon khugepaged, since that takes mmap_lock in write * mode; but shmem or file collapse to THP could still morph * it into a huge pmd: just retry later if so. * * Use the maywrite version to indicate that vmf->pte may be * modified, but since we will use pte_same() to detect the * change of the !pte_none() entry, there is no need to recheck * the pmdval. Here we chooes to pass a dummy variable instead * of NULL, which helps new user think about why this place is * special. */ vmf->pte = pte_offset_map_rw_nolock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &dummy_pmdval, &vmf->ptl); if (unlikely(!vmf->pte)) return 0; vmf->orig_pte = ptep_get_lockless(vmf->pte); vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) return do_pte_missing(vmf); if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(ptep_get(vmf->pte), entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) return do_wp_page(vmf); else if (likely(vmf->flags & FAULT_FLAG_WRITE)) entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache_range(vmf, vmf->vma, vmf->address, vmf->pte, 1); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address, vmf->pte); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * On entry, we hold either the VMA lock or the mmap_lock * (FAULT_FLAG_VMA_LOCK tells you which). If VM_FAULT_RETRY is set in * the result, the mmap_lock is not held on exit. See filemap_fault() * and __folio_lock_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .real_address = address, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; struct mm_struct *mm = vma->vm_mm; unsigned long vm_flags = vma->vm_flags; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && thp_vma_allowable_order(vma, vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, PUD_ORDER)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* * TODO once we support anonymous PUDs: NUMA case and * FAULT_FLAG_UNSHARE handling. */ if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && thp_vma_allowable_order(vma, vm_flags, TVA_IN_PF | TVA_ENFORCE_SYSFS, PMD_ORDER)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); if (unlikely(is_swap_pmd(vmf.orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(vmf.orig_pmd)); if (is_pmd_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf); if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !pmd_write(vmf.orig_pmd)) { ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accounting * @mm: mm from which memcg should be extracted. It can be NULL. * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accounting. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct mm_struct *mm, struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* Incomplete faults will be accounted upon completion. */ if (ret & VM_FAULT_RETRY) return; /* * To preserve the behavior of older kernels, PGFAULT counters record * both successful and failed faults, as opposed to perf counters, * which ignore failed cases. */ count_vm_event(PGFAULT); count_memcg_event_mm(mm, PGFAULT); /* * Do not account for unsuccessful faults (e.g. when the address wasn't * valid). That includes arch_vma_access_permitted() failing before * reaching here. So this is not a "this many hardware page faults" * counter. We should use the hw profiling for that. */ if (ret & VM_FAULT_ERROR) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } #ifdef CONFIG_LRU_GEN static void lru_gen_enter_fault(struct vm_area_struct *vma) { /* the LRU algorithm only applies to accesses with recency */ current->in_lru_fault = vma_has_recency(vma); } static void lru_gen_exit_fault(void) { current->in_lru_fault = false; } #else static void lru_gen_enter_fault(struct vm_area_struct *vma) { } static void lru_gen_exit_fault(void) { } #endif /* CONFIG_LRU_GEN */ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, unsigned int *flags) { if (unlikely(*flags & FAULT_FLAG_UNSHARE)) { if (WARN_ON_ONCE(*flags & FAULT_FLAG_WRITE)) return VM_FAULT_SIGSEGV; /* * FAULT_FLAG_UNSHARE only applies to COW mappings. Let's * just treat it like an ordinary read-fault otherwise. */ if (!is_cow_mapping(vma->vm_flags)) *flags &= ~FAULT_FLAG_UNSHARE; } else if (*flags & FAULT_FLAG_WRITE) { /* Write faults on read-only mappings are impossible ... */ if (WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE))) return VM_FAULT_SIGSEGV; /* ... and FOLL_FORCE only applies to COW mappings. */ if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE) && !is_cow_mapping(vma->vm_flags))) return VM_FAULT_SIGSEGV; } #ifdef CONFIG_PER_VMA_LOCK /* * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of * the assumption that lock is dropped on VM_FAULT_RETRY. */ if (WARN_ON_ONCE((*flags & (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) == (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT))) return VM_FAULT_SIGSEGV; #endif return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* If the fault handler drops the mmap_lock, vma may be freed */ struct mm_struct *mm = vma->vm_mm; vm_fault_t ret; bool is_droppable; __set_current_state(TASK_RUNNING); ret = sanitize_fault_flags(vma, &flags); if (ret) goto out; if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) { ret = VM_FAULT_SIGSEGV; goto out; } is_droppable = !!(vma->vm_flags & VM_DROPPABLE); /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); lru_gen_enter_fault(vma); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); /* * Warning: It is no longer safe to dereference vma-> after this point, * because mmap_lock might have been dropped by __handle_mm_fault(), so * vma might be destroyed from underneath us. */ lru_gen_exit_fault(); /* If the mapping is droppable, then errors due to OOM aren't fatal. */ if (is_droppable) ret &= ~VM_FAULT_OOM; if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } out: mm_account_fault(mm, regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifdef CONFIG_LOCK_MM_AND_FIND_VMA #include <linux/extable.h> static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs) { if (likely(mmap_read_trylock(mm))) return true; if (regs && !user_mode(regs)) { unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } return !mmap_read_lock_killable(mm); } static inline bool mmap_upgrade_trylock(struct mm_struct *mm) { /* * We don't have this operation yet. * * It should be easy enough to do: it's basically a * atomic_long_try_cmpxchg_acquire() * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but * it also needs the proper lockdep magic etc. */ return false; } static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs) { mmap_read_unlock(mm); if (regs && !user_mode(regs)) { unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } return !mmap_write_lock_killable(mm); } /* * Helper for page fault handling. * * This is kind of equivalend to "mmap_read_lock()" followed * by "find_extend_vma()", except it's a lot more careful about * the locking (and will drop the lock on failure). * * For example, if we have a kernel bug that causes a page * fault, we don't want to just use mmap_read_lock() to get * the mm lock, because that would deadlock if the bug were * to happen while we're holding the mm lock for writing. * * So this checks the exception tables on kernel faults in * order to only do this all for instructions that are actually * expected to fault. * * We can also actually take the mm lock for writing if we * need to extend the vma, which helps the VM layer a lot. */ struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long addr, struct pt_regs *regs) { struct vm_area_struct *vma; if (!get_mmap_lock_carefully(mm, regs)) return NULL; vma = find_vma(mm, addr); if (likely(vma && (vma->vm_start <= addr))) return vma; /* * Well, dang. We might still be successful, but only * if we can extend a vma to do so. */ if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) { mmap_read_unlock(mm); return NULL; } /* * We can try to upgrade the mmap lock atomically, * in which case we can continue to use the vma * we already looked up. * * Otherwise we'll have to drop the mmap lock and * re-take it, and also look up the vma again, * re-checking it. */ if (!mmap_upgrade_trylock(mm)) { if (!upgrade_mmap_lock_carefully(mm, regs)) return NULL; vma = find_vma(mm, addr); if (!vma) goto fail; if (vma->vm_start <= addr) goto success; if (!(vma->vm_flags & VM_GROWSDOWN)) goto fail; } if (expand_stack_locked(vma, addr)) goto fail; success: mmap_write_downgrade(mm); return vma; fail: mmap_write_unlock(mm); return NULL; } #endif #ifdef CONFIG_PER_VMA_LOCK /* * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be * stable and not isolated. If the VMA is not found or is being modified the * function returns NULL. */ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { MA_STATE(mas, &mm->mm_mt, address, address); struct vm_area_struct *vma; rcu_read_lock(); retry: vma = mas_walk(&mas); if (!vma) goto inval; if (!vma_start_read(vma)) goto inval; /* Check if the VMA got isolated after we found it */ if (vma->detached) { vma_end_read(vma); count_vm_vma_lock_event(VMA_LOCK_MISS); /* The area was replaced with another one */ goto retry; } /* * At this point, we have a stable reference to a VMA: The VMA is * locked and we know it hasn't already been isolated. * From here on, we can access the VMA without worrying about which * fields are accessible for RCU readers. */ /* Check since vm_start/vm_end might change before we lock the VMA */ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; rcu_read_unlock(); return vma; inval_end_read: vma_end_read(vma); inval: rcu_read_unlock(); count_vm_vma_lock_event(VMA_LOCK_ABORT); return NULL; } #endif /* CONFIG_PER_VMA_LOCK */ #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) { /* Another has populated it */ p4d_free(mm, new); } else { smp_wmb(); /* See comment in pmd_install() */ pgd_populate(mm, pgd, new); } spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); smp_wmb(); /* See comment in pmd_install() */ p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); smp_wmb(); /* See comment in pmd_install() */ pud_populate(mm, pud, new); } else { /* Another has populated it */ pmd_free(mm, new); } spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ static inline void pfnmap_args_setup(struct follow_pfnmap_args *args, spinlock_t *lock, pte_t *ptep, pgprot_t pgprot, unsigned long pfn_base, unsigned long addr_mask, bool writable, bool special) { args->lock = lock; args->ptep = ptep; args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT); args->pgprot = pgprot; args->writable = writable; args->special = special; } static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma) { #ifdef CONFIG_LOCKDEP struct file *file = vma->vm_file; struct address_space *mapping = file ? file->f_mapping : NULL; if (mapping) lockdep_assert(lockdep_is_held(&mapping->i_mmap_rwsem) || lockdep_is_held(&vma->vm_mm->mmap_lock)); else lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock)); #endif } /** * follow_pfnmap_start() - Look up a pfn mapping at a user virtual address * @args: Pointer to struct @follow_pfnmap_args * * The caller needs to setup args->vma and args->address to point to the * virtual address as the target of such lookup. On a successful return, * the results will be put into other output fields. * * After the caller finished using the fields, the caller must invoke * another follow_pfnmap_end() to proper releases the locks and resources * of such look up request. * * During the start() and end() calls, the results in @args will be valid * as proper locks will be held. After the end() is called, all the fields * in @follow_pfnmap_args will be invalid to be further accessed. Further * use of such information after end() may require proper synchronizations * by the caller with page table updates, otherwise it can create a * security bug. * * If the PTE maps a refcounted page, callers are responsible to protect * against invalidation with MMU notifiers; otherwise access to the PFN at * a later point in time can trigger use-after-free. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read, and the mmap semaphore cannot be released * before the end() is invoked. * * This function must not be used to modify PTE content. * * Return: zero on success, negative otherwise. */ int follow_pfnmap_start(struct follow_pfnmap_args *args) { struct vm_area_struct *vma = args->vma; unsigned long address = args->address; struct mm_struct *mm = vma->vm_mm; spinlock_t *lock; pgd_t *pgdp; p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; pfnmap_lockdep_assert(vma); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto out; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; retry: pgdp = pgd_offset(mm, address); if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) goto out; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); if (p4d_none(p4d) || unlikely(p4d_bad(p4d))) goto out; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (pud_none(pud)) goto out; if (pud_leaf(pud)) { lock = pud_lock(mm, pudp); if (!unlikely(pud_leaf(pud))) { spin_unlock(lock); goto retry; } pfnmap_args_setup(args, lock, NULL, pud_pgprot(pud), pud_pfn(pud), PUD_MASK, pud_write(pud), pud_special(pud)); return 0; } pmdp = pmd_offset(pudp, address); pmd = pmdp_get_lockless(pmdp); if (pmd_leaf(pmd)) { lock = pmd_lock(mm, pmdp); if (!unlikely(pmd_leaf(pmd))) { spin_unlock(lock); goto retry; } pfnmap_args_setup(args, lock, NULL, pmd_pgprot(pmd), pmd_pfn(pmd), PMD_MASK, pmd_write(pmd), pmd_special(pmd)); return 0; } ptep = pte_offset_map_lock(mm, pmdp, address, &lock); if (!ptep) goto out; pte = ptep_get(ptep); if (!pte_present(pte)) goto unlock; pfnmap_args_setup(args, lock, ptep, pte_pgprot(pte), pte_pfn(pte), PAGE_MASK, pte_write(pte), pte_special(pte)); return 0; unlock: pte_unmap_unlock(ptep, lock); out: return -EINVAL; } EXPORT_SYMBOL_GPL(follow_pfnmap_start); /** * follow_pfnmap_end(): End a follow_pfnmap_start() process * @args: Pointer to struct @follow_pfnmap_args * * Must be used in pair of follow_pfnmap_start(). See the start() function * above for more information. */ void follow_pfnmap_end(struct follow_pfnmap_args *args) { if (args->lock) spin_unlock(args->lock); if (args->ptep) pte_unmap(args->ptep); } EXPORT_SYMBOL_GPL(follow_pfnmap_end); #ifdef CONFIG_HAVE_IOREMAP_PROT /** * generic_access_phys - generic implementation for iomem mmap access * @vma: the vma to access * @addr: userspace address, not relative offset within @vma * @buf: buffer to read/write * @len: length of transfer * @write: set to FOLL_WRITE when writing, otherwise reading * * This is a generic implementation for &vm_operations_struct.access for an * iomem mapping. This callback is used by access_process_vm() when the @vma is * not page based. */ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; int offset = offset_in_page(addr); int ret = -EINVAL; bool writable; struct follow_pfnmap_args args = { .vma = vma, .address = addr }; retry: if (follow_pfnmap_start(&args)) return -EINVAL; prot = pgprot_val(args.pgprot); phys_addr = (resource_size_t)args.pfn << PAGE_SHIFT; writable = args.writable; follow_pfnmap_end(&args); if ((write & FOLL_WRITE) && !writable) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (follow_pfnmap_start(&args)) goto out_unmap; if ((prot != pgprot_val(args.pgprot)) || (phys_addr != (args.pfn << PAGE_SHIFT)) || (writable != args.writable)) { follow_pfnmap_end(&args); iounmap(maddr); goto retry; } if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); ret = len; follow_pfnmap_end(&args); out_unmap: iounmap(maddr); return ret; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. */ static int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* Untag the address before looking up the VMA */ addr = untagged_addr_remote(mm, addr); /* Avoid triggering the temporary warning in __get_user_pages */ if (!vma_lookup(mm, addr) && !expand_stack(mm, addr)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, offset; void *maddr; struct vm_area_struct *vma = NULL; struct page *page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); if (IS_ERR(page)) { /* We might need to expand the stack to access it */ vma = vma_lookup(mm, addr); if (!vma) { vma = expand_stack(mm, addr); /* mmap_lock was dropped on failure */ if (!vma) return buf - old_buf; /* Try again if stack expansion worked */ continue; } /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ bytes = 0; #ifdef CONFIG_HAVE_IOREMAP_PROT if (vma->vm_ops && vma->vm_ops->access) bytes = vma->vm_ops->access(vma, addr, buf, len, write); #endif if (bytes <= 0) break; } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap_local_page(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } unmap_and_put_page(page, maddr); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = vma_lookup(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; ip -= vma->vm_start; ip += vma->vm_pgoff << PAGE_SHIFT; printk("%s%pD[%lx,%lx+%lx]", prefix, f, ip, vma->vm_start, vma->vm_end - vma->vm_start); } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { if (pagefault_disabled()) return; __might_sleep(file, line); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline int process_huge_page( unsigned long addr_hint, unsigned int nr_pages, int (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l, ret; unsigned long addr = addr_hint & ~(((unsigned long)nr_pages << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= nr_pages) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = nr_pages - 1; i >= 2 * n; i--) { cond_resched(); ret = process_subpage(addr + i * PAGE_SIZE, i, arg); if (ret) return ret; } } else { /* If target subpage in second half of huge page */ base = nr_pages - 2 * (nr_pages - n); l = nr_pages - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); ret = process_subpage(addr + i * PAGE_SIZE, i, arg); if (ret) return ret; } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); ret = process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); if (ret) return ret; cond_resched(); ret = process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); if (ret) return ret; } return 0; } static void clear_gigantic_page(struct folio *folio, unsigned long addr, unsigned int nr_pages) { int i; might_sleep(); for (i = 0; i < nr_pages; i++) { cond_resched(); clear_user_highpage(folio_page(folio, i), addr + i * PAGE_SIZE); } } static int clear_subpage(unsigned long addr, int idx, void *arg) { struct folio *folio = arg; clear_user_highpage(folio_page(folio, idx), addr); return 0; } /** * folio_zero_user - Zero a folio which will be mapped to userspace. * @folio: The folio to zero. * @addr_hint: The address will be accessed or the base address if uncelar. */ void folio_zero_user(struct folio *folio, unsigned long addr_hint) { unsigned int nr_pages = folio_nr_pages(folio); if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) clear_gigantic_page(folio, addr_hint, nr_pages); else process_huge_page(addr_hint, nr_pages, clear_subpage, folio); } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, unsigned long addr, struct vm_area_struct *vma, unsigned int nr_pages) { int i; struct page *dst_page; struct page *src_page; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); src_page = folio_page(src, i); cond_resched(); if (copy_mc_user_highpage(dst_page, src_page, addr + i*PAGE_SIZE, vma)) return -EHWPOISON; } return 0; } struct copy_subpage_arg { struct folio *dst; struct folio *src; struct vm_area_struct *vma; }; static int copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; struct page *dst = folio_page(copy_arg->dst, idx); struct page *src = folio_page(copy_arg->src, idx); if (copy_mc_user_highpage(dst, src, addr, copy_arg->vma)) return -EHWPOISON; return 0; } int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma) { unsigned int nr_pages = folio_nr_pages(dst); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) return copy_user_gigantic_page(dst, src, addr_hint, vma, nr_pages); return process_huge_page(addr_hint, nr_pages, copy_subpage, &arg); } long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault) { void *kaddr; unsigned long i, rc = 0; unsigned int nr_pages = folio_nr_pages(dst_folio); unsigned long ret_val = nr_pages * PAGE_SIZE; struct page *subpage; for (i = 0; i < nr_pages; i++) { subpage = folio_page(dst_folio, i); kaddr = kmap_local_page(subpage); if (!allow_pagefault) pagefault_disable(); rc = copy_from_user(kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE); if (!allow_pagefault) pagefault_enable(); kunmap_local(kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct ptdesc *ptdesc) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; ptdesc->ptl = ptl; return true; } void ptlock_free(struct ptdesc *ptdesc) { kmem_cache_free(page_ptl_cachep, ptdesc->ptl); } #endif void vma_pgtable_walk_begin(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma); } void vma_pgtable_walk_end(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; bool inaccessible; }; /* * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/mm/hmm.rst. * * MEMORY_DEVICE_COHERENT: * Device memory that is cache coherent from device and CPU point of view. This * is used on platforms that have an advanced system bus (like CAPI or CXL). A * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the page refcount reaches 0. The reference count will be * reset to one by the core code after the method is called to prepare * for handing out the page again. */ void (*page_free)(struct page *page); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); /* * Handle the memory failure happens on a range of pfns. Notify the * processes who are using these pfns, and try to recover the data on * them if necessary. The mf_flags is finally passed to the recover * function through the whole notify routine. * * When this is not implemented, or it returns -EOPNOTSUPP, the caller * will fall back to a common handler called mf_generic_kill_procs(). */ int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref * @type: memory type: see MEMORY_* above in memremap.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. * A zero value (default) uses base pages as the vmemmap metadata * representation. A bigger value will set up compound struct pages * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; DECLARE_FLEX_ARRAY(struct range, ranges); }; }; static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) { return pgmap->ops && pgmap->ops->memory_failure; } static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) { return 1 << pgmap->vmemmap_shift; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool folio_is_device_private(const struct folio *folio) { return is_device_private_page(&folio->page); } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_device_coherent_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool folio_is_device_coherent(const struct folio *folio) { return is_device_coherent_page(&folio->page); } #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), }; struct udp_tunnel_nic_table_entry { __be16 port; u8 type; u8 flags; u16 use_cnt; #define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; /** * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { struct work_struct work; struct net_device *dev; u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; unsigned int n_tables; unsigned long missed; struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. * We need a workqueue we can flush before module gets removed. */ static struct workqueue_struct *udp_tunnel_nic_workqueue; static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) { switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: return "geneve"; case UDP_TUNNEL_TYPE_VXLAN_GPE: return "vxlan-gpe"; default: return "unknown"; } } static bool udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt == 0 && !entry->flags; } static bool udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); } static bool udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) { if (!udp_tunnel_nic_entry_is_free(entry)) entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) { entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; } static bool udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | UDP_TUNNEL_NIC_ENTRY_DEL); } static void udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, struct udp_tunnel_nic_table_entry *entry, unsigned int flag) { entry->flags |= flag; utn->need_sync = 1; } static void udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, struct udp_tunnel_info *ti) { memset(ti, 0, sizeof(*ti)); ti->port = entry->port; ti->type = entry->type; ti->hw_priv = entry->hw_priv; } static bool udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return false; return true; } static bool udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; if (!utn->missed) return false; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!test_bit(i, &utn->missed)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return true; } return false; } static void __udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; entry = &utn->entries[table][idx]; if (entry->use_cnt) udp_tunnel_nic_ti_from_entry(entry, ti); } static void __udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; } static void udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, int err) { bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && (!err || (err == -EEXIST && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && (!err || (err == -ENOENT && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; if (!err) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; else entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; } static void udp_tunnel_nic_device_sync_one(struct net_device *dev, struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_info ti; int err; entry = &utn->entries[table][idx]; if (!udp_tunnel_nic_entry_is_queued(entry)) return; udp_tunnel_nic_ti_from_entry(entry, &ti); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); else err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, &ti); udp_tunnel_nic_entry_update_done(entry, err); if (err) netdev_warn(dev, "UDP tunnel port sync failed port %d type %s: %d\n", be16_to_cpu(entry->port), udp_tunnel_nic_tunnel_type_name(entry->type), err); } static void udp_tunnel_nic_device_sync_by_port(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_device_sync_one(dev, utn, i, j); } static void udp_tunnel_nic_device_sync_by_table(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; int err; for (i = 0; i < utn->n_tables; i++) { /* Find something that needs sync in this table */ for (j = 0; j < info->tables[i].n_entries; j++) if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) break; if (j == info->tables[i].n_entries) continue; err = info->sync_table(dev, i); if (err) netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", i, err); for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (udp_tunnel_nic_entry_is_queued(entry)) udp_tunnel_nic_entry_update_done(entry, err); } } } static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; if (dev->udp_tunnel_nic_info->sync_table) udp_tunnel_nic_device_sync_by_table(dev, utn); else udp_tunnel_nic_device_sync_by_port(dev, utn); utn->need_sync = 0; /* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); } static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; bool may_sleep; if (!utn->need_sync) return; /* Drivers which sleep in the callback need to update from * the workqueue, if we come from the tunnel driver's notification. */ may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; if (!may_sleep) __udp_tunnel_nic_device_sync(dev, utn); if (may_sleep || utn->need_replay) { queue_work(udp_tunnel_nic_workqueue, &utn->work); utn->work_pending = 1; } } static bool udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, struct udp_tunnel_info *ti) { return table->tunnel_types & ti->type; } static bool udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i; /* Special case IPv4-only NICs */ if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && ti->sa_family != AF_INET) return false; for (i = 0; i < utn->n_tables; i++) if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) return true; return false; } static int udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_table_entry *entry; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { __set_bit(i, &utn->missed); return true; } } return false; } static void udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ entry->use_cnt += use_cnt_adj; if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) return; /* Cancel the op before it was sent to the device, if possible, * otherwise we'd need to take special care to issue commands * in the same order the ports arrived. */ if (use_cnt_adj < 0) { from = UDP_TUNNEL_NIC_ENTRY_ADD; to = UDP_TUNNEL_NIC_ENTRY_DEL; } else { from = UDP_TUNNEL_NIC_ENTRY_DEL; to = UDP_TUNNEL_NIC_ENTRY_ADD; } if (entry->flags & from) { entry->flags &= ~from; if (!dodgy) return; } udp_tunnel_nic_entry_queue(utn, entry, to); } static bool udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; if (udp_tunnel_nic_entry_is_free(entry) || entry->port != ti->port || entry->type != ti->type) return false; if (udp_tunnel_nic_entry_is_frozen(entry)) return true; udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); return true; } /* Try to find existing matching entry and adjust its use count, instead of * adding a new one. Returns true if entry was found. In case of delete the * entry may have gotten removed in the process, in which case it will be * queued for removal. */ static bool udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti, int use_cnt_adj) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, use_cnt_adj)) return true; } return false; } static bool udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, +1); } static bool udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, -1); } static bool udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry)) continue; entry->port = ti->port; entry->type = ti->type; entry->use_cnt = 1; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); return true; } /* The different table may still fit this port in, but there * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ __set_bit(i, &utn->missed); } return false; } static void __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && ti->port == htons(IANA_VXLAN_UDP_PORT)) { if (ti->type != UDP_TUNNEL_TYPE_VXLAN) netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); return; } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; /* It may happen that a tunnel of one type is removed and different * tunnel type tries to reuse its port before the device was informed. * Rely on utn->missed to re-add this port later. */ if (udp_tunnel_nic_has_collision(dev, utn, ti)) return; if (!udp_tunnel_nic_add_existing(dev, utn, ti)) udp_tunnel_nic_add_new(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; udp_tunnel_nic_del_existing(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int i, j; ASSERT_RTNL(); utn = dev->udp_tunnel_nic; if (!utn) return; utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); /* We don't release rtnl across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); } __udp_tunnel_nic_device_sync(dev, utn); } static size_t __udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int j; size_t size; utn = dev->udp_tunnel_nic; if (!utn) return 0; size = 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; size += nla_total_size(0) + /* _TABLE_ENTRY */ nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ } return size; } static int __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; struct nlattr *nest; unsigned int j; utn = dev->udp_tunnel_nic; if (!utn) return 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, ilog2(utn->entries[table][j].type))) goto err_cancel; nla_nest_end(skb, nest); } return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, .add_port = __udp_tunnel_nic_add_port, .del_port = __udp_tunnel_nic_del_port, .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, }; static void udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { int adj_cnt = -utn->entries[i][j].use_cnt; if (adj_cnt) udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); } __udp_tunnel_nic_device_sync(dev, utn); for (i = 0; i < utn->n_tables; i++) memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, sizeof(**utn->entries))); WARN_ON(utn->need_sync); utn->need_replay = 0; } static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay * does not double up the refcount. */ for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); utn->missed = 0; utn->need_replay = 0; if (!info->shared) { udp_tunnel_get_rx_info(dev); } else { list_for_each_entry(node, &info->shared->devices, list) udp_tunnel_get_rx_info(node->dev); } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); rtnl_unlock(); } static struct udp_tunnel_nic * udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, unsigned int n_tables) { struct udp_tunnel_nic *utn; unsigned int i; utn = kzalloc(struct_size(utn, entries, n_tables), GFP_KERNEL); if (!utn) return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, sizeof(*utn->entries[i]), GFP_KERNEL); if (!utn->entries[i]) goto err_free_prev_entries; } return utn; err_free_prev_entries: while (i--) kfree(utn->entries[i]); kfree(utn); return NULL; } static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) { unsigned int i; for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); kfree(utn); } static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); /* Expect use count of at most 2 (IPv4, IPv6) per device */ BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; if (WARN_ON(info->shared && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return -EINVAL; n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) continue; n_tables++; if (WARN_ON(!info->tables[i - 1].n_entries)) return -EINVAL; } /* Create UDP tunnel state structures */ if (info->shared) { node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->dev = dev; } if (info->shared && info->shared->udp_tunnel_nic_info) { utn = info->shared->udp_tunnel_nic_info; } else { utn = udp_tunnel_nic_alloc(info, n_tables); if (!utn) { kfree(node); return -ENOMEM; } } if (info->shared) { if (!info->shared->udp_tunnel_nic_info) { INIT_LIST_HEAD(&info->shared->devices); info->shared->udp_tunnel_nic_info = utn; } list_add_tail(&node->list, &info->shared->devices); } utn->dev = dev; dev_hold(dev); dev->udp_tunnel_nic = utn; if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) udp_tunnel_get_rx_info(dev); return 0; } static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ if (info->shared) { struct udp_tunnel_nic_shared_node *node, *first; list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; if (list_entry_is_head(node, &info->shared->devices, list)) return; list_del(&node->list); kfree(node); first = list_first_entry_or_null(&info->shared->devices, typeof(*first), list); if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; goto release_dev; } info->shared->udp_tunnel_nic_info = NULL; } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. */ if (utn->work_pending) return; udp_tunnel_nic_free(utn); release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } static int udp_tunnel_nic_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); const struct udp_tunnel_nic_info *info; struct udp_tunnel_nic *utn; info = dev->udp_tunnel_nic_info; if (!info) return NOTIFY_DONE; if (event == NETDEV_REGISTER) { int err; err = udp_tunnel_nic_register(dev); if (err) netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ utn = dev->udp_tunnel_nic; if (!utn) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { udp_tunnel_nic_unregister(dev, utn); return NOTIFY_OK; } /* All other events only matter if NIC has to be programmed open */ if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return NOTIFY_DONE; if (event == NETDEV_UP) { WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { udp_tunnel_nic_flush(dev, utn); return NOTIFY_OK; } return NOTIFY_DONE; } static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { .notifier_call = udp_tunnel_nic_netdevice_event, }; static int __init udp_tunnel_nic_init_module(void) { int err; udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; rtnl_lock(); udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; rtnl_unlock(); err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); if (err) goto err_unset_ops; return 0; err_unset_ops: rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); return err; } late_initcall(udp_tunnel_nic_init_module); static void __exit udp_tunnel_nic_cleanup_module(void) { unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); } module_exit(udp_tunnel_nic_cleanup_module); MODULE_LICENSE("GPL"); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * Forwarding Information Database * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Changes: * Yuji SEKIYA @USAGI: Support default route on router node; * remove ip6_null_entry from the top of * routing table. * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/bpf.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; bool skip_notify; }; #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else #define FWS_INIT FWS_L #endif static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* * A routing update causes an increase of the serial number on the * affected subtree. This allows for cached routes to be asynchronously * tested when modifications are made to the destination cache as a * result of redirects, path MTU changes, etc. */ static void fib6_gc_timer_cb(struct timer_list *t); #define FOR_WALKERS(net, w) \ list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) static void fib6_walker_link(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_add(&w->lh, &net->ipv6.fib6_walkers); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) { int new, old = atomic_read(&net->ipv6.fib6_sernum); do { new = old < INT_MAX ? old + 1 : 1; } while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new)); return new; } enum { FIB6_NO_SERNUM_CHANGE = 0, }; void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { struct fib6_node *fn; fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* * Auxiliary address test functions for the radix tree. * * These assume a 32bit processor (although it will work on * 64bit processors) */ /* * test bit */ #if defined(__LITTLE_ENDIAN) # define BITOP_BE32_SWIZZLE (0x1F & ~7) #else # define BITOP_BE32_SWIZZLE 0 #endif static __be32 addr_bit_set(const void *token, int fn_bit) { const __be32 *addr = token; /* * Here, * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5]; } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) { struct fib6_info *f6i; size_t sz = sizeof(*f6i); if (with_fib6_nh) sz += sizeof(struct fib6_nh); f6i = kzalloc(sz, gfp_flags); if (!f6i) return NULL; /* fib6_siblings is a union with nh_list, so this initializes both */ INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); INIT_HLIST_NODE(&f6i->gc_link); return f6i; } void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); WARN_ON(f6i->fib6_node); if (f6i->nh) nexthop_put(f6i->nh); else fib6_nh_release(f6i->fib6_nh); ip_fib_metrics_put(f6i->fib6_metrics); kfree(f6i); } EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); if (fn) net->ipv6.rt6_stats->fib_nodes++; return fn; } static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); net->ipv6.rt6_stats->fib_nodes--; } static void node_free(struct net *net, struct fib6_node *fn) { kfree_rcu(fn, rcu); net->ipv6.rt6_stats->fib_nodes--; } static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); kfree(table); } static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; /* * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation * operation, tables never disappear once they exist. */ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) { struct fib6_table *table; table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; } struct fib6_table *fib6_new_table(struct net *net, u32 id) { struct fib6_table *tb; if (id == 0) id = RT6_TABLE_MAIN; tb = fib6_get_table(net, id); if (tb) return tb; tb = fib6_alloc_table(net, id); if (tb) fib6_link_table(net, tb); return tb; } EXPORT_SYMBOL_GPL(fib6_new_table); struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct fib6_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT6_TABLE_MAIN; h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (tb->tb6_id == id) { rcu_read_unlock(); return tb; } } rcu_read_unlock(); return NULL; } EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); } #else struct fib6_table *fib6_new_table(struct net *net, u32 id) { return fib6_get_table(net, id); } struct fib6_table *fib6_get_table(struct net *net, u32 id) { return net->ipv6.fib6_main_tbl; } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); } return &rt->dst; } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } #endif unsigned int fib6_tables_seq_read(const struct net *net) { unsigned int h, fib_seq = 0; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { const struct hlist_head *head = &net->ipv6.fib_table_hash[h]; const struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += READ_ONCE(tb->fib_seq); } rcu_read_unlock(); return fib_seq; } static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; return call_fib6_notifier(nb, event_type, &info.info); } static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, .nsiblings = rt->fib6_nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); } struct fib6_dump_arg { struct net *net; struct notifier_block *nb; struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; if (rt->fib6_nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, rt->fib6_nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, arg->extack); return err; } static int fib6_node_dump(struct fib6_walker *w) { int err; err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } static int fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { int err; w->root = &tb->tb6_root; spin_lock_bh(&tb->tb6_lock); err = fib6_walk(net, w); spin_unlock_bh(&tb->tb6_lock); return err; } /* Called with rcu_read_lock() */ int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; unsigned int h; int err = 0; w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_node_dump; arg.net = net; arg.nb = nb; arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); if (err) goto out; } } out: kfree(w); /* The tree traversal function should never return a positive value. */ return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) { int res; struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args, w->skip_in_node); if (res >= 0) { /* Frame is full, suspend walking */ w->leaf = rt; /* We'll restart from this node, so if some routes were * already dumped, skip them next time. */ w->skip_in_node += res; return 1; } w->skip_in_node = 0; /* Multipath routes are dumped in one route with the * RTA_MULTIPATH attribute. Jump 'rt' to point to the * last sibling of this route (no need to dump the * sibling routes again) */ if (rt->fib6_nsiblings) rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); } w->leaf = NULL; return 0; } static void fib6_dump_end(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); } cb->done = (void *)cb->args[3]; cb->args[1] = 3; } static int fib6_dump_done(struct netlink_callback *cb) { fib6_dump_end(cb); return cb->done ? cb->done(cb) : 0; } static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; w = (void *)cb->args[2]; w->root = &table->tb6_root; if (cb->args[4] == 0) { w->count = 0; w->skip = 0; w->skip_in_node = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { int sernum = READ_ONCE(w->root->fn_sernum); if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; w->skip_in_node = 0; } else w->skip = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; } } return res; } static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, .filter.dump_routes = true, .filter.rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int e = 0, s_e; struct hlist_head *head; struct fib6_walker *w; struct fib6_table *tb; unsigned int h, s_h; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); if (rtm->rtm_flags & RTM_F_PREFIX) arg.filter.flags = RTM_F_PREFIX; } w = (void *)cb->args[2]; if (!w) { /* New dump: * * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) { err = -ENOMEM; goto unlock; } w->func = fib6_dump_node; cb->args[2] = (long)w; /* 2. hook callback destructor. */ cb->args[3] = (long)cb->done; cb->done = fib6_dump_done; } arg.skb = skb; arg.cb = cb; arg.net = net; w->args = &arg; if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET6) goto unlock; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); err = -ENOENT; goto unlock; } if (!cb->args[0]) { err = fib6_dump_table(tb, skb, cb); if (!err) cb->args[0] = 1; } goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; err = fib6_dump_table(tb, skb, cb); if (err != 0) goto out; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); if (err <= 0) fib6_dump_end(cb); return err; } void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) { if (!f6i) return; if (f6i->fib6_metrics == &dst_default_metrics) { struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); if (!p) return; refcount_set(&p->refcnt, 1); f6i->fib6_metrics = p; } f6i->fib6_metrics->metrics[metric - 1] = val; } /* * Routing Table * * return the appropriate node for a routing tree "add" operation * by either creating and inserting or by returning an existing * node. */ static struct fib6_node *fib6_add_1(struct net *net, struct fib6_table *table, struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required, struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; __be32 dir = 0; /* insert node in tree */ fn = root; do { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } goto insert_above; } /* * Exact match ? */ if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } return fn; } /* * We have more bits to go */ /* Try to walk down on tree. */ dir = addr_bit_set(addr, fn->fn_bit); pn = fn; fn = dir ? rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)) : rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { /* We should not create new node because * NLM_F_REPLACE was specified without NLM_F_CREATE * I assume it is safe to require NLM_F_CREATE when * REPLACE flag is used! Later we may want to remove the * check for replace_required, because according * to netlink specification, NLM_F_CREATE * MUST be specified if new route is created. * That would keep IPv6 consistent with IPv4 */ if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } /* * We walked to the bottom of tree. * Create new leaf node without children. */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); return ln; insert_above: /* * split since we don't have a common prefix anymore or * we have a less significant route. * we've to insert an intermediate node on the list * this new node will point to the one we need to create * and the current */ pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. See comment in __ipv6_addr_diff: bit may be an invalid value, but if it is >= plen, the value is ignored in any case. */ bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] * / \ * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { in = node_alloc(net); ln = node_alloc(net); if (!in || !ln) { if (in) node_free_immediate(net, in); if (ln) node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } /* * new intermediate node. * RTN_RTINFO will * be off since that an address that chooses one of * the branches would not match less specific routes * in the other branch */ in->fn_bit = bit; RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; fib6_info_hold(rcu_dereference_protected(in->leaf, lockdep_is_held(&table->tb6_lock))); /* update parent pointer */ if (dir) rcu_assign_pointer(pn->right, in); else rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, in); rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { rcu_assign_pointer(in->right, ln); rcu_assign_pointer(in->left, fn); } else { rcu_assign_pointer(in->left, ln); rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ /* * (new leaf node)[ln] * / \ * (old node)[fn] NULL */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) RCU_INIT_POINTER(ln->right, fn); else RCU_INIT_POINTER(ln->left, fn); rcu_assign_pointer(fn->parent, ln); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); } return ln; } static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, const struct fib6_info *match, const struct fib6_table *table) { int cpu; if (!fib6_nh->rt6i_pcpu) return; rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ for_each_possible_cpu(cpu) { struct rt6_info **ppcpu_rt; struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); /* Paired with xchg() in rt6_get_pcpu_route() */ pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes * from a fib6_info to NULL (ip6_dst_destroy); it can never * change from one fib6_info reference to another */ if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } } rcu_read_unlock(); } struct fib6_nh_pcpu_arg { struct fib6_info *from; const struct fib6_table *table; }; static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { struct fib6_nh_pcpu_arg *arg = _arg; __fib6_drop_pcpu_from(nh, arg->from, arg->table); return 0; } static void fib6_drop_pcpu_from(struct fib6_info *f6i, const struct fib6_table *table) { /* Make sure rt6_make_pcpu_route() wont add other percpu routes * while we are cleaning them here. */ f6i->fib6_destroying = 1; mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ if (f6i->nh) { struct fib6_nh_pcpu_arg arg = { .from = f6i, .table = table }; nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; __fib6_drop_pcpu_from(fib6_nh, f6i, table); } } static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { struct fib6_table *table = rt->fib6_table; /* Flush all cached dst in exception table */ rt6_flush_exceptions(rt); fib6_drop_pcpu_from(rt, table); if (rt->nh && !list_empty(&rt->nh_list)) list_del_init(&rt->nh_list); if (refcount_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes * and replace dummy references to this route with references * to still alive ones. */ while (fn) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); fib6_info_hold(new_leaf); rcu_assign_pointer(fn->leaf, new_leaf); fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } } fib6_clean_expires(rt); fib6_remove_gc_list(rt); } /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; for (iter = leaf; iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; nlflags &= ~NLM_F_EXCL; if (replace) { if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { found++; break; } fallback_ins = fallback_ins ?: ins; goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) rt->fib6_nsiblings = 0; if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); fib6_remove_gc_list(iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, * but not the same gateway, then the route we try to * add is sibling to this route, increment our counter * of siblings, and later we will add our route to the * list. * Only static routes (which don't have flag * RTF_EXPIRES) are used for ECMPv6. * * To avoid long list, we only had siblings if the * route have a gateway. */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; next_iter: ins = &iter->fib6_next; } if (fallback_ins && !found) { /* No matching route with same ecmp-able-ness found, replace * first matching route */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); found++; } /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ if (rt->fib6_nsiblings) { unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ sibling = leaf; notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { list_add_tail_rcu(&rt->fib6_siblings, &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rt6_multipath_rebalance(temp_sibling); } /* * insert node */ if (!replace) { if (!add) pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: nlflags |= NLM_F_CREATE; /* The route should only be notified if it is the first * route in the node or if it is added as a sibling * route to the first route in the node. */ if (!info->skip_notify_kernel && (notify_sibling_rt || ins == &fn->leaf)) { enum fib_event_type fib_event; if (notify_sibling_rt) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, fib_event, rt, extack); if (err) { struct fib6_info *sibling, *next_sibling; /* If the route has siblings, then it first * needs to be unlinked from them. */ if (!rt->fib6_nsiblings) return err; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } } rcu_assign_pointer(rt->fib6_next, iter); fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } } else { int nsiblings; if (!found) { if (add) goto add; pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; } fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } nsiblings = iter->fib6_nsiblings; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->fib6_next; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric > rt->fib6_metric) break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->fib6_next; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->fib6_next; } iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); } WARN_ON(nsiblings != 0); } } return 0; } static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } void fib6_force_start_gc(struct net *net) { if (!timer_pending(&net->ipv6.ip6_fib_timer)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } } void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } /* allow ipv4 to update sernum via ipv6_stub */ void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum_upto_root(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); } /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; struct fib6_node *fn; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node *pn = NULL; #endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; if (info->nlh->nlmsg_flags & NLM_F_REPLACE) replace_required = 1; } if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, &rt->fib6_dst.addr, rt->fib6_dst.plen, offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; goto out; } #ifdef CONFIG_IPV6_SUBTREES pn = fn; if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* * Create subtree. * * fn[main tree] * | * sfn[subtree root] * \ * sn[new leaf node] */ /* Create subtree root node */ sfn = node_alloc(info->nl_net); if (!sfn) goto failure; fib6_info_hold(info->nl_net->ipv6.fib6_null_entry); rcu_assign_pointer(sfn->leaf, info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ rcu_assign_pointer(sfn->parent, fn); rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); goto failure; } } if (!rcu_access_pointer(fn->leaf)) { if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, info->nl_net->ipv6.fib6_null_entry); } else { fib6_info_hold(rt); rcu_assign_pointer(fn->leaf, rt); } } fn = sn; } #endif err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); if (rt->fib6_flags & RTF_EXPIRES) fib6_add_gc_list(rt); fib6_start_gc(info->nl_net, rt); } out: if (err) { #ifdef CONFIG_IPV6_SUBTREES /* * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } #endif goto failure; } else if (fib6_requires_src(rt)) { fib6_routes_require_src_inc(info->nl_net); } return err; failure: /* fn->leaf could be NULL and fib6_repair_tree() needs to be called if: * 1. fn is an intermediate node and we failed to add the new * route to it in both subtree creation failure and fib6_add_rt2node() * failure case. * 2. fn is the root node in the table and we fail to add the first * default route to it. */ if (fn && (!(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)) || (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); return err; } /* * Routing tree lookup * */ struct lookup_args { int offset; /* key offset on fib6_info */ const struct in6_addr *addr; /* search key */ }; static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root, struct lookup_args *args) { struct fib6_node *fn; __be32 dir; if (unlikely(args->offset == 0)) return NULL; /* * Descend on a tree */ fn = root; for (;;) { struct fib6_node *next; dir = addr_bit_set(args->addr, fn->fn_bit); next = dir ? rcu_dereference(fn->right) : rcu_dereference(fn->left); if (next) { fn = next; continue; } break; } while (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) goto backtrack; key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES if (subtree) { struct fib6_node *sfn; sfn = fib6_node_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; } #endif if (fn->fn_flags & RTN_RTINFO) return fn; } } backtrack: if (fn->fn_flags & RTN_ROOT) break; fn = rcu_dereference(fn->parent); } return NULL; } /* called with rcu_read_lock() held */ struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { { .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif { .offset = 0, /* sentinel */ } }; fn = fib6_node_lookup_1(root, daddr ? args : args + 1); if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; } /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) * exact_match == true means we try to find fn with exact match of * the passed in prefix addr * exact_match == false means we try to find fn with longest prefix * match of the passed in prefix addr. This is useful for finding fn * for cached route as it will be stored in the exception table under * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, int plen, int offset, bool exact_match) { struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ if (!leaf) { if (plen <= fn->fn_bit) goto out; else goto next; } key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) goto out; if (plen == fn->fn_bit) return fn; if (fn->fn_flags & RTN_RTINFO) prev = fn; next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) fn = rcu_dereference(fn->right); else fn = rcu_dereference(fn->left); } out: if (exact_match) return NULL; else return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); if (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct fib6_info, fib6_src), exact_match); } } } #endif if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; } /* * Deletion * */ static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); child_right = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); if (child_left) return rcu_dereference_protected(child_left->leaf, lockdep_is_held(&table->tb6_lock)); if (child_right) return rcu_dereference_protected(child_right->leaf, lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } return NULL; } /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn) { int children; int nstate; struct fib6_node *child; struct fib6_walker *w; int iter = 0; /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } for (;;) { struct fib6_node *fn_r = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *fn_l = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_r = rcu_dereference_protected(pn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); WARN_ON(fn_leaf); children = 0; child = NULL; if (fn_r) { child = fn_r; children |= 1; } if (fn_l) { child = fn_l; children |= 2; } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ || (children && fn->fn_flags & RTN_ROOT) #endif ) { new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); new_fn_leaf = net->ipv6.fib6_null_entry; } #endif fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif if (pn_r == fn) rcu_assign_pointer(pn->right, child); else if (pn_l == fn) rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } #endif read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { if (w->node == fn) { w->node = child; if (children&2) { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } } read_unlock(&net->ipv6.fib6_walker_lock); node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; bool notify_del = false; /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. */ leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); if (leaf == rt && !rt->fib6_nsiblings) { if (rcu_access_pointer(rt->fib6_next)) replace_rt = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); else notify_del = true; } /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; /* Reset round-robin state, if necessary */ if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; /* The route is deleted from a multipath route. If this * multipath route is the first route in the node, then we need * to emit a delete notification. Otherwise, we need to skip * the notification. */ if (rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf)) notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } /* Adjust walkers */ read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); /* If it was last route, call fib6_repair_tree() to: * 1. For root node, put back null_entry as how the table was created. * 2. For other nodes, expunge its radix tree node. */ if (!rcu_access_pointer(fn->leaf)) { if (!(fn->fn_flags & RTN_TL_ROOT)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; } fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); if (!info->skip_notify_kernel) { if (notify_del) call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); else if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); fib6_info_release(rt); } /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; struct fib6_table *table; struct fib6_node *fn; if (rt == net->ipv6.fib6_null_entry) return -ENOENT; table = rt->fib6_table; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { if (fib6_requires_src(cur)) fib6_routes_require_src_dec(info->nl_net); fib6_del_route(table, fn, rtp, info); return 0; } rtp_next = &cur->fib6_next; } return -ENOENT; } /* * Tree traversal function. * * Certainly, it is not interrupt safe. * However, it is internally reenterable wrt itself and fib6_add/fib6_del. * It means, that we can modify tree during walking * and use this function for garbage collection, clone pruning, * cleaning tree when a device goes down etc. etc. * * It guarantees that every node will be traversed, * and that it will be traversed only once. * * Callback function w->func may return: * 0 -> continue walking. * positive value -> walking is suspended (used by tree dumps, * and probably by gc, if it will be split to several slices) * negative value -> terminate walking. * * The function itself returns: * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. * * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn, *left, *right; /* w->root should always be table->tb6_root */ WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: if (FIB6_SUBTREE(fn)) { w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; fallthrough; #endif case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; fallthrough; case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); fallthrough; case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; if (w->skip) { w->skip--; goto skip; } err = w->func(w); if (err) return err; w->count++; continue; } skip: w->state = FWS_U; fallthrough; case FWS_U: if (fn == w->root) return 0; pn = rcu_dereference_protected(fn->parent, 1); left = rcu_dereference_protected(pn->left, 1); right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } #endif if (left == fn) { w->state = FWS_R; continue; } if (right == fn) { w->state = FWS_C; w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 WARN_ON(1); #endif } } } static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) fib6_walker_unlink(net, w); return res; } static int fib6_clean_node(struct fib6_walker *w) { int res; struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, .skip_notify = c->skip_notify, }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && READ_ONCE(w->node->fn_sernum) != c->sernum) WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); w->leaf = NULL; return 0; } for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res == -1) { w->leaf = rt; res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { if (WARN_ON(!rt->fib6_nsiblings)) continue; rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); } w->leaf = rt; return 0; } /* * Convenient frontend to tree walker. * * func is called on each route. * It may return -2 -> skip multipath route. * -1 -> delete this route. * 0 -> continue walking */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct fib6_info *, void *arg), int sernum, void *arg, bool skip_notify) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; c.w.count = 0; c.w.skip = 0; c.w.skip_in_node = 0; c.func = func; c.sernum = sernum; c.arg = arg; c.net = net; c.skip_notify = skip_notify; fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), int sernum, void *arg, bool skip_notify) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, sernum, arg, skip_notify); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false); } void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true); } static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); __fib6_clean_all(net, NULL, new_sernum, NULL, false); } /* * Garbage collection */ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { unsigned long now = jiffies; /* * check addrconf expiration here. * Routes are expired even if they are in use. */ if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; } /* Also age clones in the exception table. * Note, that clones are aged out * only if they are not in use now. */ rt6_age_exceptions(rt, gc_args, now); return 0; } static void fib6_gc_table(struct net *net, struct fib6_table *tb6, struct fib6_gc_args *gc_args) { struct fib6_info *rt; struct hlist_node *n; struct nl_info info = { .nl_net = net, .skip_notify = false, }; hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) if (fib6_age(rt, gc_args) == -1) fib6_del(rt, &info); } static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_gc_table(net, table, gc_args); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; unsigned long now; if (force) { spin_lock_bh(&net->ipv6.fib6_gc_lock); } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, round_jiffies(now + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(struct timer_list *t) { struct net *arg = from_timer(arg, t, ipv6.ip6_fib_timer); fib6_run_gc(0, arg, true); } static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; int err; err = fib6_notifier_init(net); if (err) return err; /* Default to 3-tuple */ net->ipv6.sysctl.multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); timer_setup(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, 0); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl), GFP_KERNEL); if (!net->ipv6.fib6_main_tbl) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), GFP_KERNEL); if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: kfree(net->ipv6.fib6_main_tbl); #endif out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); out_notifier: fib6_notifier_exit(net); return -ENOMEM; } static void fib6_net_exit(struct net *net) { unsigned int i; del_timer_sync(&net->ipv6.ip6_fib_timer); for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { struct hlist_head *head = &net->ipv6.fib_table_hash[i]; struct hlist_node *tmp; struct fib6_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { hlist_del(&tb->tb6_hlist); fib6_free_table(tb); } } kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); fib6_notifier_exit(net); } static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, }; static const struct rtnl_msg_handler fib6_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .dumpit = inet6_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; int __init fib6_init(void) { int ret = -ENOMEM; fib6_node_kmem = KMEM_CACHE(fib6_node, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; ret = register_pernet_subsys(&fib6_net_ops); if (ret) goto out_kmem_cache_create; ret = rtnl_register_many(fib6_rtnl_msg_handlers); if (ret) goto out_unregister_subsys; __fib6_flush_trees = fib6_flush_trees; out: return ret; out_unregister_subsys: unregister_pernet_subsys(&fib6_net_ops); out_kmem_cache_create: kmem_cache_destroy(fib6_node_kmem); goto out; } void fib6_gc_cleanup(void) { unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } #ifdef CONFIG_PROC_FS static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) { struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; struct fib6_nh *fib6_nh = rt->fib6_nh; unsigned int flags = rt->fib6_flags; const struct net_device *dev; if (rt->nh) fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif if (fib6_nh->fib_nh_gw_family) { flags |= RTF_GATEWAY; seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); } else { seq_puts(seq, "00000000000000000000000000000000"); } dev = fib6_nh->fib_nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } static int ipv6_route_yield(struct fib6_walker *w) { struct ipv6_route_iter *iter = w->args; if (!iter->skip) return 1; do { iter->w.leaf = rcu_dereference_protected( iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; } while (iter->w.leaf); return 0; } static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; iter->w.root = &iter->tbl->tb6_root; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, struct net *net) { unsigned int h; struct hlist_node *node; if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); } static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { int sernum = READ_ONCE(iter->w.root->fn_sernum); if (iter->sernum != sernum) { iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); iter->w.skip = iter->w.count; } } static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; ++(*pos); if (!v) goto iter_table; n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; iter_table: ipv6_route_check_sernum(iter); spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); return NULL; } fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; ipv6_route_seq_setup_walk(iter, net); goto iter_table; } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; if (iter->tbl) { loff_t p = 0; ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } } static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; return w->node && !(w->state == FWS_U && w->node == w->root); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) static int ipv6_route_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__ipv6_route ctx; ctx.meta = meta; ctx.rt = v; return bpf_iter_run_prog(prog, &ctx); } static int ipv6_route_seq_show(struct seq_file *seq, void *v) { struct ipv6_route_iter *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return ipv6_route_native_seq_show(seq, v); ret = ipv6_route_prog_seq_show(prog, &meta, v); iter->w.leaf = NULL; return ret; } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)ipv6_route_prog_seq_show(prog, &meta, v); } ipv6_route_native_seq_stop(seq, v); } #else static int ipv6_route_seq_show(struct seq_file *seq, void *v) { return ipv6_route_native_seq_show(seq, v); } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { ipv6_route_native_seq_stop(seq, v); } #endif const struct seq_operations ipv6_route_seq_ops = { .start = ipv6_route_seq_start, .next = ipv6_route_seq_next, .stop = ipv6_route_seq_stop, .show = ipv6_route_seq_show }; #endif /* CONFIG_PROC_FS */ |
| 91 546 217 217 217 216 188 188 541 541 50 50 529 529 528 226 225 177 178 178 482 483 261 261 261 324 325 68 68 101 101 47 47 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * iw_table is the sysfs-set interleave weight table, a value of 0 denotes * system-default value should be used. A NULL iw_table also denotes that * system-default values should be used. Until the system-default table * is implemented, the system-default is always 1. * * iw_table is RCU protected */ static u8 __rcu *iw_table; static DEFINE_MUTEX(iw_table_lock); static u8 get_il_weight(int node) { u8 *table; u8 weight; rcu_read_lock(); table = rcu_dereference(iw_table); /* if no iw_table, use system default */ weight = table ? table[node] : 1; /* if value in iw_table is 0, use system default */ weight = weight ? weight : 1; rcu_read_unlock(); return weight; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed++; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table; unsigned int weight_total = 0; u8 weight; int nid; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); table = rcu_dereference(iw_table); /* calculate the total weight */ for_each_node_mask(nid, nodemask) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; weight_total += weight; } /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node_noprof(nid, gfp | __GFP_THISNODE | __GFP_NORETRY, order); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { return page_rmappable_folio(alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, pol, ilx, nid)); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of alloc_pages_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, NULL, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, NULL, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *table, *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock(); /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1; weight_total += weights[node]; } /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, NULL, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, NULL, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, NULL, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_array_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_array_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_array_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, NULL, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct iw_node_attr *node_attr; u8 *new; u8 *old; u8 weight = 0; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "")) weight = 0; else if (kstrtou8(buf, 0, &weight)) return -EINVAL; new = kzalloc(nr_node_ids, GFP_KERNEL); if (!new) return -ENOMEM; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); if (old) memcpy(new, old, nr_node_ids); new[node_attr->nid] = weight; rcu_assign_pointer(iw_table, new); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); return count; } static struct iw_node_attr **node_attrs; static void sysfs_wi_node_release(struct iw_node_attr *node_attr, struct kobject *parent) { if (!node_attr) return; sysfs_remove_file(parent, &node_attr->kobj_attr.attr); kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); } static void sysfs_wi_release(struct kobject *wi_kobj) { int i; for (i = 0; i < nr_node_ids; i++) sysfs_wi_node_release(node_attrs[i], wi_kobj); kobject_put(wi_kobj); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = sysfs_wi_release, }; static int add_weight_node(int nid, struct kobject *wi_kobj) { struct iw_node_attr *node_attr; char *name; node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); if (!node_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(node_attr); return -ENOMEM; } sysfs_attr_init(&node_attr->kobj_attr.attr); node_attr->kobj_attr.attr.name = name; node_attr->kobj_attr.attr.mode = 0644; node_attr->kobj_attr.show = node_show; node_attr->kobj_attr.store = node_store; node_attr->nid = nid; if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); pr_err("failed to add attribute to weighted_interleave\n"); return -ENOMEM; } node_attrs[nid] = node_attr; return 0; } static int add_weighted_interleave_group(struct kobject *root_kobj) { struct kobject *wi_kobj; int nid, err; wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!wi_kobj) return -ENOMEM; err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, "weighted_interleave"); if (err) { kfree(wi_kobj); return err; } for_each_node_state(nid, N_POSSIBLE) { err = add_weight_node(nid, wi_kobj); if (err) { pr_err("failed to add sysfs [node%d]\n", nid); break; } } if (err) kobject_put(wi_kobj); return 0; } static void mempolicy_kobj_release(struct kobject *kobj) { u8 *old; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); rcu_assign_pointer(iw_table, NULL); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); kfree(node_attrs); kfree(kobj); } static const struct kobj_type mempolicy_ktype = { .release = mempolicy_kobj_release }; static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); if (!mempolicy_kobj) { err = -ENOMEM; goto err_out; } node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), GFP_KERNEL); if (!node_attrs) { err = -ENOMEM; goto mempol_out; } err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, "mempolicy"); if (err) goto node_out; err = add_weighted_interleave_group(mempolicy_kobj); if (err) { pr_err("mempolicy sysfs structure failed to initialize\n"); kobject_put(mempolicy_kobj); return err; } return err; node_out: kfree(node_attrs); mempol_out: kfree(mempolicy_kobj); err_out: pr_err("failed to add mempolicy kobject to the system\n"); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ ifa = rtnl_net_dereference(net, ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { struct ns_common ns; struct mount * root; struct rb_root mounts; /* Protected by namespace_sem */ struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ union { struct rb_node mnt_node; /* Under ns->mounts */ struct list_head mnt_list; }; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); mnt->mnt.mnt_flags &= ~MNT_ONRB; rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns) { return __lookup_next_mnt_ns(mntns, false); } static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns) { return __lookup_next_mnt_ns(mntns, true); } static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } |
| 18 18 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains the procedures for the handling of select and poll * * Created for Linux based loosely upon Mathius Lattner's minix * patches by Peter MacDonald. Heavily edited by Linus. * * 4 February 1994 * COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS * flag set in its personality we do *not* modify the given timeout * parameter to reflect time remaining. * * 24 January 2000 * Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation * of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian). */ #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/rt.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/personality.h> /* for STICKY_TIMEOUTS */ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/freezer.h> #include <net/busy_poll.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> /* * Estimate expected accuracy in ns from a timeval. * * After quite a bit of churning around, we've settled on * a simple thing of taking 0.1% of the timeout as the * slack, with a cap of 100 msec. * "nice" tasks get a 0.5% slack instead. * * Consider this comment an open invitation to come up with even * better solutions.. */ #define MAX_SLACK (100 * NSEC_PER_MSEC) static long __estimate_accuracy(struct timespec64 *tv) { long slack; int divfactor = 1000; if (tv->tv_sec < 0) return 0; if (task_nice(current) > 0) divfactor = divfactor / 5; if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor)) return MAX_SLACK; slack = tv->tv_nsec / divfactor; slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); if (slack > MAX_SLACK) return MAX_SLACK; return slack; } u64 select_estimate_accuracy(struct timespec64 *tv) { u64 ret; struct timespec64 now; u64 slack = current->timer_slack_ns; if (slack == 0) return 0; ktime_get_ts64(&now); now = timespec64_sub(*tv, now); ret = __estimate_accuracy(&now); if (ret < slack) return slack; return ret; } struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; struct poll_table_entry entries[]; }; #define POLL_TABLE_FULL(table) \ ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table)) /* * Ok, Peter made a complicated, but straightforward multiple_wait() function. * I have rewritten this, taking some shortcuts: This code may not be easy to * follow, but it should be free of race-conditions, and it's practical. If you * understand what I'm doing here, then you understand how the linux * sleep/wakeup mechanism works. * * Two very simple procedures, poll_wait() and poll_freewait() make all the * work. poll_wait() is an inline-function defined in <linux/poll.h>, * as all select/poll functions have to call it to add an entry to the * poll table. */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p); void poll_initwait(struct poll_wqueues *pwq) { init_poll_funcptr(&pwq->pt, __pollwait); pwq->polling_task = current; pwq->triggered = 0; pwq->error = 0; pwq->table = NULL; pwq->inline_index = 0; } EXPORT_SYMBOL(poll_initwait); static void free_poll_entry(struct poll_table_entry *entry) { remove_wait_queue(entry->wait_address, &entry->wait); fput(entry->filp); } void poll_freewait(struct poll_wqueues *pwq) { struct poll_table_page * p = pwq->table; int i; for (i = 0; i < pwq->inline_index; i++) free_poll_entry(pwq->inline_entries + i); while (p) { struct poll_table_entry * entry; struct poll_table_page *old; entry = p->entry; do { entry--; free_poll_entry(entry); } while (entry > p->entries); old = p; p = p->next; free_page((unsigned long) old); } } EXPORT_SYMBOL(poll_freewait); static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) { struct poll_table_page *table = p->table; if (p->inline_index < N_INLINE_POLL_ENTRIES) return p->inline_entries + p->inline_index++; if (!table || POLL_TABLE_FULL(table)) { struct poll_table_page *new_table; new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL); if (!new_table) { p->error = -ENOMEM; return NULL; } new_table->entry = new_table->entries; new_table->next = table; p->table = new_table; table = new_table; } return table->entry++; } static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); /* * Although this function is called under waitqueue lock, LOCK * doesn't imply write barrier and the users expect write * barrier semantics on wakeup functions. The following * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() * and is paired with smp_store_mb() in poll_schedule_timeout. */ smp_wmb(); pwq->triggered = 1; /* * Perform the default wake up operation using a dummy * waitqueue. * * TODO: This is hacky but there currently is no interface to * pass in @sync. @sync is scheduled to be removed and once * that happens, wake_up_process() can be used directly. */ return default_wake_function(&dummy_wait, mode, sync, key); } static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; entry = container_of(wait, struct poll_table_entry, wait); if (key && !(key_to_poll(key) & entry->key)) return 0; return __pollwake(wait, mode, sync, key); } /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt); struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); } static int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack) { int rc = -EINTR; set_current_state(state); if (!pwq->triggered) rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * Prepare for the next iteration. * * The following smp_store_mb() serves two purposes. First, it's * the counterpart rmb of the wmb in pollwake() such that data * written before wake up is always visible after wake up. * Second, the full barrier guarantees that triggered clearing * doesn't pass event check of the next iteration. Note that * this problem doesn't exist for the first iteration as * add_wait_queue() has full barrier semantics. */ smp_store_mb(pwq->triggered, 0); return rc; } /** * poll_select_set_timeout - helper function to setup the timeout value * @to: pointer to timespec64 variable for the final timeout * @sec: seconds (from user space) * @nsec: nanoseconds (from user space) * * Note, we do not use a timespec for the user space value here, That * way we can use the function for timeval and compat interfaces as well. * * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. */ int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec) { struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec}; if (!timespec64_valid(&ts)) return -EINVAL; /* Optimize for the zero timeout value here */ if (!sec && !nsec) { to->tv_sec = to->tv_nsec = 0; } else { ktime_get_ts64(to); *to = timespec64_add_safe(*to, ts); } return 0; } enum poll_time_type { PT_TIMEVAL = 0, PT_OLD_TIMEVAL = 1, PT_TIMESPEC = 2, PT_OLD_TIMESPEC = 3, }; static int poll_select_finish(struct timespec64 *end_time, void __user *p, enum poll_time_type pt_type, int ret) { struct timespec64 rts; restore_saved_sigmask_unless(ret == -ERESTARTNOHAND); if (!p) return ret; if (current->personality & STICKY_TIMEOUTS) goto sticky; /* No update for zero timeout */ if (!end_time->tv_sec && !end_time->tv_nsec) return ret; ktime_get_ts64(&rts); rts = timespec64_sub(*end_time, rts); if (rts.tv_sec < 0) rts.tv_sec = rts.tv_nsec = 0; switch (pt_type) { case PT_TIMEVAL: { struct __kernel_old_timeval rtv; if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec)) memset(&rtv, 0, sizeof(rtv)); rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_OLD_TIMEVAL: { struct old_timeval32 rtv; rtv.tv_sec = rts.tv_sec; rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } break; case PT_TIMESPEC: if (!put_timespec64(&rts, p)) return ret; break; case PT_OLD_TIMESPEC: if (!put_old_timespec32(&rts, p)) return ret; break; default: BUG(); } /* * If an application puts its timeval in read-only memory, we * don't want the Linux-specific update to the timeval to * cause a fault after the select has completed * successfully. However, because we're not updating the * timeval, we can't restart the system call. */ sticky: if (ret == -ERESTARTNOHAND) ret = -EINTR; return ret; } /* * Scalable version of the fd_set. */ typedef struct { unsigned long *in, *out, *ex; unsigned long *res_in, *res_out, *res_ex; } fd_set_bits; /* * How many longwords for "nr" bits? */ #define FDS_BITPERLONG (8*sizeof(long)) #define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG) #define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long)) /* * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned. */ static inline int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { nr = FDS_BYTES(nr); if (ufdset) return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0; memset(fdset, 0, nr); return 0; } static inline unsigned long __must_check set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset) { if (ufdset) return __copy_to_user(ufdset, fdset, FDS_BYTES(nr)); return 0; } static inline void zero_fd_set(unsigned long nr, unsigned long *fdset) { memset(fdset, 0, FDS_BYTES(nr)); } #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) #define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n)) static int max_select_fd(unsigned long n, fd_set_bits *fds) { unsigned long *open_fds; unsigned long set; int max; struct fdtable *fdt; /* handle last in-complete long-word first */ set = ~(~0UL << (n & (BITS_PER_LONG-1))); n /= BITS_PER_LONG; fdt = files_fdtable(current->files); open_fds = fdt->open_fds + n; max = 0; if (set) { set &= BITS(fds, n); if (set) { if (!(set & ~*open_fds)) goto get_max; return -EBADF; } } while (n) { open_fds--; n--; set = BITS(fds, n); if (!set) continue; if (set & ~*open_fds) return -EBADF; if (max) continue; get_max: do { max++; set >>= 1; } while (set); max += n * BITS_PER_LONG; } return max; } #define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR |\ EPOLLNVAL) #define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR |\ EPOLLNVAL) #define POLLEX_SET (EPOLLPRI | EPOLLNVAL) static inline __poll_t select_poll_one(int fd, poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, __poll_t ll_flag) { CLASS(fd, f)(fd); if (fd_empty(f)) return EPOLLNVAL; wait->_key = POLLEX_SET | ll_flag; if (in & bit) wait->_key |= POLLIN_SET; if (out & bit) wait->_key |= POLLOUT_SET; return vfs_poll(fd_file(f), wait); } static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; rcu_read_lock(); retval = max_select_fd(n, fds); rcu_read_unlock(); if (retval < 0) return retval; n = retval; poll_initwait(&table); wait = &table.pt; if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; bool can_busy_loop = false; inp = fds->in; outp = fds->out; exp = fds->ex; rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex; for (i = 0; i < n; ++rinp, ++routp, ++rexp) { unsigned long in, out, ex, all_bits, bit = 1, j; unsigned long res_in = 0, res_out = 0, res_ex = 0; __poll_t mask; in = *inp++; out = *outp++; ex = *exp++; all_bits = in | out | ex; if (all_bits == 0) { i += BITS_PER_LONG; continue; } for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) { if (i >= n) break; if (!(bit & all_bits)) continue; mask = select_poll_one(i, wait, in, out, bit, busy_flag); if ((mask & POLLIN_SET) && (in & bit)) { res_in |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |= bit; retval++; wait->_qproc = NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |= bit; retval++; wait->_qproc = NULL; } /* got something, stop busy polling */ if (retval) { can_busy_loop = false; busy_flag = 0; /* * only remember a returned * POLL_BUSY_LOOP if we asked for it */ } else if (busy_flag & mask) can_busy_loop = true; } if (res_in) *rinp = res_in; if (res_out) *routp = res_out; if (res_ex) *rexp = res_ex; cond_resched(); } wait->_qproc = NULL; if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } poll_freewait(&table); return retval; } /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int ret, max_fds; size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; if (size > (SIZE_MAX / 6)) goto out_nofds; alloc_size = 6 * size; bits = kvmalloc(alloc_size, GFP_KERNEL); if (!bits) goto out_nofds; } fds.in = bits; fds.out = bits + size; fds.ex = bits + 2*size; fds.res_in = bits + 3*size; fds.res_out = bits + 4*size; fds.res_ex = bits + 5*size; if ((ret = get_fd_set(n, inp, fds.in)) || (ret = get_fd_set(n, outp, fds.out)) || (ret = get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (set_fd_set(n, inp, fds.res_in) || set_fd_set(n, outp, fds.res_out) || set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kvfree(bits); out_nofds: return ret; } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; struct __kernel_old_timeval tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret); } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, void __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } /* * Most architectures can't handle 7-argument syscalls. So we provide a * 6-argument version where the sixth argument is a pointer to a structure * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ struct sigset_argpack { sigset_t __user *p; size_t size; }; static inline int get_sigset_argpack(struct sigset_argpack *to, struct sigset_argpack __user *from) { // the path is hot enough for overhead of copy_from_user() to matter if (from) { if (can_do_masked_user_access()) from = masked_user_access_begin(from); else if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, outp, fd_set __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct sigset_argpack x = {NULL, 0}; if (get_sigset_argpack(&x, sig)) return -EFAULT; return do_pselect(n, inp, outp, exp, tsp, x.p, x.size, PT_OLD_TIMESPEC); } #endif #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) { struct sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return kern_select(a.n, a.inp, a.outp, a.exp, a.tvp); } #endif struct poll_list { struct poll_list *next; unsigned int len; struct pollfd entries[] __counted_by(len); }; #define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd)) /* * Fish for pollable events on the pollfd->fd file descriptor. We're only * interested in events matching the pollfd->events mask, and the result * matching that mask is both recorded in pollfd->revents and returned. The * pwait poll_table will be used by the fd-provided poll handler for waiting, * if pwait->_qproc is non-NULL. */ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, bool *can_busy_poll, __poll_t busy_flag) { int fd = pollfd->fd; __poll_t mask, filter; if (fd < 0) return 0; CLASS(fd, f)(fd); if (fd_empty(f)) return EPOLLNVAL; /* userland u16 ->events contains POLL... bitmap */ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP; pwait->_key = filter | busy_flag; mask = vfs_poll(fd_file(f), pwait); if (mask & busy_flag) *can_busy_poll = true; return mask & filter; /* Mask out unneeded events. */ } static int do_poll(struct poll_list *list, struct poll_wqueues *wait, struct timespec64 *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; int timed_out = 0, count = 0; u64 slack = 0; __poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0; unsigned long busy_start = 0; /* Optimise the no-wait case */ if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt->_qproc = NULL; timed_out = 1; } if (end_time && !timed_out) slack = select_estimate_accuracy(end_time); for (;;) { struct poll_list *walk; bool can_busy_loop = false; for (walk = list; walk != NULL; walk = walk->next) { struct pollfd * pfd, * pfd_end; pfd = walk->entries; pfd_end = pfd + walk->len; for (; pfd != pfd_end; pfd++) { __poll_t mask; /* * Fish for events. If we found one, record it * and kill poll_table->_qproc, so we don't * needlessly register any other waiters after * this. They'll get immediately deregistered * when we break out and return. */ mask = do_pollfd(pfd, pt, &can_busy_loop, busy_flag); pfd->revents = mangle_poll(mask); if (mask) { count++; pt->_qproc = NULL; /* found something, stop busy polling */ busy_flag = 0; can_busy_loop = false; } } } /* * All waiters have already been registered, so don't provide * a poll_table->_qproc to them on the next loop iteration. */ pt->_qproc = NULL; if (!count) { count = wait->error; if (signal_pending(current)) count = -ERESTARTNOHAND; } if (count || timed_out) break; /* only if found POLL_BUSY_LOOP sockets && not out of time */ if (can_busy_loop && !need_resched()) { if (!busy_start) { busy_start = busy_loop_current_time(); continue; } if (!busy_loop_timeout(busy_start)) continue; } busy_flag = 0; /* * If this is the first loop and we have a timeout * given, then we convert to ktime_t and set the to * pointer to the expiry value. */ if (end_time && !to) { expire = timespec64_to_ktime(*end_time); to = &expire; } if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack)) timed_out = 1; } return count; } #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; struct poll_list *const head = (struct poll_list *)stack_pps; struct poll_list *walk = head; unsigned int todo = nfds; unsigned int len; if (nfds > rlimit(RLIMIT_NOFILE)) return -EINVAL; len = min_t(unsigned int, nfds, N_STACK_PPS); for (;;) { walk->next = NULL; walk->len = len; if (!len) break; if (copy_from_user(walk->entries, ufds + nfds-todo, sizeof(struct pollfd) * walk->len)) goto out_fds; if (walk->len >= todo) break; todo -= walk->len; len = min(todo, POLLFD_PER_PAGE); walk = walk->next = kmalloc(struct_size(walk, entries, len), GFP_KERNEL); if (!walk) { err = -ENOMEM; goto out_fds; } } poll_initwait(&table); fdcount = do_poll(head, &table, end_time); poll_freewait(&table); if (!user_write_access_begin(ufds, nfds * sizeof(*ufds))) goto out_fds; for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; unsigned int j; for (j = walk->len; j; fds++, ufds++, j--) unsafe_put_user(fds->revents, &ufds->revents, Efault); } user_write_access_end(); err = fdcount; out_fds: walk = head->next; while (walk) { struct poll_list *pos = walk; walk = walk->next; kfree(pos); } return err; Efault: user_write_access_end(); err = -EFAULT; goto out_fds; } static long do_restart_poll(struct restart_block *restart_block) { struct pollfd __user *ufds = restart_block->poll.ufds; int nfds = restart_block->poll.nfds; struct timespec64 *to = NULL, end_time; int ret; if (restart_block->poll.has_timeout) { end_time.tv_sec = restart_block->poll.tv_sec; end_time.tv_nsec = restart_block->poll.tv_nsec; to = &end_time; } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) ret = set_restart_fn(restart_block, do_restart_poll); return ret; } SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout_msecs) { struct timespec64 end_time, *to = NULL; int ret; if (timeout_msecs >= 0) { to = &end_time; poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } ret = do_sys_poll(ufds, nfds, to); if (ret == -ERESTARTNOHAND) { struct restart_block *restart_block; restart_block = ¤t->restart_block; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; if (timeout_msecs >= 0) { restart_block->poll.tv_sec = end_time.tv_sec; restart_block->poll.tv_nsec = end_time.tv_nsec; restart_block->poll.has_timeout = 1; } else restart_block->poll.has_timeout = 0; ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif #ifdef CONFIG_COMPAT #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (ufdset) { return compat_get_bitmap(fdset, ufdset, nr); } else { zero_fd_set(nr, fdset); return 0; } } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { if (!ufdset) return 0; return compat_put_bitmap(ufdset, fdset, nr); } /* * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ /* * We can actually return ERESTARTSYS instead of EINTR, but I'd * like to be certain this leads to no problems. So I return * EINTR just for safety. * * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ static int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct timespec64 *end_time) { fd_set_bits fds; void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); max_fds = fdt->max_fds; rcu_read_unlock(); if (n > max_fds) n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ size = FDS_BYTES(n); bits = stack_fds; if (size > sizeof(stack_fds) / 6) { bits = kmalloc_array(6, size, GFP_KERNEL); ret = -ENOMEM; if (!bits) goto out_nofds; } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); fds.res_in = (unsigned long *) (bits + 3*size); fds.res_out = (unsigned long *) (bits + 4*size); fds.res_ex = (unsigned long *) (bits + 5*size); if ((ret = compat_get_fd_set(n, inp, fds.in)) || (ret = compat_get_fd_set(n, outp, fds.out)) || (ret = compat_get_fd_set(n, exp, fds.ex))) goto out; zero_fd_set(n, fds.res_in); zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); ret = do_select(n, &fds, end_time); if (ret < 0) goto out; if (!ret) { ret = -ERESTARTNOHAND; if (signal_pending(current)) goto out; ret = 0; } if (compat_set_fd_set(n, inp, fds.res_in) || compat_set_fd_set(n, outp, fds.res_out) || compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: if (bits != stack_fds) kfree(bits); out_nofds: return ret; } static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; struct old_timeval32 tv; int ret; if (tvp) { if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; } ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret); } COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } struct compat_sel_arg_struct { compat_ulong_t n; compat_uptr_t inp; compat_uptr_t outp; compat_uptr_t exp; compat_uptr_t tvp; }; COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { struct compat_sel_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; return do_compat_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), compat_ptr(a.exp), compat_ptr(a.tvp)); } static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, void __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize, enum poll_time_type type) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { switch (type) { case PT_OLD_TIMESPEC: if (get_old_timespec32(&ts, tsp)) return -EFAULT; break; case PT_TIMESPEC: if (get_timespec64(&ts, tsp)) return -EFAULT; break; default: BUG(); } to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); return poll_select_finish(&end_time, tsp, type, ret); } struct compat_sigset_argpack { compat_uptr_t p; compat_size_t size; }; static inline int get_compat_sigset_argpack(struct compat_sigset_argpack *to, struct compat_sigset_argpack __user *from) { if (from) { if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(to->p, &from->p, Efault); unsafe_get_user(to->size, &from->size, Efault); user_read_access_end(); } return 0; Efault: user_access_end(); return -EFAULT; } COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct __kernel_timespec __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_TIMESPEC); } #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { struct compat_sigset_argpack x = {0, 0}; if (get_compat_sigset_argpack(&x, sig)) return -EFAULT; return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(x.p), x.size, PT_OLD_TIMESPEC); } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret); } #endif /* New compat syscall for 64 bit time_t*/ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, unsigned int, nfds, struct __kernel_timespec __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, end_time, *to = NULL; int ret; if (tsp) { if (get_timespec64(&ts, tsp)) return -EFAULT; to = &end_time; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } ret = set_compat_user_sigmask(sigmask, sigsetsize); if (ret) return ret; ret = do_sys_poll(ufds, nfds, to); return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Type definitions for the multi-level security (MLS) policy. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. */ #ifndef _SS_MLS_TYPES_H_ #define _SS_MLS_TYPES_H_ #include "security.h" #include "ebitmap.h" struct mls_level { u32 sens; /* sensitivity */ struct ebitmap cat; /* category set */ }; struct mls_range { struct mls_level level[2]; /* low == level[0], high == level[1] */ }; static inline int mls_level_eq(const struct mls_level *l1, const struct mls_level *l2) { return ((l1->sens == l2->sens) && ebitmap_cmp(&l1->cat, &l2->cat)); } static inline int mls_level_dom(const struct mls_level *l1, const struct mls_level *l2) { return ((l1->sens >= l2->sens) && ebitmap_contains(&l1->cat, &l2->cat, 0)); } #define mls_level_incomp(l1, l2) \ (!mls_level_dom((l1), (l2)) && !mls_level_dom((l2), (l1))) #define mls_level_between(l1, l2, l3) \ (mls_level_dom((l1), (l2)) && mls_level_dom((l3), (l1))) #define mls_range_contains(r1, r2) \ (mls_level_dom(&(r2).level[0], &(r1).level[0]) && \ mls_level_dom(&(r1).level[1], &(r2).level[1])) #endif /* _SS_MLS_TYPES_H_ */ |
| 486 486 486 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Procedures for maintaining information about logical memory blocks. * * Peter Bergner, IBM Corp. June 2001. * Copyright (C) 2001 Peter Bergner. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/bitops.h> #include <linux/poison.h> #include <linux/pfn.h> #include <linux/debugfs.h> #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> #include <asm/sections.h> #include <linux/io.h> #include "internal.h" #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 #ifndef INIT_MEMBLOCK_RESERVED_REGIONS # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif #ifndef INIT_MEMBLOCK_MEMORY_REGIONS #define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS #endif /** * DOC: memblock overview * * Memblock is a method of managing memory regions during the early * boot period when the usual kernel memory allocators are not up and * running. * * Memblock views the system memory as collections of contiguous * regions. There are several types of these collections: * * * ``memory`` - describes the physical memory available to the * kernel; this may differ from the actual physical memory installed * in the system, for instance when the memory is restricted with * ``mem=`` command line parameter * * ``reserved`` - describes the regions that were allocated * * ``physmem`` - describes the actual physical memory available during * boot regardless of the possible restrictions and memory hot(un)plug; * the ``physmem`` type is only available on some architectures. * * Each region is represented by struct memblock_region that * defines the region extents, its attributes and NUMA node id on NUMA * systems. Every memory type is described by the struct memblock_type * which contains an array of memory regions along with * the allocator metadata. The "memory" and "reserved" types are nicely * wrapped with struct memblock. This structure is statically * initialized at build time. The region arrays are initially sized to * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not * overlap with areas that should be reserved, for example initrd. * * The early architecture setup should tell memblock what the physical * memory layout is by using memblock_add() or memblock_add_node() * functions. The first function does not assign the region to a NUMA * node and it is appropriate for UMA systems. Yet, it is possible to * use it on NUMA systems as well and assign the region to a NUMA node * later in the setup process using memblock_set_node(). The * memblock_add_node() performs such an assignment directly. * * Once memblock is setup the memory can be allocated using one of the * API variants: * * * memblock_phys_alloc*() - these functions return the **physical** * address of the allocated memory * * memblock_alloc*() - these functions return the **virtual** address * of the allocated memory. * * Note, that both API variants use implicit assumptions about allowed * memory ranges and the fallback methods. Consult the documentation * of memblock_alloc_internal() and memblock_alloc_range_nid() * functions for more elaborate description. * * As the system boot progresses, the architecture specific mem_init() * function frees all the memory to the buddy page allocator. * * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the * memblock data structures (except "physmem") will be discarded after the * system initialization completes. */ #ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; #endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP struct memblock_type physmem = { .regions = memblock_physmem_init_regions, .max = INIT_PHYSMEM_REGIONS, .name = "physmem", }; #endif /* * keep a pointer to &memblock.memory in the text section to use it in * __next_mem_range() and its helpers. * For architectures that do not keep memblock data after init, this * pointer will be reset to NULL at memblock_discard() */ static __refdata struct memblock_type *memblock_memory = &memblock.memory; #define for_each_memblock_type(i, memblock_type, rgn) \ for (i = 0, rgn = &memblock_type->regions[0]; \ i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) #define memblock_dbg(fmt, ...) \ do { \ if (memblock_debug) \ pr_info(fmt, ##__VA_ARGS__); \ } while (0) static int memblock_debug __initdata_memblock; static bool system_has_some_mirror __initdata_memblock; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock; static int memblock_reserved_in_slab __initdata_memblock; bool __init_memblock memblock_has_mirror(void) { return system_has_some_mirror; } static enum memblock_flags __init_memblock choose_memblock_flags(void) { return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { return *size = min(*size, PHYS_ADDR_MAX - base); } /* * Address comparison utilities */ unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } bool __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { unsigned long i; memblock_cap_size(base, &size); for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) return true; return false; } /** * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); cand = round_up(this_start, align); if (cand < this_end && this_end - cand >= size) return cand; } return 0; } /** * __memblock_find_range_top_down - find free area utility, in top-down * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area top-down. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); if (this_end < size) continue; cand = round_down(this_end - size, align); if (cand >= this_start) return cand; } return 0; } /** * memblock_find_in_range_node - find free area in given range and node * @size: size of free area to find * @align: alignment of free area to find * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Find @size free area aligned to @align in the specified range and node. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, enum memblock_flags flags) { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); if (memblock_bottom_up()) return __memblock_find_range_bottom_up(start, end, size, align, nid, flags); else return __memblock_find_range_top_down(start, end, size, align, nid, flags); } /** * memblock_find_in_range - find free area in given range * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * * Find @size free area aligned to @align in the specified range. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { phys_addr_t ret; enum memblock_flags flags = choose_memblock_flags(); again: ret = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (!ret && (flags & MEMBLOCK_MIRROR)) { pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); flags &= ~MEMBLOCK_MIRROR; goto again; } return ret; } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; memmove(&type->regions[r], &type->regions[r + 1], (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ if (type->cnt == 0) { WARN_ON(type->total_size != 0); type->regions[0].base = 0; type->regions[0].size = 0; type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } #ifndef CONFIG_ARCH_KEEP_MEMBLOCK /** * memblock_discard - discard memory and reserved arrays if they were allocated */ void __init memblock_discard(void) { phys_addr_t addr, size; if (memblock.reserved.regions != memblock_reserved_init_regions) { addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); if (memblock_reserved_in_slab) kfree(memblock.reserved.regions); else memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); if (memblock_memory_in_slab) kfree(memblock.memory.regions); else memblock_free_late(addr, size); } memblock_memory = NULL; } #endif /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled * @new_area_start: starting address of memory range to avoid overlap with * @new_area_size: size of memory range to avoid overlap with * * Double the size of the @type regions array. If memblock is being used to * allocate memory for a new reserved regions array and there is a previously * allocated memory range [@new_area_start, @new_area_start + @new_area_size] * waiting to be reserved, ensure the memory used by the new array does * not overlap. * * Return: * 0 on success, -1 on failure. */ static int __init_memblock memblock_double_array(struct memblock_type *type, phys_addr_t new_area_start, phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr, new_end; int use_slab = slab_is_available(); int *in_slab; /* We don't allow resizing until we know about the reserved regions * of memory that aren't suitable for allocation */ if (!memblock_can_resize) panic("memblock: cannot resize %s array\n", type->name); /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; /* * We need to allocated new one align to PAGE_SIZE, * so we can free them completely later. */ old_alloc_size = PAGE_ALIGN(old_size); new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) in_slab = &memblock_memory_in_slab; else in_slab = &memblock_reserved_in_slab; /* Try to find some space for it */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { /* only exclude range when trying to double reserved.regions */ if (type != &memblock.reserved) new_area_start = new_area_size = 0; addr = memblock_find_in_range(new_area_start + new_area_size, memblock.current_limit, new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : NULL; } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", type->name, type->max, type->max * 2); return -1; } new_end = addr + new_size - 1; memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]", type->name, type->max * 2, &addr, &new_end); /* * Found space, we now need to move the array over before we add the * reserved region since it may be our reserved array itself that is * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); old_array = type->regions; type->regions = new_array; type->max <<= 1; /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we * needn't do it */ if (!use_slab) BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; return 0; } /** * memblock_merge_regions - merge neighboring compatible regions * @type: memblock type to scan * @start_rgn: start scanning from (@start_rgn - 1) * @end_rgn: end scanning at (@end_rgn - 1) * Scan @type and merge neighboring compatible regions in [@start_rgn - 1, @end_rgn) */ static void __init_memblock memblock_merge_regions(struct memblock_type *type, unsigned long start_rgn, unsigned long end_rgn) { int i = 0; if (start_rgn) i = start_rgn - 1; end_rgn = min(end_rgn, type->cnt - 1); while (i < end_rgn) { struct memblock_region *this = &type->regions[i]; struct memblock_region *next = &type->regions[i + 1]; if (this->base + this->size != next->base || memblock_get_region_node(this) != memblock_get_region_node(next) || this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; } this->size += next->size; /* move forward from next + 1, index of which is i + 2 */ memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next)); type->cnt--; end_rgn--; } } /** * memblock_insert_region - insert new memblock region * @type: memblock type to insert into * @idx: index for the insertion point * @base: base address of the new region * @size: size of the new region * @nid: node id of the new region * @flags: flags of the new region * * Insert new memblock region [@base, @base + @size) into @type at @idx. * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { struct memblock_region *rgn = &type->regions[idx]; BUG_ON(type->cnt >= type->max); memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; } /** * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already * existing regions. @type is guaranteed to be minimal (all neighbouring * compatible regions are merged) after the addition. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); int idx, nr_new, start_rgn = -1, end_rgn; struct memblock_region *rgn; if (!size) return 0; /* special case for empty array */ if (type->regions[0].size == 0) { WARN_ON(type->cnt != 0 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; type->cnt = 1; return 0; } /* * The worst case is when new range overlaps all existing regions, * then we'll need type->cnt + 1 empty regions in @type. So if * type->cnt * 2 + 1 is less than or equal to type->max, we know * that there is enough empty regions in @type, and we can insert * regions directly. */ if (type->cnt * 2 + 1 <= type->max) insert = true; repeat: /* * The following is executed twice. Once with %false @insert and * then with %true. The first counts the number of regions needed * to accommodate the new area. The second actually inserts them. */ base = obase; nr_new = 0; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; /* * @rgn overlaps. If it separates the lower part of new * area, insert that portion. */ if (rbase > base) { #ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } } /* area below @rend is dealt with, forget about it */ base = min(rend, end); } /* insert the remaining portion */ if (base < end) { nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx, base, end - base, nid, flags); } } if (!nr_new) return 0; /* * If this was the first round, resize array and repeat for actual * insertions; otherwise, merge and return. */ if (!insert) { while (type->cnt + nr_new > type->max) if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; } else { memblock_merge_regions(type, start_rgn, end_rgn); return 0; } } /** * memblock_add_node - add new memblock region within a NUMA node * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, &base, &end, nid, flags, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** * memblock_add - add new memblock region * @base: base address of the new region * @size: size of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } /** * memblock_validate_numa_coverage - check if amount of memory with * no node ID assigned is less than a threshold * @threshold_bytes: maximal memory size that can have unassigned node * ID (in bytes). * * A buggy firmware may report memory that does not belong to any node. * Check if amount of such memory is below @threshold_bytes. * * Return: true on success, false on failure. */ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) { unsigned long nr_pages = 0; unsigned long start_pfn, end_pfn, mem_size_mb; int nid, i; /* calculate lose page */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (!numa_valid_node(nid)) nr_pages += end_pfn - start_pfn; } if ((nr_pages << PAGE_SHIFT) > threshold_bytes) { mem_size_mb = memblock_phys_mem_size() >> 20; pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); return false; } return true; } /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for * @base: base of range to isolate * @size: size of range to isolate * @start_rgn: out parameter for the start of isolated region * @end_rgn: out parameter for the end of isolated region * * Walk @type and ensure that regions don't cross the boundaries defined by * [@base, @base + @size). Crossing regions are split at the boundaries, * which may create at most two more regions. The index of the first * region inside the range is returned in *@start_rgn and the index of the * first region after the range is returned in *@end_rgn. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_isolate_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); int idx; struct memblock_region *rgn; *start_rgn = *end_rgn = 0; if (!size) return 0; /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; if (rbase < base) { /* * @rgn intersects from below. Split and continue * to process the next region - the new top half. */ rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the * current region - the new bottom half. */ rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) *start_rgn = idx; *end_rgn = idx + 1; } } return 0; } static int __init_memblock memblock_remove_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = end_rgn - 1; i >= start_rgn; i--) memblock_remove_region(type, i); return 0; } int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_remove_range(&memblock.memory, base, size); } /** * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); } /** * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_phys_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); } #endif /** * memblock_setclr_flag - set or clear flag for a memory region * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag * @flag: the flag to update * * This function isolates region [@base, @base + @size), and sets/clears flag * * Return: 0 on success, -errno on failure. */ static int __init_memblock memblock_setclr_flag(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int set, int flag) { int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) { struct memblock_region *r = &type->regions[i]; if (set) r->flags |= flag; else r->flags &= ~flag; } memblock_merge_regions(type, start_rgn, end_rgn); return 0; } /** * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { if (!mirrored_kernelcore) return 0; system_has_some_mirror = true; return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. * @base: the base phys addr of the region * @size: the size of the region * * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the * direct mapping of the physical memory. These regions will still be * covered by the memory map. The struct page representing NOMAP memory * frames in the memory map will be PageReserved() * * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from * memblock, the caller must inform kmemleak to ignore that memory * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); } /** * memblock_reserved_mark_noinit - Mark a reserved memory region with flag * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized * for this region. * @base: the base phys addr of the region * @size: the size of the region * * struct pages will not be initialized for reserved memory regions marked with * %MEMBLOCK_RSRV_NOINIT. * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.reserved, base, size, 1, MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, struct memblock_region *m, int nid, int flags) { int m_nid = memblock_get_region_node(m); /* we never skip regions when iterating memblock.reserved or physmem */ if (type != memblock_memory) return false; /* only memory regions are associated with nodes, check it */ if (numa_valid_node(nid) && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) return true; /* skip nomap memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; /* skip driver-managed memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) return true; return false; } /** * __next_mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of * *@idx contains index into type_a and the upper 32bit indexes the * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) * * The upper 32bit indexes the following regions. * * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) * * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; for (; idx_a < type_a->cnt; idx_a++) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b < type_b->cnt + 1; idx_b++) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; /* * The region which ends first is * advanced for the next iteration. */ if (m_end <= r_end) idx_a++; else idx_b++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /** * __next_mem_range_rev - generic next function for for_each_*_range_rev() * * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Finds the next range from type_a which is not marked as unsuitable * in type_b. * * Reverse of __next_mem_range(). */ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; if (type_b != NULL) idx_b = type_b->cnt; else idx_b = 0; } for (; idx_a >= 0; idx_a--) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b >= 0; idx_b--) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ if (m_end > r_start) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; if (m_start >= r_start) idx_a--; else idx_b--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /* * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid) { struct memblock_type *type = &memblock.memory; struct memblock_region *r; int r_nid; while (++*idx < type->cnt) { r = &type->regions[*idx]; r_nid = memblock_get_region_node(r); if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; if (!numa_valid_node(nid) || nid == r_nid) break; } if (*idx >= type->cnt) { *idx = -1; return; } if (out_start_pfn) *out_start_pfn = PFN_UP(r->base); if (out_end_pfn) *out_end_pfn = PFN_DOWN(r->base + r->size); if (out_nid) *out_nid = r_nid; } /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for * @type: memblock type to set node ID for * @nid: node ID to set * * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. * Regions which cross the area boundaries are split as necessary. * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { #ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type, start_rgn, end_rgn); #endif return 0; } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() * * @idx: pointer to u64 loop variable * @zone: zone in which all of the memory blocks reside * @out_spfn: ptr to ulong for start pfn of the range, can be %NULL * @out_epfn: ptr to ulong for end pfn of the range, can be %NULL * * This function is meant to be a zone/pfn specific wrapper for the * for_each_mem_range type iterators. Specifically they are used in the * deferred memory init routines and as such we were duplicating much of * this logic throughout the code. So instead of having it in multiple * locations it seemed like it would make more sense to centralize this to * one new iterator that does everything they need. */ void __init_memblock __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn) { int zone_nid = zone_to_nid(zone); phys_addr_t spa, epa; __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); while (*idx != U64_MAX) { unsigned long epfn = PFN_DOWN(epa); unsigned long spfn = PFN_UP(spa); /* * Verify the end is at least past the start of the zone and * that we have at least one PFN to initialize. */ if (zone->zone_start_pfn < epfn && spfn < epfn) { /* if we went too far just stop searching */ if (zone_end_pfn(zone) <= spfn) { *idx = U64_MAX; break; } if (out_spfn) *out_spfn = max(zone->zone_start_pfn, spfn); if (out_epfn) *out_epfn = min(zone_end_pfn(zone), epfn); return; } __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); } /* signal end of iteration */ if (out_spfn) *out_spfn = ULONG_MAX; if (out_epfn) *out_epfn = 0; } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** * memblock_alloc_range_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. * * If the specified node can not hold the requested memory and @exact_nid * is false, the allocation falls back to any node in the system. * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any * memory region. * * In addition, function using kmemleak_alloc_phys for allocated boot * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. */ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) { void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid); return vaddr ? virt_to_phys(vaddr) : 0; } if (!align) { /* Can't use WARNs this early in boot on powerpc */ dump_stack(); align = SMP_CACHE_BYTES; } again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) goto done; if (numa_valid_node(nid) && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (found && !memblock_reserve(found, size)) goto done; } if (flags & MEMBLOCK_MIRROR) { flags &= ~MEMBLOCK_MIRROR; pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); goto again; } return 0; done: /* * Skip kmemleak for those places like kasan_init() and * early_pgtable_alloc() due to high volume. */ if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * Memblock allocated blocks are never reported as * leaks. This is because many of these blocks are * only referred via the physical address which is * not looked up by kmemleak. */ kmemleak_alloc_phys(found, size, 0); /* * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP, * require memory to be accepted before it can be used by the * guest. * * Accept the memory of the allocated buffer. */ accept_memory(found, size); return found; } /** * memblock_phys_alloc_range - allocate a memory block inside specified range * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (physical address) * @end: the upper bound of the memory region to allocate (physical address) * * Allocate @size bytes in the between @start and @end. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end) { memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, &start, &end, (void *)_RET_IP_); return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, false); } /** * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Allocates memory block from the specified NUMA node. If the node * has no available memory, attempts to allocated from any node in the * system. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. * * The @min_addr limit is dropped if it can not be satisfied and the allocation * will fall back to memory below @min_addr. Other constraints, such * as node and mirrored memory will be handled again in * memblock_alloc_range_nid(). * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid, bool exact_nid) { phys_addr_t alloc; if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, exact_nid); if (!alloc) return NULL; return phys_to_virt(alloc); } /** * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node * without zeroing memory * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_exact_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, true); } /** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory, does not panic if request * cannot be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); } /** * memblock_alloc_try_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. This function zeroes the allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { void *ptr; memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); return ptr; } /** * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * This is only useful when the memblock allocator has already been torn * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); cursor = PFN_UP(base); end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } /* * Remaining API functions */ phys_addr_t __init_memblock memblock_phys_mem_size(void) { return memblock.memory.total_size; } phys_addr_t __init_memblock memblock_reserved_size(void) { return memblock.reserved.total_size; } /** * memblock_estimated_nr_free_pages - return estimated number of free pages * from memblock point of view * * During bootup, subsystems might need a rough estimate of the number of free * pages in the whole system, before precise numbers are available from the * buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers * obtained from the buddy might be very imprecise during bootup. * * Return: * An estimated number of free pages from memblock point of view. */ unsigned long __init memblock_estimated_nr_free_pages(void) { return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); } /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { return memblock.memory.regions[0].base; } phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = PHYS_ADDR_MAX; struct memblock_region *r; /* * translate the memory @limit size into the max address within one of * the memory memblock regions, if the @limit exceeds the total size * of those regions, max_addr will keep original value PHYS_ADDR_MAX */ for_each_mem_region(r) { if (limit <= r->size) { max_addr = r->base + limit; break; } limit -= r->size; } return max_addr; } void __init memblock_enforce_memory_limit(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, PHYS_ADDR_MAX); memblock_remove_range(&memblock.reserved, max_addr, PHYS_ADDR_MAX); } void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; if (!size) return; if (!memblock_memory->total_size) { pr_warn("%s: No memory registered yet\n", __func__); return; } ret = memblock_isolate_range(&memblock.memory, base, size, &start_rgn, &end_rgn); if (ret) return; /* remove all the MAP regions */ for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); for (i = start_rgn - 1; i >= 0; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); /* truncate the reserved regions */ memblock_remove_range(&memblock.reserved, 0, base); memblock_remove_range(&memblock.reserved, base + size, PHYS_ADDR_MAX); } void __init memblock_mem_limit_remove_map(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; memblock_cap_memory_range(0, max_addr); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; do { unsigned int mid = (right + left) / 2; if (addr < type->regions[mid].base) right = mid; else if (addr >= (type->regions[mid].base + type->regions[mid].size)) left = mid + 1; else return mid; } while (left < right); return -1; } bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } bool __init_memblock memblock_is_map_memory(phys_addr_t addr) { int i = memblock_search(&memblock.memory, addr); if (i == -1) return false; return !memblock_is_nomap(&memblock.memory.regions[i]); } int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { struct memblock_type *type = &memblock.memory; int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) return NUMA_NO_NODE; *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); return memblock_get_region_node(&type->regions[mid]); } /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) is a subset of a memory block. * * Return: * 0 if false, non-zero if true */ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) return false; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } /** * memblock_is_region_reserved - check if a region intersects reserved memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) intersects a reserved * memory block. * * Return: * True if they intersect, false if not. */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { return memblock_overlaps_region(&memblock.reserved, base, size); } void __init_memblock memblock_trim_memory(phys_addr_t align) { phys_addr_t start, end, orig_start, orig_end; struct memblock_region *r; for_each_mem_region(r) { orig_start = r->base; orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); if (start == orig_start && end == orig_end) continue; if (start < end) { r->base = start; r->size = end - start; } else { memblock_remove_region(&memblock.memory, r - memblock.memory.regions); r--; } } } void __init_memblock memblock_set_current_limit(phys_addr_t limit) { memblock.current_limit = limit; } phys_addr_t __init_memblock memblock_get_current_limit(void) { return memblock.current_limit; } static void __init_memblock memblock_dump(struct memblock_type *type) { phys_addr_t base, end, size; enum memblock_flags flags; int idx; struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); for_each_memblock_type(idx, type, rgn) { char nid_buf[32] = ""; base = rgn->base; size = rgn->size; end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_NUMA if (numa_valid_node(memblock_get_region_node(rgn))) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", type->name, idx, &base, &end, &size, nid_buf, flags); } } static void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); pr_info(" memory size = %pa reserved size = %pa\n", &memblock.memory.total_size, &memblock.reserved.total_size); memblock_dump(&memblock.memory); memblock_dump(&memblock.reserved); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP memblock_dump(&physmem); #endif } void __init_memblock memblock_dump_all(void) { if (memblock_debug) __memblock_dump_all(); } void __init memblock_allow_resize(void) { memblock_can_resize = 1; } static int __init early_memblock(char *p) { if (p && strstr(p, "debug")) memblock_debug = 1; return 0; } early_param("memblock", early_memblock); static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) { struct page *start_pg, *end_pg; phys_addr_t pg, pgend; /* * Convert start_pfn/end_pfn to a struct page pointer. */ start_pg = pfn_to_page(start_pfn - 1) + 1; end_pg = pfn_to_page(end_pfn - 1) + 1; /* * Convert to physical addresses, and round start upwards and end * downwards. */ pg = PAGE_ALIGN(__pa(start_pg)); pgend = PAGE_ALIGN_DOWN(__pa(end_pg)); /* * If there are free pages between these, free the section of the * memmap array. */ if (pg < pgend) memblock_phys_free(pg, pgend - pg); } /* * The mem_map array can get very big. Free the unused area of the memory map. */ static void __init free_unused_memmap(void) { unsigned long start, end, prev_end = 0; int i; if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) || IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) return; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); #endif /* * Align down here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ start = pageblock_start_pfn(start); /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ if (prev_end && prev_end < start) free_memmap(prev_end, start); /* * Align up here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ prev_end = pageblock_align(end); } #ifdef CONFIG_SPARSEMEM if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { prev_end = pageblock_align(end); free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); } #endif } static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; while (start < end) { /* * Free the 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 (start) order = min_t(int, MAX_PAGE_ORDER, __ffs(start)); else order = MAX_PAGE_ORDER; while (start + (1UL << order) > end) order--; memblock_free_pages(pfn_to_page(start), start, order); start += (1UL << order); } } static unsigned long __init __free_memory_core(phys_addr_t start, phys_addr_t end) { unsigned long start_pfn = PFN_UP(start); unsigned long end_pfn = min_t(unsigned long, PFN_DOWN(end), max_low_pfn); if (start_pfn >= end_pfn) return 0; __free_pages_memory(start_pfn, end_pfn); return end_pfn - start_pfn; } static void __init memmap_init_reserved_pages(void) { struct memblock_region *region; phys_addr_t start, end; int nid; /* * set nid on all reserved pages and also treat struct * pages for the NOMAP regions as PageReserved */ for_each_mem_region(region) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (memblock_is_nomap(region)) reserve_bootmem_region(start, end, nid); memblock_set_node(start, end, &memblock.reserved, nid); } /* * initialize struct pages for reserved regions that don't have * the MEMBLOCK_RSRV_NOINIT flag set */ for_each_reserved_mem_region(region) { if (!memblock_is_reserved_noinit(region)) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (!numa_valid_node(nid)) nid = early_pfn_to_nid(PFN_DOWN(start)); reserve_bootmem_region(start, end, nid); } } } static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; phys_addr_t start, end; u64 i; memblock_clear_hotplug(0, -1); memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); return count; } static int reset_managed_pages_done __initdata; static void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) atomic_long_set(&z->managed_pages, 0); } void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; if (reset_managed_pages_done) return; for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); reset_managed_pages_done = 1; } /** * memblock_free_all - release free pages to the buddy allocator */ void __init memblock_free_all(void) { unsigned long pages; free_unused_memmap(); reset_all_zones_managed_pages(); pages = free_low_memory_core_early(); totalram_pages_add(pages); } /* Keep a table to reserve named memory */ #define RESERVE_MEM_MAX_ENTRIES 8 #define RESERVE_MEM_NAME_SIZE 16 struct reserve_mem_table { char name[RESERVE_MEM_NAME_SIZE]; phys_addr_t start; phys_addr_t size; }; static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES]; static int reserved_mem_count; /* Add wildcard region with a lookup name */ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size, const char *name) { struct reserve_mem_table *map; map = &reserved_mem_table[reserved_mem_count++]; map->start = start; map->size = size; strscpy(map->name, name); } /** * reserve_mem_find_by_name - Find reserved memory region with a given name * @name: The name that is attached to a reserved memory region * @start: If found, holds the start address * @size: If found, holds the size of the address. * * @start and @size are only updated if @name is found. * * Returns: 1 if found or 0 if not found. */ int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size) { struct reserve_mem_table *map; int i; for (i = 0; i < reserved_mem_count; i++) { map = &reserved_mem_table[i]; if (!map->size) continue; if (strcmp(name, map->name) == 0) { *start = map->start; *size = map->size; return 1; } } return 0; } EXPORT_SYMBOL_GPL(reserve_mem_find_by_name); /* * Parse reserve_mem=nn:align:name */ static int __init reserve_mem(char *p) { phys_addr_t start, size, align, tmp; char *name; char *oldp; int len; if (!p) return -EINVAL; /* Check if there's room for more reserved memory */ if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES) return -EBUSY; oldp = p; size = memparse(p, &p); if (!size || p == oldp) return -EINVAL; if (*p != ':') return -EINVAL; align = memparse(p+1, &p); if (*p != ':') return -EINVAL; /* * memblock_phys_alloc() doesn't like a zero size align, * but it is OK for this command to have it. */ if (align < SMP_CACHE_BYTES) align = SMP_CACHE_BYTES; name = p + 1; len = strlen(name); /* name needs to have length but not too big */ if (!len || len >= RESERVE_MEM_NAME_SIZE) return -EINVAL; /* Make sure that name has text */ for (p = name; *p; p++) { if (!isspace(*p)) break; } if (!*p) return -EINVAL; /* Make sure the name is not already used */ if (reserve_mem_find_by_name(name, &start, &tmp)) return -EBUSY; start = memblock_phys_alloc(size, align); if (!start) return -ENOMEM; reserved_mem_add(start, size, name); return 1; } __setup("reserve_mem=", reserve_mem); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) static const char * const flagname[] = { [ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG", [ilog2(MEMBLOCK_MIRROR)] = "MIRROR", [ilog2(MEMBLOCK_NOMAP)] = "NOMAP", [ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG", [ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT", }; static int memblock_debug_show(struct seq_file *m, void *private) { struct memblock_type *type = m->private; struct memblock_region *reg; int i, j, nid; unsigned int count = ARRAY_SIZE(flagname); phys_addr_t end; for (i = 0; i < type->cnt; i++) { reg = &type->regions[i]; end = reg->base + reg->size - 1; nid = memblock_get_region_node(reg); seq_printf(m, "%4d: ", i); seq_printf(m, "%pa..%pa ", ®->base, &end); if (numa_valid_node(nid)) seq_printf(m, "%4d ", nid); else seq_printf(m, "%4c ", 'x'); if (reg->flags) { for (j = 0; j < count; j++) { if (reg->flags & (1U << j)) { seq_printf(m, "%s\n", flagname[j]); break; } } if (j == count) seq_printf(m, "%s\n", "UNKNOWN"); } else { seq_printf(m, "%s\n", "NONE"); } } return 0; } DEFINE_SHOW_ATTRIBUTE(memblock_debug); static int __init memblock_init_debugfs(void) { struct dentry *root = debugfs_create_dir("memblock", NULL); debugfs_create_file("memory", 0444, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", 0444, root, &memblock.reserved, &memblock_debug_fops); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP debugfs_create_file("physmem", 0444, root, &physmem, &memblock_debug_fops); #endif return 0; } __initcall(memblock_init_debugfs); #endif /* CONFIG_DEBUG_FS */ |
| 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 | /* * llc_core.c - Minimum needed routines for sap handling and module init/exit * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/llc.h> LIST_HEAD(llc_sap_list); static DEFINE_SPINLOCK(llc_sap_list_lock); /** * llc_sap_alloc - allocates and initializes sap. * * Allocates and initializes sap. */ static struct llc_sap *llc_sap_alloc(void) { struct llc_sap *sap = kzalloc(sizeof(*sap), GFP_ATOMIC); int i; if (sap) { /* sap->laddr.mac - leave as a null, it's filled by bind */ sap->state = LLC_SAP_STATE_ACTIVE; spin_lock_init(&sap->sk_lock); for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); refcount_set(&sap->refcnt, 1); } return sap; } static struct llc_sap *__llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; list_for_each_entry(sap, &llc_sap_list, node) if (sap->laddr.lsap == sap_value) goto out; sap = NULL; out: return sap; } /** * llc_sap_find - searches a SAP in station * @sap_value: sap to be found * * Searches for a sap in the sap list of the LLC's station upon the sap ID. * If the sap is found it will be refcounted and the user will have to do * a llc_sap_put after use. * Returns the sap or %NULL if not found. */ struct llc_sap *llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); if (!sap || !llc_sap_hold_safe(sap)) sap = NULL; rcu_read_unlock_bh(); return sap; } /** * llc_sap_open - open interface to the upper layers. * @lsap: SAP number. * @func: rcv func for datalink protos * * Interface function to upper layer. Each one who wants to get a SAP * (for example NetBEUI) should call this function. Returns the opened * SAP for success, NULL for failure. */ struct llc_sap *llc_sap_open(unsigned char lsap, int (*func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)) { struct llc_sap *sap = NULL; spin_lock_bh(&llc_sap_list_lock); if (__llc_sap_find(lsap)) /* SAP already exists */ goto out; sap = llc_sap_alloc(); if (!sap) goto out; sap->laddr.lsap = lsap; sap->rcv_func = func; list_add_tail_rcu(&sap->node, &llc_sap_list); out: spin_unlock_bh(&llc_sap_list_lock); return sap; } /** * llc_sap_close - close interface for upper layers. * @sap: SAP to be closed. * * Close interface function to upper layer. Each one who wants to * close an open SAP (for example NetBEUI) should call this function. * Removes this sap from the list of saps in the station and then * frees the memory for this sap. */ void llc_sap_close(struct llc_sap *sap) { WARN_ON(sap->sk_count); spin_lock_bh(&llc_sap_list_lock); list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_2), .func = llc_rcv, }; static int __init llc_init(void) { dev_add_pack(&llc_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); } module_init(llc_init); module_exit(llc_exit); EXPORT_SYMBOL(llc_sap_list); EXPORT_SYMBOL(llc_sap_find); EXPORT_SYMBOL(llc_sap_open); EXPORT_SYMBOL(llc_sap_close); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("LLC IEEE 802.2 core support"); |
| 163 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock LSM - Ruleset management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #ifndef _SECURITY_LANDLOCK_RULESET_H #define _SECURITY_LANDLOCK_RULESET_H #include <linux/bitops.h> #include <linux/build_bug.h> #include <linux/kernel.h> #include <linux/mutex.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <uapi/linux/landlock.h> #include "limits.h" #include "object.h" /* * All access rights that are denied by default whether they are handled or not * by a ruleset/layer. This must be ORed with all ruleset->access_masks[] * entries when we need to get the absolute handled access masks. */ /* clang-format off */ #define LANDLOCK_ACCESS_FS_INITIALLY_DENIED ( \ LANDLOCK_ACCESS_FS_REFER) /* clang-format on */ typedef u16 access_mask_t; /* Makes sure all filesystem access rights can be stored. */ static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS); /* Makes sure all network access rights can be stored. */ static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_NET); /* Makes sure all scoped rights can be stored. */ static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_SCOPE); /* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */ static_assert(sizeof(unsigned long) >= sizeof(access_mask_t)); /* Ruleset access masks. */ struct access_masks { access_mask_t fs : LANDLOCK_NUM_ACCESS_FS; access_mask_t net : LANDLOCK_NUM_ACCESS_NET; access_mask_t scope : LANDLOCK_NUM_SCOPE; }; union access_masks_all { struct access_masks masks; u32 all; }; /* Makes sure all fields are covered. */ static_assert(sizeof(typeof_member(union access_masks_all, masks)) == sizeof(typeof_member(union access_masks_all, all))); typedef u16 layer_mask_t; /* Makes sure all layers can be checked. */ static_assert(BITS_PER_TYPE(layer_mask_t) >= LANDLOCK_MAX_NUM_LAYERS); /** * struct landlock_layer - Access rights for a given layer */ struct landlock_layer { /** * @level: Position of this layer in the layer stack. */ u16 level; /** * @access: Bitfield of allowed actions on the kernel object. They are * relative to the object type (e.g. %LANDLOCK_ACTION_FS_READ). */ access_mask_t access; }; /** * union landlock_key - Key of a ruleset's red-black tree */ union landlock_key { /** * @object: Pointer to identify a kernel object (e.g. an inode). */ struct landlock_object *object; /** * @data: Raw data to identify an arbitrary 32-bit value * (e.g. a TCP port). */ uintptr_t data; }; /** * enum landlock_key_type - Type of &union landlock_key */ enum landlock_key_type { /** * @LANDLOCK_KEY_INODE: Type of &landlock_ruleset.root_inode's node * keys. */ LANDLOCK_KEY_INODE = 1, /** * @LANDLOCK_KEY_NET_PORT: Type of &landlock_ruleset.root_net_port's * node keys. */ LANDLOCK_KEY_NET_PORT, }; /** * struct landlock_id - Unique rule identifier for a ruleset */ struct landlock_id { /** * @key: Identifies either a kernel object (e.g. an inode) or * a raw value (e.g. a TCP port). */ union landlock_key key; /** * @type: Type of a landlock_ruleset's root tree. */ const enum landlock_key_type type; }; /** * struct landlock_rule - Access rights tied to an object */ struct landlock_rule { /** * @node: Node in the ruleset's red-black tree. */ struct rb_node node; /** * @key: A union to identify either a kernel object (e.g. an inode) or * a raw data value (e.g. a network socket port). This is used as a key * for this ruleset element. The pointer is set once and never * modified. It always points to an allocated object because each rule * increments the refcount of its object. */ union landlock_key key; /** * @num_layers: Number of entries in @layers. */ u32 num_layers; /** * @layers: Stack of layers, from the latest to the newest, implemented * as a flexible array member (FAM). */ struct landlock_layer layers[] __counted_by(num_layers); }; /** * struct landlock_hierarchy - Node in a ruleset hierarchy */ struct landlock_hierarchy { /** * @parent: Pointer to the parent node, or NULL if it is a root * Landlock domain. */ struct landlock_hierarchy *parent; /** * @usage: Number of potential children domains plus their parent * domain. */ refcount_t usage; }; /** * struct landlock_ruleset - Landlock ruleset * * This data structure must contain unique entries, be updatable, and quick to * match an object. */ struct landlock_ruleset { /** * @root_inode: Root of a red-black tree containing &struct * landlock_rule nodes with inode object. Once a ruleset is tied to a * process (i.e. as a domain), this tree is immutable until @usage * reaches zero. */ struct rb_root root_inode; #if IS_ENABLED(CONFIG_INET) /** * @root_net_port: Root of a red-black tree containing &struct * landlock_rule nodes with network port. Once a ruleset is tied to a * process (i.e. as a domain), this tree is immutable until @usage * reaches zero. */ struct rb_root root_net_port; #endif /* IS_ENABLED(CONFIG_INET) */ /** * @hierarchy: Enables hierarchy identification even when a parent * domain vanishes. This is needed for the ptrace protection. */ struct landlock_hierarchy *hierarchy; union { /** * @work_free: Enables to free a ruleset within a lockless * section. This is only used by * landlock_put_ruleset_deferred() when @usage reaches zero. * The fields @lock, @usage, @num_rules, @num_layers and * @access_masks are then unused. */ struct work_struct work_free; struct { /** * @lock: Protects against concurrent modifications of * @root, if @usage is greater than zero. */ struct mutex lock; /** * @usage: Number of processes (i.e. domains) or file * descriptors referencing this ruleset. */ refcount_t usage; /** * @num_rules: Number of non-overlapping (i.e. not for * the same object) rules in this ruleset. */ u32 num_rules; /** * @num_layers: Number of layers that are used in this * ruleset. This enables to check that all the layers * allow an access request. A value of 0 identifies a * non-merged ruleset (i.e. not a domain). */ u32 num_layers; /** * @access_masks: Contains the subset of filesystem and * network actions that are restricted by a ruleset. * A domain saves all layers of merged rulesets in a * stack (FAM), starting from the first layer to the * last one. These layers are used when merging * rulesets, for user space backward compatibility * (i.e. future-proof), and to properly handle merged * rulesets without overlapping access rights. These * layers are set once and never changed for the * lifetime of the ruleset. */ struct access_masks access_masks[]; }; }; }; struct landlock_ruleset * landlock_create_ruleset(const access_mask_t access_mask_fs, const access_mask_t access_mask_net, const access_mask_t scope_mask); void landlock_put_ruleset(struct landlock_ruleset *const ruleset); void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset); int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const access_mask_t access); struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const ruleset); const struct landlock_rule * landlock_find_rule(const struct landlock_ruleset *const ruleset, const struct landlock_id id); static inline void landlock_get_ruleset(struct landlock_ruleset *const ruleset) { if (ruleset) refcount_inc(&ruleset->usage); } /** * landlock_union_access_masks - Return all access rights handled in the * domain * * @domain: Landlock ruleset (used as a domain) * * Returns: an access_masks result of the OR of all the domain's access masks. */ static inline struct access_masks landlock_union_access_masks(const struct landlock_ruleset *const domain) { union access_masks_all matches = {}; size_t layer_level; for (layer_level = 0; layer_level < domain->num_layers; layer_level++) { union access_masks_all layer = { .masks = domain->access_masks[layer_level], }; matches.all |= layer.all; } return matches.masks; } /** * landlock_get_applicable_domain - Return @domain if it applies to (handles) * at least one of the access rights specified * in @masks * * @domain: Landlock ruleset (used as a domain) * @masks: access masks * * Returns: @domain if any access rights specified in @masks is handled, or * NULL otherwise. */ static inline const struct landlock_ruleset * landlock_get_applicable_domain(const struct landlock_ruleset *const domain, const struct access_masks masks) { const union access_masks_all masks_all = { .masks = masks, }; union access_masks_all merge = {}; if (!domain) return NULL; merge.masks = landlock_union_access_masks(domain); if (merge.all & masks_all.all) return domain; return NULL; } static inline void landlock_add_fs_access_mask(struct landlock_ruleset *const ruleset, const access_mask_t fs_access_mask, const u16 layer_level) { access_mask_t fs_mask = fs_access_mask & LANDLOCK_MASK_ACCESS_FS; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(fs_access_mask != fs_mask); ruleset->access_masks[layer_level].fs |= fs_mask; } static inline void landlock_add_net_access_mask(struct landlock_ruleset *const ruleset, const access_mask_t net_access_mask, const u16 layer_level) { access_mask_t net_mask = net_access_mask & LANDLOCK_MASK_ACCESS_NET; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(net_access_mask != net_mask); ruleset->access_masks[layer_level].net |= net_mask; } static inline void landlock_add_scope_mask(struct landlock_ruleset *const ruleset, const access_mask_t scope_mask, const u16 layer_level) { access_mask_t mask = scope_mask & LANDLOCK_MASK_SCOPE; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(scope_mask != mask); ruleset->access_masks[layer_level].scope |= mask; } static inline access_mask_t landlock_get_fs_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { /* Handles all initially denied by default access rights. */ return ruleset->access_masks[layer_level].fs | LANDLOCK_ACCESS_FS_INITIALLY_DENIED; } static inline access_mask_t landlock_get_net_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { return ruleset->access_masks[layer_level].net; } static inline access_mask_t landlock_get_scope_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { return ruleset->access_masks[layer_level].scope; } bool landlock_unmask_layers(const struct landlock_rule *const rule, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], const size_t masks_array_size); access_mask_t landlock_init_layer_masks(const struct landlock_ruleset *const domain, const access_mask_t access_request, layer_mask_t (*const layer_masks)[], const enum landlock_key_type key_type); #endif /* _SECURITY_LANDLOCK_RULESET_H */ |
| 523 361 8 362 51 7 385 385 92 150 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGTABLE_H #define _LINUX_PGTABLE_H #include <linux/pfn.h> #include <asm/pgtable.h> #define PMD_ORDER (PMD_SHIFT - PAGE_SHIFT) #define PUD_ORDER (PUD_SHIFT - PAGE_SHIFT) #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU #include <linux/mm_types.h> #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS #error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* * On almost all architectures and configurations, 0 can be used as the * upper ceiling to free_pgtables(): on many architectures it has the same * effect as using TASK_SIZE. However, there is one configuration which * must impose a more careful limit, to avoid freeing kernel pgtables. */ #ifndef USER_PGTABLES_CEILING #define USER_PGTABLES_CEILING 0UL #endif /* * This defines the first usable user address. Platforms * can override its value with custom FIRST_USER_ADDRESS * defined in their respective <asm/pgtable.h>. */ #ifndef FIRST_USER_ADDRESS #define FIRST_USER_ADDRESS 0UL #endif /* * This defines the generic helper for accessing PMD page * table page. Although platforms can still override this * via their respective <asm/pgtable.h>. */ #ifndef pmd_pgtable #define pmd_pgtable(pmd) pmd_page(pmd) #endif #define pmd_folio(pmd) page_folio(pmd_page(pmd)) /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * * The pXx_index() functions return the index of the entry in the page * table page which would control the given virtual address * * As these functions may be used by the same code for different levels of * the page table folding, they are always available, regardless of * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 * because in such cases PTRS_PER_PxD equals 1. */ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } #define pmd_index pmd_index #endif #ifndef pud_index static inline unsigned long pud_index(unsigned long address) { return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); } #define pud_index pud_index #endif #ifndef pgd_index /* Must be a compile-time constant, so implement it as a macro */ #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif #ifndef kernel_pte_init static inline void kernel_pte_init(void *addr) { } #define kernel_pte_init kernel_pte_init #endif #ifndef pmd_init static inline void pmd_init(void *addr) { } #define pmd_init pmd_init #endif #ifndef pud_init static inline void pud_init(void *addr) { } #define pud_init pud_init #endif #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); } #define pte_offset_kernel pte_offset_kernel #endif #ifdef CONFIG_HIGHPTE #define __pte_map(pmd, address) \ ((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address))) #define pte_unmap(pte) do { \ kunmap_local((pte)); \ rcu_read_unlock(); \ } while (0) #else static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline void pte_unmap(pte_t *pte) { rcu_read_unlock(); } #endif void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); /* Find an entry in the second-level page table.. */ #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return pud_pgtable(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { return p4d_pgtable(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) { return (pgd + pgd_index(address)); }; /* * a shortcut to get a pgd_t in a given mm */ #ifndef pgd_offset #define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) #endif /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a * pointer to the PMD entry in user or kernel page table or translate a virtual * address to the pointer in the PTE in the kernel page tables with simple * helpers. */ static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); } static inline pmd_t *pmd_off_k(unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); } static inline pte_t *virt_to_kpte(unsigned long vaddr) { pmd_t *pmd = pmd_off_k(vaddr); return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } #ifndef pmd_young static inline int pmd_young(pmd_t pmd) { return 0; } #endif #ifndef pmd_dirty static inline int pmd_dirty(pmd_t pmd) { return 0; } #endif /* * A facility to provide lazy MMU batching. This allows PTE updates and * page invalidations to be delayed until a call to leave lazy MMU mode * is issued. Some architectures may benefit from doing this, and it is * beneficial for both shadow and direct mode hypervisors, which may batch * the PTE updates which happen during this window. Note that using this * interface requires that read hazards be removed from the code. A read * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be * up to date. This mode can only be entered and left under the protection of * the page table locks for all page tables which may be modified. In the UP * case, this is required so that preemption is disabled, and in the SMP case, * it must synchronize the delayed page table writes properly on other CPUs. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE #define arch_enter_lazy_mmu_mode() do {} while (0) #define arch_leave_lazy_mmu_mode() do {} while (0) #define arch_flush_lazy_mmu_mode() do {} while (0) #endif #ifndef pte_batch_hint /** * pte_batch_hint - Number of pages that can be added to batch without scanning. * @ptep: Page table pointer for the entry. * @pte: Page table entry. * * Some architectures know that a set of contiguous ptes all map the same * contiguous memory with the same permissions. In this case, it can provide a * hint to aid pte batching without the core code needing to scan every pte. * * An architecture implementation may ignore the PTE accessed state. Further, * the dirty state must apply atomically to all the PTEs described by the hint. * * May be overridden by the architecture, else pte_batch_hint is always 1. */ static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { return 1; } #endif #ifndef pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #endif #define pte_next_pfn(pte) pte_advance_pfn(pte, 1) #ifndef set_ptes /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. * @addr: Address to map the first page at. * @ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @nr: Number of pages to map. * * When nr==1, initial state of pte may be present or not present, and new state * may be present or not present. When nr>1, initial state of all ptes must be * not present, and new state must be present. * * May be overridden by the architecture, or the architecture can define * set_pte() and PFN_PTE_SHIFT. * * Context: The caller holds the page table lock. The pages all belong * to the same folio. The PTEs are all in the same PMD. */ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); arch_enter_lazy_mmu_mode(); for (;;) { set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_next_pfn(pte); } arch_leave_lazy_mmu_mode(); } #endif #define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #endif #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #else static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { BUILD_BUG(); return 0; } static inline int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef ptep_get static inline pte_t ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } #endif #ifndef pmdp_get static inline pmd_t pmdp_get(pmd_t *pmdp) { return READ_ONCE(*pmdp); } #endif #ifndef pudp_get static inline pud_t pudp_get(pud_t *pudp) { return READ_ONCE(*pudp); } #endif #ifndef p4dp_get static inline p4d_t p4dp_get(p4d_t *p4dp) { return READ_ONCE(*p4dp); } #endif #ifndef pgdp_get static inline pgd_t pgdp_get(pgd_t *pgdp) { return READ_ONCE(*pgdp); } #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); int r = 1; if (!pte_young(pte)) r = 0; else set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); return r; } #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; int r = 1; if (!pmd_young(pmd)) r = 0; else set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); return r; } #else static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else /* * Despite relevant to THP only, this API is called from generic rmap code * under PageTransHuge(), hence needs a dummy implementation for !THP */ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef arch_has_hw_nonleaf_pmd_young /* * Return whether the accessed bit in non-leaf PMD entries is supported on the * local CPU. */ static inline bool arch_has_hw_nonleaf_pmd_young(void) { return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG); } #endif #ifndef arch_has_hw_pte_young /* * Return whether the accessed bit is supported on the local CPU. * * This stub assumes accessing through an old PTE triggers a page fault. * Architectures that automatically set the access bit should overwrite it. */ static inline bool arch_has_hw_pte_young(void) { return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG); } #endif #ifndef arch_check_zapped_pte static inline void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { } #endif #ifndef arch_check_zapped_pmd static inline void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { } #endif #ifndef arch_check_zapped_pud static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { } #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); pte_clear(mm, address, ptep); page_table_check_pte_clear(mm, pte); return pte; } #endif #ifndef clear_young_dirty_ptes /** * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the * same folio as old/clean. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to mark old/clean. * @flags: Flags to modify the PTE batch semantics. * * May be overridden by the architecture; otherwise, implemented by * get_and_clear/modify/set for each pte in the range. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { if (flags == CYDP_CLEAR_YOUNG) ptep_test_and_clear_young(vma, addr, ptep); else { pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); set_pte_at(vma->vm_mm, addr, ptep, pte); } if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { ptep_get_and_clear(mm, addr, ptep); } #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH /* * For walking the pagetables without holding any locks. Some architectures * (eg x86-32 PAE) cannot load the entries atomically without using expensive * instructions. We are guaranteed that a PTE will only either go from not * present to present, or present to not present -- it will not switch to a * completely different present page without a TLB flush inbetween; which we * are blocking by holding interrupts off. * * Setting ptes from not present to present goes: * * ptep->pte_high = h; * smp_wmb(); * ptep->pte_low = l; * * And present to not present goes: * * ptep->pte_low = 0; * smp_wmb(); * ptep->pte_high = 0; * * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. * We load pte_high *after* loading pte_low, which ensures we don't see an older * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't * picked up a changed pte high. We might have gotten rubbish values from * pte_low and pte_high, but we are guaranteed that pte_low will not have the * present bit set *unless* it is 'l'. Because get_user_pages_fast() only * operates on present ptes we're safe. */ static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte; do { pte.pte_low = ptep->pte_low; smp_rmb(); pte.pte_high = ptep->pte_high; smp_rmb(); } while (unlikely(pte.pte_low != ptep->pte_low)); return pte; } #define ptep_get_lockless ptep_get_lockless #if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { pmd_t pmd; do { pmd.pmd_low = pmdp->pmd_low; smp_rmb(); pmd.pmd_high = pmdp->pmd_high; smp_rmb(); } while (unlikely(pmd.pmd_low != pmdp->pmd_low)); return pmd; } #define pmdp_get_lockless pmdp_get_lockless #define pmdp_get_lockless_sync() tlb_remove_table_sync_one() #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */ /* * We require that the PTE can be read atomically. */ #ifndef ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { return ptep_get(ptep); } #endif #ifndef pmdp_get_lockless static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { return pmdp_get(pmdp); } static inline void pmdp_get_lockless_sync(void) { } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; pmd_clear(pmdp); page_table_check_pmd_clear(mm, pmd); return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t pud = *pudp; pud_clear(pudp); page_table_check_pud_clear(mm, pud); return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, int full) { return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); } #endif #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL static inline pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, int full) { return pudp_huge_get_and_clear(vma->vm_mm, address, pudp); } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { return ptep_get_and_clear(mm, address, ptep); } #endif #ifndef get_and_clear_full_ptes /** * get_and_clear_full_ptes - Clear present PTEs that map consecutive pages of * the same folio, collecting dirty/accessed bits. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_get_and_clear_full(), merging dirty/accessed bits into the * returned PTE. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = ptep_get_and_clear_full(mm, addr, ptep, full); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = ptep_get_and_clear_full(mm, addr, ptep, full); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #endif #ifndef clear_full_ptes /** * clear_full_ptes - Clear present PTEs that map consecutive pages of the same * folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_get_and_clear_full(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { ptep_get_and_clear_full(mm, addr, ptep, full); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif /* * If two threads concurrently fault at the same page, the thread that * won the race updates the PTE and its local TLB/Cache. The other thread * gives up, simply does nothing, and continues; on architectures where * software can update TLB, local TLB can be updated here to avoid next page * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ #ifndef update_mmu_tlb_range static inline void update_mmu_tlb_range(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, unsigned int nr) { } #endif static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { update_mmu_tlb_range(vma, address, ptep, 1); } /* * Some architectures may be able to avoid expensive synchronization * primitives when modifications are made to PTE's which are already * not present, or in the process of an address space destruction. */ #ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL static inline void pte_clear_not_present_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_clear(mm, address, ptep); } #endif #ifndef clear_not_present_full_ptes /** * clear_not_present_full_ptes - Clear multiple not present PTEs which are * consecutive in the pgtable. * @mm: Address space the ptes represent. * @addr: Address of the first pte. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over pte_clear_not_present_full(). * * Context: The caller holds the page table lock. The PTEs are all not present. * The PTEs are all in the same PMD. */ static inline void clear_not_present_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { pte_clear_not_present_full(mm, addr, ptep, full); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); #endif #ifndef pte_mkwrite static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { return pte_mkwrite_novma(pte); } #endif #if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite) static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { return pmd_mkwrite_novma(pmd); } #endif #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte = ptep_get(ptep); set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); } #endif #ifndef wrprotect_ptes /** * wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same * folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to write-protect. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_set_wrprotect(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { for (;;) { ptep_set_wrprotect(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibility of software setting this bit. It brings * out extra page fault penalty to track page access bit. For optimization page * access bit can be set during all page fault flow on these arches. * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ #ifndef pte_sw_mkyoung static inline pte_t pte_sw_mkyoung(pte_t pte) { return pte; } #define pte_sw_mkyoung pte_sw_mkyoung #endif #ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t old_pmd = *pmdp; set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); } #else static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t old_pud = *pudp; set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); } #else static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return *pmdp; } #define pmdp_collapse_flush pmdp_collapse_flush #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif #ifndef arch_needs_pgtable_deposit #define arch_needs_pgtable_deposit() (false) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is an implementation of pmdp_establish() that is only suitable for an * architecture that doesn't have hardware dirty/accessed bits. In this case we * can't race with CPU which sets these bits and non-atomic approach is fine. */ static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { pmd_t old_pmd = *pmdp; set_pmd_at(vma->vm_mm, address, pmdp, pmd); return old_pmd; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD /* * pmdp_invalidate_ad() invalidates the PMD while changing a transparent * hugepage mapping in the page tables. This function is similar to * pmdp_invalidate(), but should only be used if the access and dirty bits would * not be cleared by the software in the new PMD value. The function ensures * that hardware changes of the access and dirty bits updates would not be lost. * * Doing so can allow in certain architectures to avoid a TLB flush in most * cases. Yet, another TLB flush might be necessary later if the PMD update * itself requires such flush (e.g., if protection was set to be stricter). Yet, * even when a TLB flush is needed because of the update, the caller may be able * to batch these TLB flushing operations, so fewer TLB flush operations are * needed. */ extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { return pte_val(pte_a) == pte_val(pte_b); } #endif #ifndef __HAVE_ARCH_PTE_UNUSED /* * Some architectures provide facilities to virtualization guests * so that they can flag allocated pages as unused. This allows the * host to transparently reclaim unused pages. This function returns * whether the pte's page is unused. */ static inline int pte_unused(pte_t pte) { return 0; } #endif #ifndef pte_access_permitted #define pte_access_permitted(pte, write) \ (pte_present(pte) && (!(write) || pte_write(pte))) #endif #ifndef pmd_access_permitted #define pmd_access_permitted(pmd, write) \ (pmd_present(pmd) && (!(write) || pmd_write(pmd))) #endif #ifndef pud_access_permitted #define pud_access_permitted(pud, write) \ (pud_present(pud) && (!(write) || pud_write(pud))) #endif #ifndef p4d_access_permitted #define p4d_access_permitted(p4d, write) \ (p4d_present(p4d) && (!(write) || p4d_write(p4d))) #endif #ifndef pgd_access_permitted #define pgd_access_permitted(pgd, write) \ (pgd_present(pgd) && (!(write) || pgd_write(pgd))) #endif #ifndef __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { return pmd_val(pmd_a) == pmd_val(pmd_b); } #endif #ifndef pud_same static inline int pud_same(pud_t pud_a, pud_t pud_b) { return pud_val(pud_a) == pud_val(pud_b); } #define pud_same pud_same #endif #ifndef __HAVE_ARCH_P4D_SAME static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) { return p4d_val(p4d_a) == p4d_val(p4d_b); } #endif #ifndef __HAVE_ARCH_PGD_SAME static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) { return pgd_val(pgd_a) == pgd_val(pgd_b); } #endif #ifndef __HAVE_ARCH_DO_SWAP_PAGE static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte, int nr) { } #else /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte, int nr) { for (int i = 0; i < nr; i++) { arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE, pte_advance_pfn(pte, i), pte_advance_pfn(oldpte, i)); } } #endif #ifndef __HAVE_ARCH_UNMAP_ONE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_unmap_one() can save this * metadata on a swap-out of a page. */ static inline int arch_unmap_one(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t orig_pte) { return 0; } #endif /* * Allow architectures to preserve additional metadata associated with * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } #endif #ifndef __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { } static inline void arch_swap_invalidate_area(int type) { } #endif #ifndef __HAVE_ARCH_SWAP_RESTORE static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif #ifndef __HAVE_ARCH_PGD_OFFSET_GATE #define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) #endif #ifndef __HAVE_ARCH_MOVE_PTE #define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible # define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. */ #define pgd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #ifndef p4d_addr_end #define p4d_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pmd_addr_end #define pmd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif /* * When walking page tables, we usually want to skip any p?d_none entries; * and any p?d_bad entries - reporting the error before resetting to none. * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *); #else #define p4d_clear_bad(p4d) do { } while (0) #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *); #else #define pud_clear_bad(p4d) do { } while (0) #endif void pmd_clear_bad(pmd_t *); static inline int pgd_none_or_clear_bad(pgd_t *pgd) { if (pgd_none(*pgd)) return 1; if (unlikely(pgd_bad(*pgd))) { pgd_clear_bad(pgd); return 1; } return 0; } static inline int p4d_none_or_clear_bad(p4d_t *p4d) { if (p4d_none(*p4d)) return 1; if (unlikely(p4d_bad(*p4d))) { p4d_clear_bad(p4d); return 1; } return 0; } static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) return 1; if (unlikely(pud_bad(*pud))) { pud_clear_bad(pud); return 1; } return 0; } static inline int pmd_none_or_clear_bad(pmd_t *pmd) { if (pmd_none(*pmd)) return 1; if (unlikely(pmd_bad(*pmd))) { pmd_clear_bad(pmd); return 1; } return 0; } static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* * Get the current pte state, but zero it out to make it * non-present, preventing the hardware from asynchronously * updating it. */ return ptep_get_and_clear(vma->vm_mm, addr, ptep); } static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { /* * The pte is non-present, so there's no hardware state to * preserve. */ set_pte_at(vma->vm_mm, addr, ptep, pte); } #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION /* * Start a pte protection read-modify-write transaction, which * protects against asynchronous hardware modifications to the pte. * The intention is not to prevent the hardware from making pte * updates, but to prevent any updates it may make from being lost. * * This does not protect against other software modifications of the * pte; the appropriate pte lock must be held over the transaction. * * Note that this interface is intended to be batchable, meaning that * ptep_modify_prot_commit may not actually update the pte, but merely * queue the update to be done at some later time. The update must be * actually committed before the pte lock is released, however. */ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return __ptep_modify_prot_start(vma, addr, ptep); } /* * Commit an update to a pte, leaving any hardware-controlled bits in * the PTE unmodified. */ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { __ptep_modify_prot_commit(vma, addr, ptep, pte); } #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ #endif /* CONFIG_MMU */ /* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. */ #ifndef pgprot_nx #define pgprot_nx(prot) (prot) #endif #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif #ifndef pgprot_writecombine #define pgprot_writecombine pgprot_noncached #endif #ifndef pgprot_writethrough #define pgprot_writethrough pgprot_noncached #endif #ifndef pgprot_device #define pgprot_device pgprot_noncached #endif #ifndef pgprot_mhp #define pgprot_mhp(prot) (prot) #endif #ifdef CONFIG_MMU #ifndef pgprot_modify #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) newprot = pgprot_noncached(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) newprot = pgprot_writecombine(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) newprot = pgprot_device(newprot); return newprot; } #endif #endif /* CONFIG_MMU */ #ifndef pgprot_encrypted #define pgprot_encrypted(prot) (prot) #endif #ifndef pgprot_decrypted #define pgprot_decrypted(prot) (prot) #endif /* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for * paravirtualized guests. By convention, only one of the batched * update (lazy) modes (CPU, MMU) should be active at any given time, * entry should never be nested, and entry and exits should always be * paired. This is for sanity of maintaining and reasoning about the * kernel code. In this case, the exit (end of the context switch) is * in architecture-specific code, and so doesn't need a generic * definition. */ #ifndef __HAVE_ARCH_START_CONTEXT_SWITCH #define arch_start_context_switch(prev) do {} while (0) #endif #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ static inline int pte_soft_dirty(pte_t pte) { return 0; } static inline int pmd_soft_dirty(pmd_t pmd) { return 0; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte; } static inline int pte_swp_soft_dirty(pte_t pte) { return 0; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #ifndef __HAVE_PFNMAP_TRACKING /* * Interfaces that can be used by architecture code to keep track of * memory type of pfn mappings specified by the remap_pfn_range, * vmf_insert_pfn. */ /* * track_pfn_remap is called when a _new_ pfn mapping is being established * by remap_pfn_range() for physical range indicated by pfn and size. */ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size) { return 0; } /* * track_pfn_insert is called when a _new_ single pfn is established * by vmf_insert_pfn(). */ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) { } /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). */ static inline int track_pfn_copy(struct vm_area_struct *vma) { return 0; } /* * untrack_pfn is called while unmapping a pfnmap for a region. * untrack can be called for a specific region indicated by pfn and size or * can be for the entire vma (in which case pfn, size are zero). */ static inline void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { } /* * untrack_pfn_clear is called while mremapping a pfnmap for a new region * or fails to copy pgtable during duplicate vm area. */ static inline void untrack_pfn_clear(struct vm_area_struct *vma) { } #else extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked); extern void untrack_pfn_clear(struct vm_area_struct *vma); #endif #ifdef CONFIG_MMU #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; unsigned long offset_from_zero_pfn = pfn - zero_pfn; return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); } #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) #else static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; return pfn == zero_pfn; } static inline unsigned long my_zero_pfn(unsigned long addr) { extern unsigned long zero_pfn; return zero_pfn; } #endif #else static inline int is_zero_pfn(unsigned long pfn) { return 0; } static inline unsigned long my_zero_pfn(unsigned long addr) { return 0; } #endif /* CONFIG_MMU */ #ifdef CONFIG_MMU #ifndef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return 0; } #ifndef pmd_write static inline int pmd_write(pmd_t pmd) { BUG(); return 0; } #endif /* pmd_write */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef pud_write static inline int pud_write(pud_t pud) { BUG(); return 0; } #endif /* pud_write */ #if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { return 0; } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline int pud_trans_huge(pud_t pud) { return 0; } #endif static inline int pud_trans_unstable(pud_t *pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudval = READ_ONCE(*pud); if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) return 1; if (unlikely(pud_bad(pudval))) { pud_clear_bad(pud); return 1; } #endif return 0; } #ifndef CONFIG_NUMA_BALANCING /* * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is * perfectly valid to indicate "no" in that case, which is why our default * implementation defaults to "always no". * * In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE * page protection due to NUMA hinting. NUMA hinting faults only apply in * accessible VMAs. * * So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault, * looking at the VMA accessibility is sufficient. */ static inline int pte_protnone(pte_t pte) { return 0; } static inline int pmd_protnone(pmd_t pmd) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; } static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) { return 0; } static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in * THP regime. Stock flush_tlb_range() typically has optimization to nuke the * entire TLB if flush span is greater than a threshold, which will * likely be true for a single huge page. Thus a single THP flush will * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #else #define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() #define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() #endif #endif struct file; int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot); #ifndef CONFIG_X86_ESPFIX64 static inline void init_espfix_bsp(void) { } #endif extern void __init pgtable_cache_init(void); #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { return true; } static inline bool arch_has_pfn_modify_check(void) { return false; } #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ /* * Architecture PAGE_KERNEL_* fallbacks * * Some architectures don't define certain PAGE_KERNEL_* flags. This is either * because they really don't support them, or the port needs to be updated to * reflect the required functionality. Below are a set of relatively safe * fallbacks, as best effort, which we can count on in lieu of the architectures * not defining them on their own yet. */ #ifndef PAGE_KERNEL_RO # define PAGE_KERNEL_RO PAGE_KERNEL #endif #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif /* * Page Table Modification bits for pgtbl_mod_mask. * * These are used by the p?d_alloc_track*() set of functions an in the generic * vmalloc/ioremap code to track at which page-table levels entries have been * modified. Based on that the code can better decide when vmalloc and ioremap * mapping changes need to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 #define __PGTBL_PUD_MODIFIED 2 #define __PGTBL_PMD_MODIFIED 3 #define __PGTBL_PTE_MODIFIED 4 #define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) #define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) #define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) #define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) #define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) /* Page-Table Modification Mask */ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) #ifdef CONFIG_PHYS_ADDR_T_64BIT /* * ZSMALLOC needs to know the highest PFN on 32-bit architectures * with physical address space extension, but falls back to * BITS_PER_LONG otherwise. */ #error Missing MAX_POSSIBLE_PHYSMEM_BITS definition #else #define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif #endif #ifndef has_transparent_hugepage #define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif #ifndef has_transparent_pud_hugepage #define has_transparent_pud_hugepage() IS_BUILTIN(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) #endif /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. */ #ifndef mm_p4d_folded #define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) #endif #ifndef mm_pud_folded #define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) #endif #ifndef mm_pmd_folded #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif #ifndef p4d_offset_lockless #define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) #endif #ifndef pud_offset_lockless #define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) #endif #ifndef pmd_offset_lockless #define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) #endif /* * pXd_leaf() is the API to check whether a pgtable entry is a huge page * mapping. It should work globally across all archs, without any * dependency on CONFIG_* options. For architectures that do not support * huge mappings on specific levels, below fallbacks will be used. * * A leaf pgtable entry should always imply the following: * * - It is a "present" entry. IOW, before using this API, please check it * with pXd_present() first. NOTE: it may not always mean the "present * bit" is set. For example, PROT_NONE entries are always "present". * * - It should _never_ be a swap entry of any type. Above "present" check * should have guarded this, but let's be crystal clear on this. * * - It should contain a huge PFN, which points to a huge page larger than * PAGE_SIZE of the platform. The PFN format isn't important here. * * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(), * pXd_devmap(), or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false #endif #ifndef p4d_leaf #define p4d_leaf(x) false #endif #ifndef pud_leaf #define pud_leaf(x) false #endif #ifndef pmd_leaf #define pmd_leaf(x) false #endif #ifndef pgd_leaf_size #define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT) #endif #ifndef p4d_leaf_size #define p4d_leaf_size(x) P4D_SIZE #endif #ifndef pud_leaf_size #define pud_leaf_size(x) PUD_SIZE #endif #ifndef pmd_leaf_size #define pmd_leaf_size(x) PMD_SIZE #endif #ifndef __pte_leaf_size #ifndef pte_leaf_size #define pte_leaf_size(x) PAGE_SIZE #endif #define __pte_leaf_size(x,y) pte_leaf_size(y) #endif /* * We always define pmd_pfn for all archs as it's used in lots of generic * code. Now it happens too for pud_pfn (and can happen for larger * mappings too in the future; we're not there yet). Instead of defining * it for all archs (like pmd_pfn), provide a fallback. * * Note that returning 0 here means any arch that didn't define this can * get severely wrong when it hits a real pud leaf. It's arch's * responsibility to properly define it when a huge pud is possible. */ #ifndef pud_pfn #define pud_pfn(x) 0 #endif /* * Some architectures have MMUs that are configurable or selectable at boot * time. These lead to variable PTRS_PER_x. For statically allocated arrays it * helps to have a static maximum value. */ #ifndef MAX_PTRS_PER_PTE #define MAX_PTRS_PER_PTE PTRS_PER_PTE #endif #ifndef MAX_PTRS_PER_PMD #define MAX_PTRS_PER_PMD PTRS_PER_PMD #endif #ifndef MAX_PTRS_PER_PUD #define MAX_PTRS_PER_PUD PTRS_PER_PUD #endif #ifndef MAX_PTRS_PER_P4D #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif #ifndef pte_pgprot #define pte_pgprot(x) ((pgprot_t) {0}) #endif #ifndef pmd_pgprot #define pmd_pgprot(x) ((pgprot_t) {0}) #endif #ifndef pud_pgprot #define pud_pgprot(x) ((pgprot_t) {0}) #endif /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and * MAP_PRIVATE (with Enhanced PAN supported): * r: (no) no * w: (no) no * x: (yes) yes */ #define DECLARE_VM_GET_PAGE_PROT \ pgprot_t vm_get_page_prot(unsigned long vm_flags) \ { \ return protection_map[vm_flags & \ (VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)]; \ } \ EXPORT_SYMBOL(vm_get_page_prot); #endif /* _LINUX_PGTABLE_H */ |
| 302 302 302 301 | 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. * * Note that these are only respected if collapse was initiated by khugepaged. */ unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct khugepaged_mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR_RW(max_ptes_none); static ssize_t max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR_RW(max_ptes_swap); static ssize_t max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = KMEM_CACHE(khugepaged_mm_slot, 0); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } static bool hugepage_pmd_enabled(void) { /* * We cover the anon, shmem and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. * Shmem pmd-sized hugepages are also determined by its pmd-size control, * except when the global shmem_huge is set to SHMEM_HUGE_DENY. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_always)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_madvise)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled()) return true; return false; } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we return all * pagetables will be destroyed) until khugepaged has finished * working on the pagetables under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount = folio_mapcount(folio); if (!folio_test_anon(folio) || folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); if (folio_test_private(folio)) expected_refcount++; return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before folio_isolate_lru because the * folio can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { pmd_t pmde; *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; pmde = pmdp_get_lockless(*pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { /* * Here the ptl is only used to check pte_same() in * do_swap_page(), so readonly version is enough. */ pte = pte_offset_map_ro_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. "False negatives" from * folio_likely_mapped_shared() are not expected to matter * much in practice. */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * @install_pmd: If a huge PMD should be installed * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) goto abort; /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) { spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) { flush_tlb_mm(mm); goto unlock; } } } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); pte_unmap_unlock(start_pte, ptl); if (ptl != pml) spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } unlock: if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool skipped_uffd = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) { skipped_uffd = true; } else { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); } if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (!skipped_uffd) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto rollback; } } while (1); for (index = start; index < end;) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } } nr_none++; index++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control 2 + nr_pages references to the folio: * - we hold a pin on it; * - nr_pages reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); index += folio_nr_pages(folio); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure i_writecount is up to date and the update to nr_thps * is visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { int i, nr_pages = folio_nr_pages(folio); while (index < folio->index) { clear_highpage(dst); index++; dst++; } for (i = 0; i < nr_pages; i++) { if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 2 + folio_nr_pages(folio)); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); mm = slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (hpage_collapse_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (hugepage_pmd_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; if (!hugepage_pmd_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 96 59 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LINUX_RESUME_USER_MODE_H #define LINUX_RESUME_USER_MODE_H #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/rseq.h> #include <linux/blk-cgroup.h> /** * set_notify_resume - cause resume_user_mode_work() to be called * @task: task that will call resume_user_mode_work() * * Calling this arranges that @task will call resume_user_mode_work() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call resume_user_mode_work() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); } /** * resume_user_mode_work - Perform work before returning to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void resume_user_mode_work(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(task_work_pending(current))) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); } #endif /* LINUX_RESUME_USER_MODE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_USER_NAMESPACE_H #define _LINUX_USER_NAMESPACE_H #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> #define UID_GID_MAP_MAX_BASE_EXTENTS 5 #define UID_GID_MAP_MAX_EXTENTS 340 struct uid_gid_extent { u32 first; u32 lower_first; u32 count; }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ union { struct { struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; u32 nr_extents; }; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; }; }; }; #define USERNS_SETGROUPS_ALLOWED 1UL #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED struct ucounts; enum ucount_type { UCOUNT_USER_NAMESPACES, UCOUNT_PID_NAMESPACES, UCOUNT_UTS_NAMESPACES, UCOUNT_IPC_NAMESPACES, UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif #ifdef CONFIG_FANOTIFY UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif UCOUNT_COUNTS, }; enum rlimit_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, UCOUNT_RLIMIT_COUNTS, }; #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc; #endif struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; struct user_namespace *parent; int level; kuid_t owner; kgid_t group; struct ns_common ns; unsigned long flags; /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP * in its effective capability set at the child ns creation time. */ bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of * these pointers is controlled by keyring_sem. Once * user_keyring_register is set, it won't be changed, so it can be * accessed directly with READ_ONCE(). */ struct list_head keyring_name_list; struct key *user_keyring_register; struct rw_semaphore keyring_sem; #endif /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; #endif struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; long rlimit_max[UCOUNT_RLIMIT_COUNTS]; #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc *binfmt_misc; #endif } __randomize_layout; struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; atomic_t count; atomic_long_t ucount[UCOUNT_COUNTS]; atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; extern struct user_namespace init_user_ns; extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { return atomic_long_read(&ucounts->rlimit[type]); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type) { return READ_ONCE(ns->rlimit_max[type]); } static inline void set_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type, unsigned long max) { ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) refcount_inc(&ns->ns.count); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { if (ns && refcount_dec_and_test(&ns->ns.count)) __put_user_ns(ns); } struct seq_operations; extern const struct seq_operations proc_uid_seq_operations; extern const struct seq_operations proc_gid_seq_operations; extern const struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { return &init_user_ns; } static inline int create_user_ns(struct cred *new) { return -EINVAL; } static inline int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { if (unshare_flags & CLONE_NEWUSER) return -EINVAL; return 0; } static inline void put_user_ns(struct user_namespace *ns) { } static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } static inline bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { return true; } static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } static inline struct ns_common *ns_get_owner(struct ns_common *ns) { return ERR_PTR(-EPERM); } #endif #endif /* _LINUX_USER_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NetLabel Unlabeled Support * * This file defines functions for dealing with unlabeled packets for the * NetLabel system. The NetLabel system manages static and dynamic label * mappings for network protocols such as CIPSO and RIPSO. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 - 2008 */ #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/audit.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/security.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <asm/bug.h> #include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_addrlist.h" #include "netlabel_domainhash.h" #include "netlabel_unlabeled.h" #include "netlabel_mgmt.h" /* NOTE: at present we always use init's network namespace since we don't * presently support different namespaces even though the majority of * the functions in this file are "namespace safe" */ /* The unlabeled connection hash table which we use to map network interfaces * and addresses of unlabeled packets to a user specified secid value for the * LSM. The hash table is used to lookup the network interface entry * (struct netlbl_unlhsh_iface) and then the interface entry is used to * lookup an IP address match from an ordered list. If a network interface * match can not be found in the hash table then the default entry * (netlbl_unlhsh_def) is used. The IP address entry list * (struct netlbl_unlhsh_addr) is ordered such that the entries with a * larger netmask come first. */ struct netlbl_unlhsh_tbl { struct list_head *tbl; u32 size; }; #define netlbl_unlhsh_addr4_entry(iter) \ container_of(iter, struct netlbl_unlhsh_addr4, list) struct netlbl_unlhsh_addr4 { u32 secid; struct netlbl_af4list list; struct rcu_head rcu; }; #define netlbl_unlhsh_addr6_entry(iter) \ container_of(iter, struct netlbl_unlhsh_addr6, list) struct netlbl_unlhsh_addr6 { u32 secid; struct netlbl_af6list list; struct rcu_head rcu; }; struct netlbl_unlhsh_iface { int ifindex; struct list_head addr4_list; struct list_head addr6_list; u32 valid; struct list_head list; struct rcu_head rcu; }; /* Argument struct for netlbl_unlhsh_walk() */ struct netlbl_unlhsh_walk_arg { struct netlink_callback *nl_cb; struct sk_buff *skb; u32 seq; }; /* Unlabeled connection hash table */ /* updates should be so rare that having one spinlock for the entire * hash table should be okay */ static DEFINE_SPINLOCK(netlbl_unlhsh_lock); #define netlbl_unlhsh_rcu_deref(p) \ rcu_dereference_check(p, lockdep_is_held(&netlbl_unlhsh_lock)) static struct netlbl_unlhsh_tbl __rcu *netlbl_unlhsh; static struct netlbl_unlhsh_iface __rcu *netlbl_unlhsh_def; /* Accept unlabeled packets flag */ static u8 netlabel_unlabel_acceptflg; /* NetLabel Generic NETLINK unlabeled family */ static struct genl_family netlbl_unlabel_gnl_family; /* NetLabel Netlink attribute policy */ static const struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = { [NLBL_UNLABEL_A_ACPTFLG] = { .type = NLA_U8 }, [NLBL_UNLABEL_A_IPV6ADDR] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [NLBL_UNLABEL_A_IPV6MASK] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [NLBL_UNLABEL_A_IPV4ADDR] = { .type = NLA_BINARY, .len = sizeof(struct in_addr) }, [NLBL_UNLABEL_A_IPV4MASK] = { .type = NLA_BINARY, .len = sizeof(struct in_addr) }, [NLBL_UNLABEL_A_IFACE] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [NLBL_UNLABEL_A_SECCTX] = { .type = NLA_BINARY } }; /* * Unlabeled Connection Hash Table Functions */ /** * netlbl_unlhsh_free_iface - Frees an interface entry from the hash table * @entry: the entry's RCU field * * Description: * This function is designed to be used as a callback to the call_rcu() * function so that memory allocated to a hash table interface entry can be * released safely. It is important to note that this function does not free * the IPv4 and IPv6 address lists contained as part of an interface entry. It * is up to the rest of the code to make sure an interface entry is only freed * once it's address lists are empty. * */ static void netlbl_unlhsh_free_iface(struct rcu_head *entry) { struct netlbl_unlhsh_iface *iface; struct netlbl_af4list *iter4; struct netlbl_af4list *tmp4; #if IS_ENABLED(CONFIG_IPV6) struct netlbl_af6list *iter6; struct netlbl_af6list *tmp6; #endif /* IPv6 */ iface = container_of(entry, struct netlbl_unlhsh_iface, rcu); /* no need for locks here since we are the only one with access to this * structure */ netlbl_af4list_foreach_safe(iter4, tmp4, &iface->addr4_list) { netlbl_af4list_remove_entry(iter4); kfree(netlbl_unlhsh_addr4_entry(iter4)); } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_safe(iter6, tmp6, &iface->addr6_list) { netlbl_af6list_remove_entry(iter6); kfree(netlbl_unlhsh_addr6_entry(iter6)); } #endif /* IPv6 */ kfree(iface); } /** * netlbl_unlhsh_hash - Hashing function for the hash table * @ifindex: the network interface/device to hash * * Description: * This is the hashing function for the unlabeled hash table, it returns the * bucket number for the given device/interface. The caller is responsible for * ensuring that the hash table is protected with either a RCU read lock or * the hash table lock. * */ static u32 netlbl_unlhsh_hash(int ifindex) { return ifindex & (netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->size - 1); } /** * netlbl_unlhsh_search_iface - Search for a matching interface entry * @ifindex: the network interface * * Description: * Searches the unlabeled connection hash table and returns a pointer to the * interface entry which matches @ifindex, otherwise NULL is returned. The * caller is responsible for ensuring that the hash table is protected with * either a RCU read lock or the hash table lock. * */ static struct netlbl_unlhsh_iface *netlbl_unlhsh_search_iface(int ifindex) { u32 bkt; struct list_head *bkt_list; struct netlbl_unlhsh_iface *iter; bkt = netlbl_unlhsh_hash(ifindex); bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]; list_for_each_entry_rcu(iter, bkt_list, list, lockdep_is_held(&netlbl_unlhsh_lock)) if (iter->valid && iter->ifindex == ifindex) return iter; return NULL; } /** * netlbl_unlhsh_add_addr4 - Add a new IPv4 address entry to the hash table * @iface: the associated interface entry * @addr: IPv4 address in network byte order * @mask: IPv4 address mask in network byte order * @secid: LSM secid value for entry * * Description: * Add a new address entry into the unlabeled connection hash table using the * interface entry specified by @iface. On success zero is returned, otherwise * a negative value is returned. * */ static int netlbl_unlhsh_add_addr4(struct netlbl_unlhsh_iface *iface, const struct in_addr *addr, const struct in_addr *mask, u32 secid) { int ret_val; struct netlbl_unlhsh_addr4 *entry; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) return -ENOMEM; entry->list.addr = addr->s_addr & mask->s_addr; entry->list.mask = mask->s_addr; entry->list.valid = 1; entry->secid = secid; spin_lock(&netlbl_unlhsh_lock); ret_val = netlbl_af4list_add(&entry->list, &iface->addr4_list); spin_unlock(&netlbl_unlhsh_lock); if (ret_val != 0) kfree(entry); return ret_val; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_unlhsh_add_addr6 - Add a new IPv6 address entry to the hash table * @iface: the associated interface entry * @addr: IPv6 address in network byte order * @mask: IPv6 address mask in network byte order * @secid: LSM secid value for entry * * Description: * Add a new address entry into the unlabeled connection hash table using the * interface entry specified by @iface. On success zero is returned, otherwise * a negative value is returned. * */ static int netlbl_unlhsh_add_addr6(struct netlbl_unlhsh_iface *iface, const struct in6_addr *addr, const struct in6_addr *mask, u32 secid) { int ret_val; struct netlbl_unlhsh_addr6 *entry; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) return -ENOMEM; entry->list.addr = *addr; entry->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; entry->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; entry->list.addr.s6_addr32[2] &= mask->s6_addr32[2]; entry->list.addr.s6_addr32[3] &= mask->s6_addr32[3]; entry->list.mask = *mask; entry->list.valid = 1; entry->secid = secid; spin_lock(&netlbl_unlhsh_lock); ret_val = netlbl_af6list_add(&entry->list, &iface->addr6_list); spin_unlock(&netlbl_unlhsh_lock); if (ret_val != 0) kfree(entry); return 0; } #endif /* IPv6 */ /** * netlbl_unlhsh_add_iface - Adds a new interface entry to the hash table * @ifindex: network interface * * Description: * Add a new, empty, interface entry into the unlabeled connection hash table. * On success a pointer to the new interface entry is returned, on failure NULL * is returned. * */ static struct netlbl_unlhsh_iface *netlbl_unlhsh_add_iface(int ifindex) { u32 bkt; struct netlbl_unlhsh_iface *iface; iface = kzalloc(sizeof(*iface), GFP_ATOMIC); if (iface == NULL) return NULL; iface->ifindex = ifindex; INIT_LIST_HEAD(&iface->addr4_list); INIT_LIST_HEAD(&iface->addr6_list); iface->valid = 1; spin_lock(&netlbl_unlhsh_lock); if (ifindex > 0) { bkt = netlbl_unlhsh_hash(ifindex); if (netlbl_unlhsh_search_iface(ifindex) != NULL) goto add_iface_failure; list_add_tail_rcu(&iface->list, &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]); } else { INIT_LIST_HEAD(&iface->list); if (netlbl_unlhsh_rcu_deref(netlbl_unlhsh_def) != NULL) goto add_iface_failure; rcu_assign_pointer(netlbl_unlhsh_def, iface); } spin_unlock(&netlbl_unlhsh_lock); return iface; add_iface_failure: spin_unlock(&netlbl_unlhsh_lock); kfree(iface); return NULL; } /** * netlbl_unlhsh_add - Adds a new entry to the unlabeled connection hash table * @net: network namespace * @dev_name: interface name * @addr: IP address in network byte order * @mask: address mask in network byte order * @addr_len: length of address/mask (4 for IPv4, 16 for IPv6) * @secid: LSM secid value for the entry * @audit_info: NetLabel audit information * * Description: * Adds a new entry to the unlabeled connection hash table. Returns zero on * success, negative values on failure. * */ int netlbl_unlhsh_add(struct net *net, const char *dev_name, const void *addr, const void *mask, u32 addr_len, u32 secid, struct netlbl_audit *audit_info) { int ret_val; int ifindex; struct net_device *dev; struct netlbl_unlhsh_iface *iface; struct audit_buffer *audit_buf = NULL; char *secctx = NULL; u32 secctx_len; if (addr_len != sizeof(struct in_addr) && addr_len != sizeof(struct in6_addr)) return -EINVAL; rcu_read_lock(); if (dev_name != NULL) { dev = dev_get_by_name_rcu(net, dev_name); if (dev == NULL) { ret_val = -ENODEV; goto unlhsh_add_return; } ifindex = dev->ifindex; iface = netlbl_unlhsh_search_iface(ifindex); } else { ifindex = 0; iface = rcu_dereference(netlbl_unlhsh_def); } if (iface == NULL) { iface = netlbl_unlhsh_add_iface(ifindex); if (iface == NULL) { ret_val = -ENOMEM; goto unlhsh_add_return; } } audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCADD, audit_info); switch (addr_len) { case sizeof(struct in_addr): { const struct in_addr *addr4 = addr; const struct in_addr *mask4 = mask; ret_val = netlbl_unlhsh_add_addr4(iface, addr4, mask4, secid); if (audit_buf != NULL) netlbl_af4list_audit_addr(audit_buf, 1, dev_name, addr4->s_addr, mask4->s_addr); break; } #if IS_ENABLED(CONFIG_IPV6) case sizeof(struct in6_addr): { const struct in6_addr *addr6 = addr; const struct in6_addr *mask6 = mask; ret_val = netlbl_unlhsh_add_addr6(iface, addr6, mask6, secid); if (audit_buf != NULL) netlbl_af6list_audit_addr(audit_buf, 1, dev_name, addr6, mask6); break; } #endif /* IPv6 */ default: ret_val = -EINVAL; } if (ret_val == 0) atomic_inc(&netlabel_mgmt_protocount); unlhsh_add_return: rcu_read_unlock(); if (audit_buf != NULL) { if (security_secid_to_secctx(secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " sec_obj=%s", secctx); security_release_secctx(secctx, secctx_len); } audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0); audit_log_end(audit_buf); } return ret_val; } /** * netlbl_unlhsh_remove_addr4 - Remove an IPv4 address entry * @net: network namespace * @iface: interface entry * @addr: IP address * @mask: IP address mask * @audit_info: NetLabel audit information * * Description: * Remove an IP address entry from the unlabeled connection hash table. * Returns zero on success, negative values on failure. * */ static int netlbl_unlhsh_remove_addr4(struct net *net, struct netlbl_unlhsh_iface *iface, const struct in_addr *addr, const struct in_addr *mask, struct netlbl_audit *audit_info) { struct netlbl_af4list *list_entry; struct netlbl_unlhsh_addr4 *entry; struct audit_buffer *audit_buf; struct net_device *dev; char *secctx; u32 secctx_len; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af4list_remove(addr->s_addr, mask->s_addr, &iface->addr4_list); spin_unlock(&netlbl_unlhsh_lock); if (list_entry != NULL) entry = netlbl_unlhsh_addr4_entry(list_entry); else entry = NULL; audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL, audit_info); if (audit_buf != NULL) { dev = dev_get_by_index(net, iface->ifindex); netlbl_af4list_audit_addr(audit_buf, 1, (dev != NULL ? dev->name : NULL), addr->s_addr, mask->s_addr); dev_put(dev); if (entry != NULL && security_secid_to_secctx(entry->secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " sec_obj=%s", secctx); security_release_secctx(secctx, secctx_len); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); } if (entry == NULL) return -ENOENT; kfree_rcu(entry, rcu); return 0; } #if IS_ENABLED(CONFIG_IPV6) /** * netlbl_unlhsh_remove_addr6 - Remove an IPv6 address entry * @net: network namespace * @iface: interface entry * @addr: IP address * @mask: IP address mask * @audit_info: NetLabel audit information * * Description: * Remove an IP address entry from the unlabeled connection hash table. * Returns zero on success, negative values on failure. * */ static int netlbl_unlhsh_remove_addr6(struct net *net, struct netlbl_unlhsh_iface *iface, const struct in6_addr *addr, const struct in6_addr *mask, struct netlbl_audit *audit_info) { struct netlbl_af6list *list_entry; struct netlbl_unlhsh_addr6 *entry; struct audit_buffer *audit_buf; struct net_device *dev; char *secctx; u32 secctx_len; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af6list_remove(addr, mask, &iface->addr6_list); spin_unlock(&netlbl_unlhsh_lock); if (list_entry != NULL) entry = netlbl_unlhsh_addr6_entry(list_entry); else entry = NULL; audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL, audit_info); if (audit_buf != NULL) { dev = dev_get_by_index(net, iface->ifindex); netlbl_af6list_audit_addr(audit_buf, 1, (dev != NULL ? dev->name : NULL), addr, mask); dev_put(dev); if (entry != NULL && security_secid_to_secctx(entry->secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " sec_obj=%s", secctx); security_release_secctx(secctx, secctx_len); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); } if (entry == NULL) return -ENOENT; kfree_rcu(entry, rcu); return 0; } #endif /* IPv6 */ /** * netlbl_unlhsh_condremove_iface - Remove an interface entry * @iface: the interface entry * * Description: * Remove an interface entry from the unlabeled connection hash table if it is * empty. An interface entry is considered to be empty if there are no * address entries assigned to it. * */ static void netlbl_unlhsh_condremove_iface(struct netlbl_unlhsh_iface *iface) { struct netlbl_af4list *iter4; #if IS_ENABLED(CONFIG_IPV6) struct netlbl_af6list *iter6; #endif /* IPv6 */ spin_lock(&netlbl_unlhsh_lock); netlbl_af4list_foreach_rcu(iter4, &iface->addr4_list) goto unlhsh_condremove_failure; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(iter6, &iface->addr6_list) goto unlhsh_condremove_failure; #endif /* IPv6 */ iface->valid = 0; if (iface->ifindex > 0) list_del_rcu(&iface->list); else RCU_INIT_POINTER(netlbl_unlhsh_def, NULL); spin_unlock(&netlbl_unlhsh_lock); call_rcu(&iface->rcu, netlbl_unlhsh_free_iface); return; unlhsh_condremove_failure: spin_unlock(&netlbl_unlhsh_lock); } /** * netlbl_unlhsh_remove - Remove an entry from the unlabeled hash table * @net: network namespace * @dev_name: interface name * @addr: IP address in network byte order * @mask: address mask in network byte order * @addr_len: length of address/mask (4 for IPv4, 16 for IPv6) * @audit_info: NetLabel audit information * * Description: * Removes and existing entry from the unlabeled connection hash table. * Returns zero on success, negative values on failure. * */ int netlbl_unlhsh_remove(struct net *net, const char *dev_name, const void *addr, const void *mask, u32 addr_len, struct netlbl_audit *audit_info) { int ret_val; struct net_device *dev; struct netlbl_unlhsh_iface *iface; if (addr_len != sizeof(struct in_addr) && addr_len != sizeof(struct in6_addr)) return -EINVAL; rcu_read_lock(); if (dev_name != NULL) { dev = dev_get_by_name_rcu(net, dev_name); if (dev == NULL) { ret_val = -ENODEV; goto unlhsh_remove_return; } iface = netlbl_unlhsh_search_iface(dev->ifindex); } else iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL) { ret_val = -ENOENT; goto unlhsh_remove_return; } switch (addr_len) { case sizeof(struct in_addr): ret_val = netlbl_unlhsh_remove_addr4(net, iface, addr, mask, audit_info); break; #if IS_ENABLED(CONFIG_IPV6) case sizeof(struct in6_addr): ret_val = netlbl_unlhsh_remove_addr6(net, iface, addr, mask, audit_info); break; #endif /* IPv6 */ default: ret_val = -EINVAL; } if (ret_val == 0) { netlbl_unlhsh_condremove_iface(iface); atomic_dec(&netlabel_mgmt_protocount); } unlhsh_remove_return: rcu_read_unlock(); return ret_val; } /* * General Helper Functions */ /** * netlbl_unlhsh_netdev_handler - Network device notification handler * @this: notifier block * @event: the event * @ptr: the netdevice notifier info (cast to void) * * Description: * Handle network device events, although at present all we care about is a * network device going away. In the case of a device going away we clear any * related entries from the unlabeled connection hash table. * */ static int netlbl_unlhsh_netdev_handler(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netlbl_unlhsh_iface *iface = NULL; if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; /* XXX - should this be a check for NETDEV_DOWN or _UNREGISTER? */ if (event == NETDEV_DOWN) { spin_lock(&netlbl_unlhsh_lock); iface = netlbl_unlhsh_search_iface(dev->ifindex); if (iface != NULL && iface->valid) { iface->valid = 0; list_del_rcu(&iface->list); } else iface = NULL; spin_unlock(&netlbl_unlhsh_lock); } if (iface != NULL) call_rcu(&iface->rcu, netlbl_unlhsh_free_iface); return NOTIFY_DONE; } /** * netlbl_unlabel_acceptflg_set - Set the unlabeled accept flag * @value: desired value * @audit_info: NetLabel audit information * * Description: * Set the value of the unlabeled accept flag to @value. * */ static void netlbl_unlabel_acceptflg_set(u8 value, struct netlbl_audit *audit_info) { struct audit_buffer *audit_buf; u8 old_val; old_val = netlabel_unlabel_acceptflg; netlabel_unlabel_acceptflg = value; audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_ALLOW, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, " unlbl_accept=%u old=%u", value, old_val); audit_log_end(audit_buf); } } /** * netlbl_unlabel_addrinfo_get - Get the IPv4/6 address information * @info: the Generic NETLINK info block * @addr: the IP address * @mask: the IP address mask * @len: the address length * * Description: * Examine the Generic NETLINK message and extract the IP address information. * Returns zero on success, negative values on failure. * */ static int netlbl_unlabel_addrinfo_get(struct genl_info *info, void **addr, void **mask, u32 *len) { u32 addr_len; if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] && info->attrs[NLBL_UNLABEL_A_IPV4MASK]) { addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]); if (addr_len != sizeof(struct in_addr) && addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK])) return -EINVAL; *len = addr_len; *addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]); *mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4MASK]); return 0; } else if (info->attrs[NLBL_UNLABEL_A_IPV6ADDR]) { addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]); if (addr_len != sizeof(struct in6_addr) && addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV6MASK])) return -EINVAL; *len = addr_len; *addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]); *mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6MASK]); return 0; } return -EINVAL; } /* * NetLabel Command Handlers */ /** * netlbl_unlabel_accept - Handle an ACCEPT message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated ACCEPT message and set the accept flag accordingly. * Returns zero on success, negative values on failure. * */ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) { u8 value; struct netlbl_audit audit_info; if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) { value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]); if (value == 1 || value == 0) { netlbl_netlink_auditinfo(&audit_info); netlbl_unlabel_acceptflg_set(value, &audit_info); return 0; } } return -EINVAL; } /** * netlbl_unlabel_list - Handle a LIST message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated LIST message and respond with the current status. * Returns zero on success, negative values on failure. * */ static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct sk_buff *ans_skb; void *data; ans_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (ans_skb == NULL) goto list_failure; data = genlmsg_put_reply(ans_skb, info, &netlbl_unlabel_gnl_family, 0, NLBL_UNLABEL_C_LIST); if (data == NULL) { ret_val = -ENOMEM; goto list_failure; } ret_val = nla_put_u8(ans_skb, NLBL_UNLABEL_A_ACPTFLG, netlabel_unlabel_acceptflg); if (ret_val != 0) goto list_failure; genlmsg_end(ans_skb, data); return genlmsg_reply(ans_skb, info); list_failure: kfree_skb(ans_skb); return ret_val; } /** * netlbl_unlabel_staticadd - Handle a STATICADD message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICADD message and add a new unlabeled * connection entry to the hash table. Returns zero on success, negative * values on failure. * */ static int netlbl_unlabel_staticadd(struct sk_buff *skb, struct genl_info *info) { int ret_val; char *dev_name; void *addr; void *mask; u32 addr_len; u32 secid; struct netlbl_audit audit_info; /* Don't allow users to add both IPv4 and IPv6 addresses for a * single entry. However, allow users to create two entries, one each * for IPv4 and IPv6, with the same LSM security context which should * achieve the same result. */ if (!info->attrs[NLBL_UNLABEL_A_SECCTX] || !info->attrs[NLBL_UNLABEL_A_IFACE] || !((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; dev_name = nla_data(info->attrs[NLBL_UNLABEL_A_IFACE]); ret_val = security_secctx_to_secid( nla_data(info->attrs[NLBL_UNLABEL_A_SECCTX]), nla_len(info->attrs[NLBL_UNLABEL_A_SECCTX]), &secid); if (ret_val != 0) return ret_val; return netlbl_unlhsh_add(&init_net, dev_name, addr, mask, addr_len, secid, &audit_info); } /** * netlbl_unlabel_staticadddef - Handle a STATICADDDEF message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICADDDEF message and add a new default * unlabeled connection entry. Returns zero on success, negative values on * failure. * */ static int netlbl_unlabel_staticadddef(struct sk_buff *skb, struct genl_info *info) { int ret_val; void *addr; void *mask; u32 addr_len; u32 secid; struct netlbl_audit audit_info; /* Don't allow users to add both IPv4 and IPv6 addresses for a * single entry. However, allow users to create two entries, one each * for IPv4 and IPv6, with the same LSM security context which should * achieve the same result. */ if (!info->attrs[NLBL_UNLABEL_A_SECCTX] || !((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; ret_val = security_secctx_to_secid( nla_data(info->attrs[NLBL_UNLABEL_A_SECCTX]), nla_len(info->attrs[NLBL_UNLABEL_A_SECCTX]), &secid); if (ret_val != 0) return ret_val; return netlbl_unlhsh_add(&init_net, NULL, addr, mask, addr_len, secid, &audit_info); } /** * netlbl_unlabel_staticremove - Handle a STATICREMOVE message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICREMOVE message and remove the specified * unlabeled connection entry. Returns zero on success, negative values on * failure. * */ static int netlbl_unlabel_staticremove(struct sk_buff *skb, struct genl_info *info) { int ret_val; char *dev_name; void *addr; void *mask; u32 addr_len; struct netlbl_audit audit_info; /* See the note in netlbl_unlabel_staticadd() about not allowing both * IPv4 and IPv6 in the same entry. */ if (!info->attrs[NLBL_UNLABEL_A_IFACE] || !((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; dev_name = nla_data(info->attrs[NLBL_UNLABEL_A_IFACE]); return netlbl_unlhsh_remove(&init_net, dev_name, addr, mask, addr_len, &audit_info); } /** * netlbl_unlabel_staticremovedef - Handle a STATICREMOVEDEF message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated STATICREMOVEDEF message and remove the default * unlabeled connection entry. Returns zero on success, negative values on * failure. * */ static int netlbl_unlabel_staticremovedef(struct sk_buff *skb, struct genl_info *info) { int ret_val; void *addr; void *mask; u32 addr_len; struct netlbl_audit audit_info; /* See the note in netlbl_unlabel_staticadd() about not allowing both * IPv4 and IPv6 in the same entry. */ if (!((!info->attrs[NLBL_UNLABEL_A_IPV4ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV4MASK]) ^ (!info->attrs[NLBL_UNLABEL_A_IPV6ADDR] || !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) return ret_val; return netlbl_unlhsh_remove(&init_net, NULL, addr, mask, addr_len, &audit_info); } /** * netlbl_unlabel_staticlist_gen - Generate messages for STATICLIST[DEF] * @cmd: command/message * @iface: the interface entry * @addr4: the IPv4 address entry * @addr6: the IPv6 address entry * @arg: the netlbl_unlhsh_walk_arg structure * * Description: * This function is designed to be used to generate a response for a * STATICLIST or STATICLISTDEF message. When called either @addr4 or @addr6 * can be specified, not both, the other unspecified entry should be set to * NULL by the caller. Returns the size of the message on success, negative * values on failure. * */ static int netlbl_unlabel_staticlist_gen(u32 cmd, const struct netlbl_unlhsh_iface *iface, const struct netlbl_unlhsh_addr4 *addr4, const struct netlbl_unlhsh_addr6 *addr6, void *arg) { int ret_val = -ENOMEM; struct netlbl_unlhsh_walk_arg *cb_arg = arg; struct net_device *dev; void *data; u32 secid; char *secctx; u32 secctx_len; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_unlabel_gnl_family, NLM_F_MULTI, cmd); if (data == NULL) goto list_cb_failure; if (iface->ifindex > 0) { dev = dev_get_by_index(&init_net, iface->ifindex); if (!dev) { ret_val = -ENODEV; goto list_cb_failure; } ret_val = nla_put_string(cb_arg->skb, NLBL_UNLABEL_A_IFACE, dev->name); dev_put(dev); if (ret_val != 0) goto list_cb_failure; } if (addr4) { struct in_addr addr_struct; addr_struct.s_addr = addr4->list.addr; ret_val = nla_put_in_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV4ADDR, addr_struct.s_addr); if (ret_val != 0) goto list_cb_failure; addr_struct.s_addr = addr4->list.mask; ret_val = nla_put_in_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV4MASK, addr_struct.s_addr); if (ret_val != 0) goto list_cb_failure; secid = addr4->secid; } else { ret_val = nla_put_in6_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV6ADDR, &addr6->list.addr); if (ret_val != 0) goto list_cb_failure; ret_val = nla_put_in6_addr(cb_arg->skb, NLBL_UNLABEL_A_IPV6MASK, &addr6->list.mask); if (ret_val != 0) goto list_cb_failure; secid = addr6->secid; } ret_val = security_secid_to_secctx(secid, &secctx, &secctx_len); if (ret_val != 0) goto list_cb_failure; ret_val = nla_put(cb_arg->skb, NLBL_UNLABEL_A_SECCTX, secctx_len, secctx); security_release_secctx(secctx, secctx_len); if (ret_val != 0) goto list_cb_failure; cb_arg->seq++; genlmsg_end(cb_arg->skb, data); return 0; list_cb_failure: genlmsg_cancel(cb_arg->skb, data); return ret_val; } /** * netlbl_unlabel_staticlist - Handle a STATICLIST message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated STATICLIST message and dump the unlabeled * connection hash table in a form suitable for use in a kernel generated * STATICLIST message. Returns the length of @skb. * */ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; u32 skip_addr4 = cb->args[2]; u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) u32 skip_addr6 = cb->args[3]; struct netlbl_af6list *addr6; #endif cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); for (iter_bkt = skip_bkt; iter_bkt < rcu_dereference(netlbl_unlhsh)->size; iter_bkt++) { iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt]; list_for_each_entry_rcu(iface, iter_list, list) { if (!iface->valid || iter_chain++ < skip_chain) continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { if (iter_addr4++ < skip_addr4) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, iface, netlbl_unlhsh_addr4_entry(addr4), NULL, &cb_arg) < 0) { iter_addr4--; iter_chain--; goto unlabel_staticlist_return; } } iter_addr4 = 0; skip_addr4 = 0; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { if (iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, iface, NULL, netlbl_unlhsh_addr6_entry(addr6), &cb_arg) < 0) { iter_addr6--; iter_chain--; goto unlabel_staticlist_return; } } iter_addr6 = 0; skip_addr6 = 0; #endif /* IPv6 */ } iter_chain = 0; skip_chain = 0; } unlabel_staticlist_return: rcu_read_unlock(); cb->args[0] = iter_bkt; cb->args[1] = iter_chain; cb->args[2] = iter_addr4; cb->args[3] = iter_addr6; return skb->len; } /** * netlbl_unlabel_staticlistdef - Handle a STATICLISTDEF message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated STATICLISTDEF message and dump the default * unlabeled connection entry in a form suitable for use in a kernel generated * STATICLISTDEF message. Returns the length of @skb. * */ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_unlhsh_walk_arg cb_arg; struct netlbl_unlhsh_iface *iface; u32 iter_addr4 = 0, iter_addr6 = 0; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) struct netlbl_af6list *addr6; #endif cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL || !iface->valid) goto unlabel_staticlistdef_return; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { if (iter_addr4++ < cb->args[0]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, netlbl_unlhsh_addr4_entry(addr4), NULL, &cb_arg) < 0) { iter_addr4--; goto unlabel_staticlistdef_return; } } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { if (iter_addr6++ < cb->args[1]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, NULL, netlbl_unlhsh_addr6_entry(addr6), &cb_arg) < 0) { iter_addr6--; goto unlabel_staticlistdef_return; } } #endif /* IPv6 */ unlabel_staticlistdef_return: rcu_read_unlock(); cb->args[0] = iter_addr4; cb->args[1] = iter_addr6; return skb->len; } /* * NetLabel Generic NETLINK Command Definitions */ static const struct genl_small_ops netlbl_unlabel_genl_ops[] = { { .cmd = NLBL_UNLABEL_C_STATICADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticadd, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICREMOVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticremove, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICLIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_unlabel_staticlist, }, { .cmd = NLBL_UNLABEL_C_STATICADDDEF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticadddef, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICREMOVEDEF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_staticremovedef, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_STATICLISTDEF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_unlabel_staticlistdef, }, { .cmd = NLBL_UNLABEL_C_ACCEPT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_unlabel_accept, .dumpit = NULL, }, { .cmd = NLBL_UNLABEL_C_LIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = netlbl_unlabel_list, .dumpit = NULL, }, }; static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = { .hdrsize = 0, .name = NETLBL_NLTYPE_UNLABELED_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_UNLABEL_A_MAX, .policy = netlbl_unlabel_genl_policy, .module = THIS_MODULE, .small_ops = netlbl_unlabel_genl_ops, .n_small_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops), .resv_start_op = NLBL_UNLABEL_C_STATICLISTDEF + 1, }; /* * NetLabel Generic NETLINK Protocol Functions */ /** * netlbl_unlabel_genl_init - Register the Unlabeled NetLabel component * * Description: * Register the unlabeled packet NetLabel component with the Generic NETLINK * mechanism. Returns zero on success, negative values on failure. * */ int __init netlbl_unlabel_genl_init(void) { return genl_register_family(&netlbl_unlabel_gnl_family); } /* * NetLabel KAPI Hooks */ static struct notifier_block netlbl_unlhsh_netdev_notifier = { .notifier_call = netlbl_unlhsh_netdev_handler, }; /** * netlbl_unlabel_init - Initialize the unlabeled connection hash table * @size: the number of bits to use for the hash buckets * * Description: * Initializes the unlabeled connection hash table and registers a network * device notification handler. This function should only be called by the * NetLabel subsystem itself during initialization. Returns zero on success, * non-zero values on error. * */ int __init netlbl_unlabel_init(u32 size) { u32 iter; struct netlbl_unlhsh_tbl *hsh_tbl; if (size == 0) return -EINVAL; hsh_tbl = kmalloc(sizeof(*hsh_tbl), GFP_KERNEL); if (hsh_tbl == NULL) return -ENOMEM; hsh_tbl->size = 1 << size; hsh_tbl->tbl = kcalloc(hsh_tbl->size, sizeof(struct list_head), GFP_KERNEL); if (hsh_tbl->tbl == NULL) { kfree(hsh_tbl); return -ENOMEM; } for (iter = 0; iter < hsh_tbl->size; iter++) INIT_LIST_HEAD(&hsh_tbl->tbl[iter]); spin_lock(&netlbl_unlhsh_lock); rcu_assign_pointer(netlbl_unlhsh, hsh_tbl); spin_unlock(&netlbl_unlhsh_lock); register_netdevice_notifier(&netlbl_unlhsh_netdev_notifier); return 0; } /** * netlbl_unlabel_getattr - Get the security attributes for an unlabled packet * @skb: the packet * @family: protocol family * @secattr: the security attributes * * Description: * Determine the security attributes, if any, for an unlabled packet and return * them in @secattr. Returns zero on success and negative values on failure. * */ int netlbl_unlabel_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr) { struct netlbl_unlhsh_iface *iface; rcu_read_lock(); iface = netlbl_unlhsh_search_iface(skb->skb_iif); if (iface == NULL) iface = rcu_dereference(netlbl_unlhsh_def); if (iface == NULL || !iface->valid) goto unlabel_getattr_nolabel; #if IS_ENABLED(CONFIG_IPV6) /* When resolving a fallback label, check the sk_buff version as * it is possible (e.g. SCTP) to have family = PF_INET6 while * receiving ip_hdr(skb)->version = 4. */ if (family == PF_INET6 && ip_hdr(skb)->version == 4) family = PF_INET; #endif /* IPv6 */ switch (family) { case PF_INET: { struct iphdr *hdr4; struct netlbl_af4list *addr4; hdr4 = ip_hdr(skb); addr4 = netlbl_af4list_search(hdr4->saddr, &iface->addr4_list); if (addr4 == NULL) goto unlabel_getattr_nolabel; secattr->attr.secid = netlbl_unlhsh_addr4_entry(addr4)->secid; break; } #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: { struct ipv6hdr *hdr6; struct netlbl_af6list *addr6; hdr6 = ipv6_hdr(skb); addr6 = netlbl_af6list_search(&hdr6->saddr, &iface->addr6_list); if (addr6 == NULL) goto unlabel_getattr_nolabel; secattr->attr.secid = netlbl_unlhsh_addr6_entry(addr6)->secid; break; } #endif /* IPv6 */ default: goto unlabel_getattr_nolabel; } rcu_read_unlock(); secattr->flags |= NETLBL_SECATTR_SECID; secattr->type = NETLBL_NLTYPE_UNLABELED; return 0; unlabel_getattr_nolabel: rcu_read_unlock(); if (netlabel_unlabel_acceptflg == 0) return -ENOMSG; secattr->type = NETLBL_NLTYPE_UNLABELED; return 0; } /** * netlbl_unlabel_defconf - Set the default config to allow unlabeled packets * * Description: * Set the default NetLabel configuration to allow incoming unlabeled packets * and to send unlabeled network traffic by default. * */ int __init netlbl_unlabel_defconf(void) { int ret_val; struct netlbl_dom_map *entry; struct netlbl_audit audit_info; /* Only the kernel is allowed to call this function and the only time * it is called is at bootup before the audit subsystem is reporting * messages so don't worry to much about these values. */ security_current_getlsmprop_subj(&audit_info.prop); audit_info.loginuid = GLOBAL_ROOT_UID; audit_info.sessionid = 0; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) return -ENOMEM; entry->family = AF_UNSPEC; entry->def.type = NETLBL_NLTYPE_UNLABELED; ret_val = netlbl_domhsh_add_default(entry, &audit_info); if (ret_val != 0) return ret_val; netlbl_unlabel_acceptflg_set(1, &audit_info); return 0; } |
| 495 380 462 380 380 463 461 113 398 240 240 240 398 399 16 384 180 2 240 240 240 384 195 198 52 367 3 3 163 278 278 277 9 269 17 17 17 17 17 17 17 12 168 380 146 12 9 163 163 195 196 115 453 454 113 113 16 16 16 16 16 17 4 4 380 16 380 380 380 380 379 3 3 3 3 30 53 54 53 30 593 918 922 767 335 953 43 2 3 915 337 265 53 48 61 149 334 333 336 147 221 187 163 163 163 356 226 225 399 399 277 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 | // SPDX-License-Identifier: GPL-2.0-only /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux hook function implementations. * * Authors: Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com> * Eric Paris <eparis@redhat.com> * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * <dgoeddel@trustedcs.com> * Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2007 Hitachi Software Engineering Co., Ltd. * Yuichi Nakamura <ynakam@hitachisoft.jp> * Copyright (C) 2016 Mellanox Technologies */ #include <linux/init.h> #include <linux/kd.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/lsm_hooks.h> #include <linux/xattr.h> #include <linux/capability.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/swap.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/dcache.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ #include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/structs.h> #include <linux/quota.h> #include <linux/un.h> /* for Unix socket types */ #include <net/af_unix.h> /* for Unix socket types */ #include <linux/parser.h> #include <linux/nfs_mount.h> #include <net/ipv6.h> #include <linux/hugetlb.h> #include <linux/personality.h> #include <linux/audit.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/posix-timers.h> #include <linux/syslog.h> #include <linux/user_namespace.h> #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> #include <uapi/linux/shm.h> #include <linux/bpf.h> #include <linux/kernfs.h> #include <linux/stringhash.h> /* for hashlen_string() */ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> #include <linux/io_uring/cmd.h> #include <uapi/linux/lsm.h> #include "avc.h" #include "objsec.h" #include "netif.h" #include "netnode.h" #include "netport.h" #include "ibpkey.h" #include "xfrm.h" #include "netlabel.h" #include "audit.h" #include "avc_ss.h" #define SELINUX_INODE_INIT_XATTRS 1 struct selinux_state selinux_state; /* SECMARK reference count */ static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static int selinux_enforcing_boot __initdata; static int __init enforcing_setup(char *str) { unsigned long enforcing; if (!kstrtoul(str, 0, &enforcing)) selinux_enforcing_boot = enforcing ? 1 : 0; return 1; } __setup("enforcing=", enforcing_setup); #else #define selinux_enforcing_boot 1 #endif int selinux_enabled_boot __initdata = 1; #ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM static int __init selinux_enabled_setup(char *str) { unsigned long enabled; if (!kstrtoul(str, 0, &enabled)) selinux_enabled_boot = enabled ? 1 : 0; return 1; } __setup("selinux=", selinux_enabled_setup); #endif static int __init checkreqprot_setup(char *str) { unsigned long checkreqprot; if (!kstrtoul(str, 0, &checkreqprot)) { if (checkreqprot) pr_err("SELinux: checkreqprot set to 1 via kernel parameter. This is no longer supported.\n"); } return 1; } __setup("checkreqprot=", checkreqprot_setup); /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * * Description: * This function checks the SECMARK reference counter to see if any SECMARK * targets are currently configured, if the reference counter is greater than * zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is * enabled, false (0) if SECMARK is disabled. If the always_check_network * policy capability is enabled, SECMARK is always considered enabled. * */ static int selinux_secmark_enabled(void) { return (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } /** * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled * * Description: * This function checks if NetLabel or labeled IPSEC is enabled. Returns true * (1) if any are enabled or false (0) if neither are enabled. If the * always_check_network policy capability is enabled, peer labeling * is always considered enabled. * */ static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_netif_flush(); sel_netnode_flush(); sel_netport_flush(); synchronize_net(); } return 0; } static int selinux_lsm_notifier_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_ib_pkey_flush(); call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); } return 0; } /* * initialise the security for the init task */ static void cred_init_security(void) { struct task_security_struct *tsec; tsec = selinux_cred(unrcu_pointer(current->real_cred)); tsec->osid = tsec->sid = SECINITSID_KERNEL; } /* * get the security ID of a set of credentials */ static inline u32 cred_sid(const struct cred *cred) { const struct task_security_struct *tsec; tsec = selinux_cred(cred); return tsec->sid; } static void __ad_net_init(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, struct sock *sk, u16 family) { ad->type = LSM_AUDIT_DATA_NET; ad->u.net = net; net->netif = ifindex; net->sk = sk; net->family = family; } static void ad_net_init_from_sk(struct common_audit_data *ad, struct lsm_network_audit *net, struct sock *sk) { __ad_net_init(ad, net, 0, sk, 0); } static void ad_net_init_from_iif(struct common_audit_data *ad, struct lsm_network_audit *net, int ifindex, u16 family) { __ad_net_init(ad, net, ifindex, NULL, family); } /* * get the objective security ID of a task */ static inline u32 task_sid_obj(const struct task_struct *task) { u32 sid; rcu_read_lock(); sid = cred_sid(__task_cred(task)); rcu_read_unlock(); return sid; } static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* * Try reloading inode security labels that have been marked as invalid. The * @may_sleep parameter indicates when sleeping and thus reloading labels is * allowed; when set to false, returns -ECHILD when the label is * invalid. The @dentry parameter should be set to a dentry of the inode. */ static int __inode_security_revalidate(struct inode *inode, struct dentry *dentry, bool may_sleep) { struct inode_security_struct *isec = selinux_inode(inode); might_sleep_if(may_sleep); /* * The check of isec->initialized below is racy but * inode_doinit_with_dentry() will recheck with * isec->lock held. */ if (selinux_initialized() && data_race(isec->initialized != LABEL_INITIALIZED)) { if (!may_sleep) return -ECHILD; /* * Try reloading the inode security label. This will fail if * @opt_dentry is NULL and no dentry for this inode can be * found; in that case, continue using the old label. */ inode_doinit_with_dentry(inode, dentry); } return 0; } static struct inode_security_struct *inode_security_novalidate(struct inode *inode) { return selinux_inode(inode); } static struct inode_security_struct *inode_security_rcu(struct inode *inode, bool rcu) { int error; error = __inode_security_revalidate(inode, NULL, !rcu); if (error) return ERR_PTR(error); return selinux_inode(inode); } /* * Get the security label of an inode. */ static struct inode_security_struct *inode_security(struct inode *inode) { __inode_security_revalidate(inode, NULL, true); return selinux_inode(inode); } static struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); return selinux_inode(inode); } /* * Get the security label of a dentry's backing inode. */ static struct inode_security_struct *backing_inode_security(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); __inode_security_revalidate(inode, dentry, true); return selinux_inode(inode); } static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); struct superblock_security_struct *sbsec; if (!isec) return; sbsec = selinux_superblock(inode->i_sb); /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste * time taking a lock doing nothing. * * The list_del_init() function can be safely called more than once. * It should not be possible for this function to be called with * concurrent list_add(), but for better safety against future changes * in the code, we use list_empty_careful() here. */ if (!list_empty_careful(&isec->list)) { spin_lock(&sbsec->isec_lock); list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } } struct selinux_mnt_opts { u32 fscontext_sid; u32 context_sid; u32 rootcontext_sid; u32 defcontext_sid; }; static void selinux_free_mnt_opts(void *mnt_opts) { kfree(mnt_opts); } enum { Opt_error = -1, Opt_context = 0, Opt_defcontext = 1, Opt_fscontext = 2, Opt_rootcontext = 3, Opt_seclabel = 4, }; #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg} static const struct { const char *name; int len; int opt; bool has_arg; } tokens[] = { A(context, true), A(fscontext, true), A(defcontext, true), A(rootcontext, true), A(seclabel, false), }; #undef A static int match_opt_prefix(char *s, int l, char **arg) { int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; if (len > l || memcmp(s, tokens[i].name, len)) continue; if (tokens[i].has_arg) { if (len == l || s[len] != '=') continue; *arg = s + len + 1; } else if (len != l) continue; return tokens[i].opt; } return Opt_error; } #define SEL_MOUNT_FAIL_MSG "SELinux: duplicate or incompatible mount options\n" static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, NULL); return rc; } static int selinux_is_genfs_special_handling(struct super_block *sb) { /* Special handling. Genfs but also in-core setxattr handler */ return !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs") || (selinux_policycap_cgroupseclabel() && (!strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2"))); } static int selinux_is_sblabel_mnt(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * IMPORTANT: Double-check logic in this function when adding a new * SECURITY_FS_USE_* definition! */ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); switch (sbsec->behavior) { case SECURITY_FS_USE_XATTR: case SECURITY_FS_USE_TRANS: case SECURITY_FS_USE_TASK: case SECURITY_FS_USE_NATIVE: return 1; case SECURITY_FS_USE_GENFS: return selinux_is_genfs_special_handling(sb); /* Never allow relabeling on context mounts */ case SECURITY_FS_USE_MNTPOINT: case SECURITY_FS_USE_NONE: default: return 0; } } static int sb_check_xattr_support(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); u32 sid; int rc; /* * Make sure that the xattr handler exists and that no * error other than -ENODATA is returned by getxattr on * the root directory. -ENODATA is ok, as this may be * the first boot of the SELinux kernel before we have * assigned xattr values to the filesystem. */ if (!(root_inode->i_opflags & IOP_XATTR)) { pr_warn("SELinux: (dev %s, type %s) has no xattr support\n", sb->s_id, sb->s_type->name); goto fallback; } rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) { pr_warn("SELinux: (dev %s, type %s) has no security xattr handler\n", sb->s_id, sb->s_type->name); goto fallback; } else { pr_warn("SELinux: (dev %s, type %s) getxattr errno %d\n", sb->s_id, sb->s_type->name, -rc); return rc; } } return 0; fallback: /* No xattr support - try to fallback to genfs if possible. */ rc = security_genfs_sid(sb->s_type->name, "/", SECCLASS_DIR, &sid); if (rc) return -EOPNOTSUPP; pr_warn("SELinux: (dev %s, type %s) falling back to genfs\n", sb->s_id, sb->s_type->name); sbsec->behavior = SECURITY_FS_USE_GENFS; sbsec->sid = sid; return 0; } static int sb_finish_set_opts(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); int rc = 0; if (sbsec->behavior == SECURITY_FS_USE_XATTR) { rc = sb_check_xattr_support(sb); if (rc) return rc; } sbsec->flags |= SE_SBINITIALIZED; /* * Explicitly set or clear SBLABEL_MNT. It's not sufficient to simply * leave the flag untouched because sb_clone_mnt_opts might be handing * us a superblock that needs the flag to be cleared. */ if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; else sbsec->flags &= ~SBLABEL_MNT; /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); /* Initialize any other inodes associated with the superblock, e.g. inodes created prior to initial policy load or inodes created during get_sb by a pseudo filesystem that directly populates itself. */ spin_lock(&sbsec->isec_lock); while (!list_empty(&sbsec->isec_head)) { struct inode_security_struct *isec = list_first_entry(&sbsec->isec_head, struct inode_security_struct, list); struct inode *inode = isec->inode; list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { if (!IS_PRIVATE(inode)) inode_doinit_with_dentry(inode, NULL); iput(inode); } spin_lock(&sbsec->isec_lock); } spin_unlock(&sbsec->isec_lock); return rc; } static int bad_option(struct superblock_security_struct *sbsec, char flag, u32 old_sid, u32 new_sid) { char mnt_flags = sbsec->flags & SE_MNTMASK; /* check if the old mount command had the same options */ if (sbsec->flags & SE_SBINITIALIZED) if (!(sbsec->flags & flag) || (old_sid != new_sid)) return 1; /* check if we were passed the same options twice, * aka someone passed context=a,context=b */ if (!(sbsec->flags & SE_SBINITIALIZED)) if (mnt_flags & flag) return 1; return 0; } /* * Allow filesystems with binary mount data to explicitly set mount point * labeling information. */ static int selinux_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; struct selinux_mnt_opts *opts = mnt_opts; struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; int rc = 0; /* * Specifying internal flags without providing a place to * place the results is not allowed */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&sbsec->lock); if (!selinux_initialized()) { if (!opts) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { sbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } rc = -EINVAL; pr_warn("SELinux: Unable to set superblock options " "before the security server is initialized\n"); goto out; } /* * Binary mount data FS will come through this function twice. Once * from an explicit call and once from the generic calls from the vfs. * Since the generic VFS calls will not contain any security mount data * we need to skip the double mount verification. * * This does open a hole in which we will not notice if the first * mount using this sb set explicit options and a second mount using * this sb does not set any security options. (The first options * will be used for both mounts) */ if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA) && !opts) goto out; root_isec = backing_inode_security_novalidate(root); /* * parse the mount options, check if they are valid sids. * also check if someone is trying to mount the same sb more * than once with different security options. */ if (opts) { if (opts->fscontext_sid) { fscontext_sid = opts->fscontext_sid; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, fscontext_sid)) goto out_double_mount; sbsec->flags |= FSCONTEXT_MNT; } if (opts->context_sid) { context_sid = opts->context_sid; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, context_sid)) goto out_double_mount; sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext_sid) { rootcontext_sid = opts->rootcontext_sid; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, rootcontext_sid)) goto out_double_mount; sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext_sid) { defcontext_sid = opts->defcontext_sid; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, defcontext_sid)) goto out_double_mount; sbsec->flags |= DEFCONTEXT_MNT; } } if (sbsec->flags & SE_SBINITIALIZED) { /* previously mounted with options, but not on this attempt? */ if ((sbsec->flags & SE_MNTMASK) && !opts) goto out_double_mount; rc = 0; goto out; } if (strcmp(sb->s_type->name, "proc") == 0) sbsec->flags |= SE_SBPROC | SE_SBGENFS; if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "bpf") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "securityfs")) sbsec->flags |= SE_SBGENFS; if (!strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2")) sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR; if (!sbsec->behavior) { /* * Determine the labeling behavior to use for this * filesystem type. */ rc = security_fs_use(sb); if (rc) { pr_warn("%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); goto out; } } /* * If this is a user namespace mount and the filesystem type is not * explicitly whitelisted, then no contexts are allowed on the command * line and security labels must be ignored. */ if (sb->s_user_ns != &init_user_ns && strcmp(sb->s_type->name, "tmpfs") && strcmp(sb->s_type->name, "ramfs") && strcmp(sb->s_type->name, "devpts") && strcmp(sb->s_type->name, "overlay")) { if (context_sid || fscontext_sid || rootcontext_sid || defcontext_sid) { rc = -EACCES; goto out; } if (sbsec->behavior == SECURITY_FS_USE_XATTR) { sbsec->behavior = SECURITY_FS_USE_MNTPOINT; rc = security_transition_sid(current_sid(), current_sid(), SECCLASS_FILE, NULL, &sbsec->mntpoint_sid); if (rc) goto out; } goto out_set_opts; } /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; sbsec->sid = fscontext_sid; } /* * Switch to using mount point labeling behavior. * sets the label used on all file below the mountpoint, and will set * the superblock context if not already set. */ if (sbsec->flags & SE_SBNATIVE) { /* * This means we are initializing a superblock that has been * mounted before the SELinux was initialized and the * filesystem requested native labeling. We had already * returned SECURITY_LSM_NATIVE_LABELS in *set_kern_flags * in the original mount attempt, so now we just need to set * the SECURITY_FS_USE_NATIVE behavior. */ sbsec->behavior = SECURITY_FS_USE_NATIVE; } else if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) { sbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (context_sid) { if (!fscontext_sid) { rc = may_context_mount_sb_relabel(context_sid, sbsec, cred); if (rc) goto out; sbsec->sid = context_sid; } else { rc = may_context_mount_inode_relabel(context_sid, sbsec, cred); if (rc) goto out; } if (!rootcontext_sid) rootcontext_sid = context_sid; sbsec->mntpoint_sid = context_sid; sbsec->behavior = SECURITY_FS_USE_MNTPOINT; } if (rootcontext_sid) { rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, cred); if (rc) goto out; root_isec->sid = rootcontext_sid; root_isec->initialized = LABEL_INITIALIZED; } if (defcontext_sid) { if (sbsec->behavior != SECURITY_FS_USE_XATTR && sbsec->behavior != SECURITY_FS_USE_NATIVE) { rc = -EINVAL; pr_warn("SELinux: defcontext option is " "invalid for this filesystem type\n"); goto out; } if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, sbsec, cred); if (rc) goto out; } sbsec->def_sid = defcontext_sid; } out_set_opts: rc = sb_finish_set_opts(sb); out: mutex_unlock(&sbsec->lock); return rc; out_double_mount: rc = -EINVAL; pr_warn("SELinux: mount invalid. Same superblock, different " "security settings for (dev %s, type %s)\n", sb->s_id, sb->s_type->name); goto out; } static int selinux_cmp_sb_context(const struct super_block *oldsb, const struct super_block *newsb) { struct superblock_security_struct *old = selinux_superblock(oldsb); struct superblock_security_struct *new = selinux_superblock(newsb); char oldflags = old->flags & SE_MNTMASK; char newflags = new->flags & SE_MNTMASK; if (oldflags != newflags) goto mismatch; if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid) goto mismatch; if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid) goto mismatch; if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid) goto mismatch; if (oldflags & ROOTCONTEXT_MNT) { struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root); struct inode_security_struct *newroot = backing_inode_security(newsb->s_root); if (oldroot->sid != newroot->sid) goto mismatch; } return 0; mismatch: pr_warn("SELinux: mount invalid. Same superblock, " "different security settings for (dev %s, " "type %s)\n", newsb->s_id, newsb->s_type->name); return -EBUSY; } static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { int rc = 0; const struct superblock_security_struct *oldsbsec = selinux_superblock(oldsb); struct superblock_security_struct *newsbsec = selinux_superblock(newsb); int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT); int set_context = (oldsbsec->flags & CONTEXT_MNT); int set_rootcontext = (oldsbsec->flags & ROOTCONTEXT_MNT); /* * Specifying internal flags without providing a place to * place the results is not allowed. */ if (kern_flags && !set_kern_flags) return -EINVAL; mutex_lock(&newsbsec->lock); /* * if the parent was able to be mounted it clearly had no special lsm * mount options. thus we can safely deal with this superblock later */ if (!selinux_initialized()) { if (kern_flags & SECURITY_LSM_NATIVE_LABELS) { newsbsec->flags |= SE_SBNATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } goto out; } /* how can we clone if the old one wasn't set up?? */ BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED)); /* if fs is reusing a sb, make sure that the contexts match */ if (newsbsec->flags & SE_SBINITIALIZED) { mutex_unlock(&newsbsec->lock); if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; return selinux_cmp_sb_context(oldsb, newsb); } newsbsec->flags = oldsbsec->flags; newsbsec->sid = oldsbsec->sid; newsbsec->def_sid = oldsbsec->def_sid; newsbsec->behavior = oldsbsec->behavior; if (newsbsec->behavior == SECURITY_FS_USE_NATIVE && !(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) { rc = security_fs_use(newsb); if (rc) goto out; } if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) { newsbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (set_context) { u32 sid = oldsbsec->mntpoint_sid; if (!set_fscontext) newsbsec->sid = sid; if (!set_rootcontext) { struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = sid; } newsbsec->mntpoint_sid = sid; } if (set_rootcontext) { const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root); struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = oldisec->sid; } sb_finish_set_opts(newsb); out: mutex_unlock(&newsbsec->lock); return rc; } /* * NOTE: the caller is responsible for freeing the memory even if on error. */ static int selinux_add_opt(int token, const char *s, void **mnt_opts) { struct selinux_mnt_opts *opts = *mnt_opts; u32 *dst_sid; int rc; if (token == Opt_seclabel) /* eaten and completely ignored */ return 0; if (!s) return -EINVAL; if (!selinux_initialized()) { pr_warn("SELinux: Unable to set superblock options before the security server is initialized\n"); return -EINVAL; } if (!opts) { opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; *mnt_opts = opts; } switch (token) { case Opt_context: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->context_sid; break; case Opt_fscontext: if (opts->fscontext_sid) goto err; dst_sid = &opts->fscontext_sid; break; case Opt_rootcontext: if (opts->rootcontext_sid) goto err; dst_sid = &opts->rootcontext_sid; break; case Opt_defcontext: if (opts->context_sid || opts->defcontext_sid) goto err; dst_sid = &opts->defcontext_sid; break; default: WARN_ON(1); return -EINVAL; } rc = security_context_str_to_sid(s, dst_sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid (%s) failed with errno=%d\n", s, rc); return rc; err: pr_warn(SEL_MOUNT_FAIL_MSG); return -EINVAL; } static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; u32 len; int rc; rc = security_sid_to_context(sid, &context, &len); if (!rc) { bool has_comma = strchr(context, ','); seq_putc(m, '='); if (has_comma) seq_putc(m, '\"'); seq_escape(m, context, "\"\n\\"); if (has_comma) seq_putc(m, '\"'); } kfree(context); return rc; } static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!selinux_initialized()) return 0; if (sbsec->flags & FSCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, FSCONTEXT_STR); rc = show_sid(m, sbsec->sid); if (rc) return rc; } if (sbsec->flags & CONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, CONTEXT_STR); rc = show_sid(m, sbsec->mntpoint_sid); if (rc) return rc; } if (sbsec->flags & DEFCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, DEFCONTEXT_STR); rc = show_sid(m, sbsec->def_sid); if (rc) return rc; } if (sbsec->flags & ROOTCONTEXT_MNT) { struct dentry *root = sb->s_root; struct inode_security_struct *isec = backing_inode_security(root); seq_putc(m, ','); seq_puts(m, ROOTCONTEXT_STR); rc = show_sid(m, isec->sid); if (rc) return rc; } if (sbsec->flags & SBLABEL_MNT) { seq_putc(m, ','); seq_puts(m, SECLABEL_STR); } return 0; } static inline u16 inode_mode_to_security_class(umode_t mode) { switch (mode & S_IFMT) { case S_IFSOCK: return SECCLASS_SOCK_FILE; case S_IFLNK: return SECCLASS_LNK_FILE; case S_IFREG: return SECCLASS_FILE; case S_IFBLK: return SECCLASS_BLK_FILE; case S_IFDIR: return SECCLASS_DIR; case S_IFCHR: return SECCLASS_CHR_FILE; case S_IFIFO: return SECCLASS_FIFO_FILE; } return SECCLASS_FILE; } static inline int default_protocol_stream(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP || protocol == IPPROTO_MPTCP); } static inline int default_protocol_dgram(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP); } static inline u16 socket_type_to_security_class(int family, int type, int protocol) { bool extsockclass = selinux_policycap_extsockclass(); switch (family) { case PF_UNIX: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: return SECCLASS_UNIX_STREAM_SOCKET; case SOCK_DGRAM: case SOCK_RAW: return SECCLASS_UNIX_DGRAM_SOCKET; } break; case PF_INET: case PF_INET6: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: if (default_protocol_stream(protocol)) return SECCLASS_TCP_SOCKET; else if (extsockclass && protocol == IPPROTO_SCTP) return SECCLASS_SCTP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DGRAM: if (default_protocol_dgram(protocol)) return SECCLASS_UDP_SOCKET; else if (extsockclass && (protocol == IPPROTO_ICMP || protocol == IPPROTO_ICMPV6)) return SECCLASS_ICMP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DCCP: return SECCLASS_DCCP_SOCKET; default: return SECCLASS_RAWIP_SOCKET; } break; case PF_NETLINK: switch (protocol) { case NETLINK_ROUTE: return SECCLASS_NETLINK_ROUTE_SOCKET; case NETLINK_SOCK_DIAG: return SECCLASS_NETLINK_TCPDIAG_SOCKET; case NETLINK_NFLOG: return SECCLASS_NETLINK_NFLOG_SOCKET; case NETLINK_XFRM: return SECCLASS_NETLINK_XFRM_SOCKET; case NETLINK_SELINUX: return SECCLASS_NETLINK_SELINUX_SOCKET; case NETLINK_ISCSI: return SECCLASS_NETLINK_ISCSI_SOCKET; case NETLINK_AUDIT: return SECCLASS_NETLINK_AUDIT_SOCKET; case NETLINK_FIB_LOOKUP: return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET; case NETLINK_CONNECTOR: return SECCLASS_NETLINK_CONNECTOR_SOCKET; case NETLINK_NETFILTER: return SECCLASS_NETLINK_NETFILTER_SOCKET; case NETLINK_DNRTMSG: return SECCLASS_NETLINK_DNRT_SOCKET; case NETLINK_KOBJECT_UEVENT: return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET; case NETLINK_GENERIC: return SECCLASS_NETLINK_GENERIC_SOCKET; case NETLINK_SCSITRANSPORT: return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET; case NETLINK_RDMA: return SECCLASS_NETLINK_RDMA_SOCKET; case NETLINK_CRYPTO: return SECCLASS_NETLINK_CRYPTO_SOCKET; default: return SECCLASS_NETLINK_SOCKET; } case PF_PACKET: return SECCLASS_PACKET_SOCKET; case PF_KEY: return SECCLASS_KEY_SOCKET; case PF_APPLETALK: return SECCLASS_APPLETALK_SOCKET; } if (extsockclass) { switch (family) { case PF_AX25: return SECCLASS_AX25_SOCKET; case PF_IPX: return SECCLASS_IPX_SOCKET; case PF_NETROM: return SECCLASS_NETROM_SOCKET; case PF_ATMPVC: return SECCLASS_ATMPVC_SOCKET; case PF_X25: return SECCLASS_X25_SOCKET; case PF_ROSE: return SECCLASS_ROSE_SOCKET; case PF_DECnet: return SECCLASS_DECNET_SOCKET; case PF_ATMSVC: return SECCLASS_ATMSVC_SOCKET; case PF_RDS: return SECCLASS_RDS_SOCKET; case PF_IRDA: return SECCLASS_IRDA_SOCKET; case PF_PPPOX: return SECCLASS_PPPOX_SOCKET; case PF_LLC: return SECCLASS_LLC_SOCKET; case PF_CAN: return SECCLASS_CAN_SOCKET; case PF_TIPC: return SECCLASS_TIPC_SOCKET; case PF_BLUETOOTH: return SECCLASS_BLUETOOTH_SOCKET; case PF_IUCV: return SECCLASS_IUCV_SOCKET; case PF_RXRPC: return SECCLASS_RXRPC_SOCKET; case PF_ISDN: return SECCLASS_ISDN_SOCKET; case PF_PHONET: return SECCLASS_PHONET_SOCKET; case PF_IEEE802154: return SECCLASS_IEEE802154_SOCKET; case PF_CAIF: return SECCLASS_CAIF_SOCKET; case PF_ALG: return SECCLASS_ALG_SOCKET; case PF_NFC: return SECCLASS_NFC_SOCKET; case PF_VSOCK: return SECCLASS_VSOCK_SOCKET; case PF_KCM: return SECCLASS_KCM_SOCKET; case PF_QIPCRTR: return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; case PF_MCTP: return SECCLASS_MCTP_SOCKET; #if PF_MAX > 46 #error New address family defined, please update this function. #endif } } return SECCLASS_SOCKET; } static int selinux_genfs_get_sid(struct dentry *dentry, u16 tclass, u16 flags, u32 *sid) { int rc; struct super_block *sb = dentry->d_sb; char *buffer, *path; buffer = (char *)__get_free_page(GFP_KERNEL); if (!buffer) return -ENOMEM; path = dentry_path_raw(dentry, buffer, PAGE_SIZE); if (IS_ERR(path)) rc = PTR_ERR(path); else { if (flags & SE_SBPROC) { /* each process gets a /proc/PID/ entry. Strip off the * PID part to get a valid selinux labeling. * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */ while (path[1] >= '0' && path[1] <= '9') { path[1] = '/'; path++; } } rc = security_genfs_sid(sb->s_type->name, path, tclass, sid); if (rc == -ENOENT) { /* No match in policy, mark as unlabeled. */ *sid = SECINITSID_UNLABELED; rc = 0; } } free_page((unsigned long)buffer); return rc; } static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry, u32 def_sid, u32 *sid) { #define INITCONTEXTLEN 255 char *context; unsigned int len; int rc; len = INITCONTEXTLEN; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { kfree(context); /* Need a larger buffer. Query for the right size. */ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0) return rc; len = rc; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); } if (rc < 0) { kfree(context); if (rc != -ENODATA) { pr_warn("SELinux: %s: getxattr returned %d for dev=%s ino=%ld\n", __func__, -rc, inode->i_sb->s_id, inode->i_ino); return rc; } *sid = def_sid; return 0; } rc = security_context_to_sid_default(context, rc, sid, def_sid, GFP_NOFS); if (rc) { char *dev = inode->i_sb->s_id; unsigned long ino = inode->i_ino; if (rc == -EINVAL) { pr_notice_ratelimited("SELinux: inode=%lu on dev=%s was found to have an invalid context=%s. This indicates you may need to relabel the inode or the filesystem in question.\n", ino, dev, context); } else { pr_warn("SELinux: %s: context_to_sid(%s) returned %d for dev=%s ino=%ld\n", __func__, context, -rc, dev, ino); } } kfree(context); return 0; } /* The inode's security attributes must be initialized before first use. */ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry) { struct superblock_security_struct *sbsec = NULL; struct inode_security_struct *isec = selinux_inode(inode); u32 task_sid, sid = 0; u16 sclass; struct dentry *dentry; int rc = 0; if (isec->initialized == LABEL_INITIALIZED) return 0; spin_lock(&isec->lock); if (isec->initialized == LABEL_INITIALIZED) goto out_unlock; if (isec->sclass == SECCLASS_FILE) isec->sclass = inode_mode_to_security_class(inode->i_mode); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SE_SBINITIALIZED)) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ spin_lock(&sbsec->isec_lock); if (list_empty(&isec->list)) list_add(&isec->list, &sbsec->isec_head); spin_unlock(&sbsec->isec_lock); goto out_unlock; } sclass = isec->sclass; task_sid = isec->task_sid; sid = isec->sid; isec->initialized = LABEL_PENDING; spin_unlock(&isec->lock); switch (sbsec->behavior) { /* * In case of SECURITY_FS_USE_NATIVE we need to re-fetch the labels * via xattr when called from delayed_superblock_init(). */ case SECURITY_FS_USE_NATIVE: case SECURITY_FS_USE_XATTR: if (!(inode->i_opflags & IOP_XATTR)) { sid = sbsec->def_sid; break; } /* Need a dentry, since the xattr API requires one. Life would be simpler if we could just pass the inode. */ if (opt_dentry) { /* Called from d_instantiate or d_splice_alias. */ dentry = dget(opt_dentry); } else { /* * Called from selinux_complete_init, try to find a dentry. * Some filesystems really want a connected one, so try * that first. We could split SECURITY_FS_USE_XATTR in * two, depending upon that... */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } if (!dentry) { /* * this is can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as these * will get fixed up the next time we go through * inode_doinit with a dentry, before these inodes could * be used again by userspace. */ goto out_invalid; } rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid, &sid); dput(dentry); if (rc) goto out; break; case SECURITY_FS_USE_TASK: sid = task_sid; break; case SECURITY_FS_USE_TRANS: /* Default to the fs SID. */ sid = sbsec->sid; /* Try to obtain a transition SID. */ rc = security_transition_sid(task_sid, sid, sclass, NULL, &sid); if (rc) goto out; break; case SECURITY_FS_USE_MNTPOINT: sid = sbsec->mntpoint_sid; break; default: /* Default to the fs superblock SID. */ sid = sbsec->sid; if ((sbsec->flags & SE_SBGENFS) && (!S_ISLNK(inode->i_mode) || selinux_policycap_genfs_seclabel_symlinks())) { /* We must have a dentry to determine the label on * procfs inodes */ if (opt_dentry) { /* Called from d_instantiate or * d_splice_alias. */ dentry = dget(opt_dentry); } else { /* Called from selinux_complete_init, try to * find a dentry. Some filesystems really want * a connected one, so try that first. */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } /* * This can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as * these will get fixed up the next time we go through * inode_doinit() with a dentry, before these inodes * could be used again by userspace. */ if (!dentry) goto out_invalid; rc = selinux_genfs_get_sid(dentry, sclass, sbsec->flags, &sid); if (rc) { dput(dentry); goto out; } if ((sbsec->flags & SE_SBGENFS_XATTR) && (inode->i_opflags & IOP_XATTR)) { rc = inode_doinit_use_xattr(inode, dentry, sid, &sid); if (rc) { dput(dentry); goto out; } } dput(dentry); } break; } out: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { if (rc) { isec->initialized = LABEL_INVALID; goto out_unlock; } isec->initialized = LABEL_INITIALIZED; isec->sid = sid; } out_unlock: spin_unlock(&isec->lock); return rc; out_invalid: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { isec->initialized = LABEL_INVALID; isec->sid = sid; } spin_unlock(&isec->lock); return 0; } /* Convert a Linux signal to an access vector. */ static inline u32 signal_to_av(int sig) { u32 perm = 0; switch (sig) { case SIGCHLD: /* Commonly granted from child to parent. */ perm = PROCESS__SIGCHLD; break; case SIGKILL: /* Cannot be caught or ignored */ perm = PROCESS__SIGKILL; break; case SIGSTOP: /* Cannot be caught or ignored */ perm = PROCESS__SIGSTOP; break; default: /* All other signals. */ perm = PROCESS__SIGNAL; break; } return perm; } #if CAP_LAST_CAP > 63 #error Fix SELinux to handle capabilities > 63. #endif /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; u16 sclass; u32 sid = cred_sid(cred); u32 av = CAP_TO_MASK(cap); int rc; ad.type = LSM_AUDIT_DATA_CAP; ad.u.cap = cap; switch (CAP_TO_INDEX(cap)) { case 0: sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS; break; case 1: sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS; break; default: pr_err("SELinux: out of range capability %d\n", cap); BUG(); return -EINVAL; } rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad); if (rc2) return rc2; } return rc; } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; if (unlikely(IS_PRIVATE(inode))) return 0; sid = cred_sid(cred); isec = selinux_inode(inode); return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ static inline int dentry_has_perm(const struct cred *cred, struct dentry *dentry, u32 av) { struct inode *inode = d_backing_inode(dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; __inode_security_revalidate(inode, dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, const struct path *path, u32 av) { struct inode *inode = d_backing_inode(path->dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; __inode_security_revalidate(inode, path->dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ static inline int file_path_has_perm(const struct cred *cred, struct file *file, u32 av) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return inode_has_perm(cred, file_inode(file), av, &ad); } #ifdef CONFIG_BPF_SYSCALL static int bpf_fd_pass(const struct file *file, u32 sid); #endif /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to check a particular permission to the file. Access to the descriptor is implicitly granted if it has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ static int file_has_perm(const struct cred *cred, struct file *file, u32 av) { struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct common_audit_data ad; u32 sid = cred_sid(cred); int rc; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, cred_sid(cred)); if (rc) return rc; #endif /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) rc = inode_has_perm(cred, inode, av, &ad); out: return rc; } /* * Determine the label for an inode that might be unioned. */ static int selinux_determine_inode_label(const struct task_security_struct *tsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) { const struct superblock_security_struct *sbsec = selinux_superblock(dir->i_sb); if ((sbsec->flags & SE_SBINITIALIZED) && (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && tsec->create_sid) { *_new_isid = tsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); return security_transition_sid(tsec->sid, dsec->sid, tclass, name, _new_isid); } return 0; } /* Check whether a task can create a file. */ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; struct common_audit_data ad; int rc; dsec = inode_security(dir); sbsec = selinux_superblock(dir->i_sb); sid = tsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } #define MAY_LINK 0 #define MAY_UNLINK 1 #define MAY_RMDIR 2 /* Check whether a task can link, unlink, or rmdir a file/directory. */ static int may_link(struct inode *dir, struct dentry *dentry, int kind) { struct inode_security_struct *dsec, *isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int rc; dsec = inode_security(dir); isec = backing_inode_security(dentry); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; switch (kind) { case MAY_LINK: av = FILE__LINK; break; case MAY_UNLINK: av = FILE__UNLINK; break; case MAY_RMDIR: av = DIR__RMDIR; break; default: pr_warn("SELinux: %s: unrecognized kind %d\n", __func__, kind); return 0; } rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad); return rc; } static inline int may_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; old_dsec = inode_security(old_dir); old_isec = backing_inode_security(old_dentry); old_is_dir = d_is_dir(old_dentry); new_dsec = inode_security(new_dir); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = old_dentry; rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; } ad.u.dentry = new_dentry; av = DIR__ADD_NAME | DIR__SEARCH; if (d_is_positive(new_dentry)) av |= DIR__REMOVE_NAME; rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (d_is_positive(new_dentry)) { new_isec = backing_inode_security(new_dentry); new_is_dir = d_is_dir(new_dentry); rc = avc_has_perm(sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) return rc; } return 0; } /* Check whether a task can perform a filesystem operation. */ static int superblock_has_perm(const struct cred *cred, const struct super_block *sb, u32 perms, struct common_audit_data *ad) { struct superblock_security_struct *sbsec; u32 sid = cred_sid(cred); sbsec = selinux_superblock(sb); return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ static inline u32 file_mask_to_av(int mode, int mask) { u32 av = 0; if (!S_ISDIR(mode)) { if (mask & MAY_EXEC) av |= FILE__EXECUTE; if (mask & MAY_READ) av |= FILE__READ; if (mask & MAY_APPEND) av |= FILE__APPEND; else if (mask & MAY_WRITE) av |= FILE__WRITE; } else { if (mask & MAY_EXEC) av |= DIR__SEARCH; if (mask & MAY_WRITE) av |= DIR__WRITE; if (mask & MAY_READ) av |= DIR__READ; } return av; } /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(const struct file *file) { u32 av = 0; if (file->f_mode & FMODE_READ) av |= FILE__READ; if (file->f_mode & FMODE_WRITE) { if (file->f_flags & O_APPEND) av |= FILE__APPEND; else av |= FILE__WRITE; } if (!av) { /* * Special file opened with flags 3 for ioctl-only use. */ av = FILE__IOCTL; } return av; } /* * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) { u32 av = file_to_av(file); struct inode *inode = file_inode(file); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC) av |= FILE__OPEN; return av; } /* Hook functions begin here. */ static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } static int selinux_binder_transaction(const struct cred *from, const struct cred *to) { u32 mysid = current_sid(); u32 fromsid = cred_sid(from); u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL); if (rc) return rc; } return avc_has_perm(fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } static int selinux_binder_transfer_binder(const struct cred *from, const struct cred *to) { return avc_has_perm(cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } static int selinux_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; struct common_audit_data ad; int rc; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, sid); if (rc) return rc; #endif if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; isec = backing_inode_security(dentry); return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file), &ad); } static int selinux_ptrace_access_check(struct task_struct *child, unsigned int mode) { u32 sid = current_sid(); u32 csid = task_sid_obj(child); if (mode & PTRACE_MODE_READ) return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL); return avc_has_perm(sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(task_sid_obj(parent), task_sid_obj(current), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return avc_has_perm(current_sid(), task_sid_obj(target), SECCLASS_PROCESS, PROCESS__GETCAP, NULL); } static int selinux_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return avc_has_perm(cred_sid(old), cred_sid(new), SECCLASS_PROCESS, PROCESS__SETCAP, NULL); } /* * (This comment used to live with the selinux_task_setuid hook, * which was removed). * * Since setuid only affects the current process, and since the SELinux * controls are not based on the Linux identity attributes, SELinux does not * need to control this operation. However, SELinux does control the use of * the CAP_SETUID and CAP_SETGID capabilities using the capable hook. */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, const struct super_block *sb) { const struct cred *cred = current_cred(); int rc = 0; if (!sb) return 0; switch (cmds) { case Q_SYNC: case Q_QUOTAON: case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: case Q_XQUOTAOFF: case Q_XQUOTAON: case Q_XSETQLIM: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: case Q_XGETQUOTA: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETNEXTQUOTA: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ break; } return rc; } static int selinux_quota_on(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) { switch (type) { case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL); case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, NULL); } /* All other syslog types */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL); } /* * Check permission for allocating a new virtual mapping. Returns * 0 if permission is granted, negative error code if not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { return cred_has_capability(current_cred(), CAP_SYS_ADMIN, CAP_OPT_NOAUDIT, true); } /* binprm security operations */ static u32 ptrace_parent_sid(void) { u32 sid = 0; struct task_struct *tracer; rcu_read_lock(); tracer = ptrace_parent(current); if (tracer) sid = task_sid_obj(tracer); rcu_read_unlock(); return sid; } static int check_nnp_nosuid(const struct linux_binprm *bprm, const struct task_security_struct *old_tsec, const struct task_security_struct *new_tsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); int rc; u32 av; if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ if (new_tsec->sid == old_tsec->sid) return 0; /* No change in credentials */ /* * If the policy enables the nnp_nosuid_transition policy capability, * then we permit transitions under NNP or nosuid if the * policy allows the corresponding permission between * the old and new contexts. */ if (selinux_policycap_nnp_nosuid_transition()) { av = 0; if (nnp) av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; } /* * We also permit NNP or nosuid transitions to bounded SIDs, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ rc = security_bounded_transition(old_tsec->sid, new_tsec->sid); if (!rc) return 0; /* * On failure, preserve the errno values for NNP vs nosuid. * NNP: Operation not permitted for caller. * nosuid: Permission denied to file. */ if (nnp) return -EPERM; return -EACCES; } static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { const struct task_security_struct *old_tsec; struct task_security_struct *new_tsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); int rc; /* SELinux context only depends on initial program or script and not * the script interpreter */ old_tsec = selinux_cred(current_cred()); new_tsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ new_tsec->sid = old_tsec->sid; new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ new_tsec->create_sid = 0; new_tsec->keycreate_sid = 0; new_tsec->sockcreate_sid = 0; /* * Before policy is loaded, label any task outside kernel space * as SECINITSID_INIT, so that any userspace tasks surviving from * early boot end up with a label different from SECINITSID_KERNEL * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL). */ if (!selinux_initialized()) { new_tsec->sid = SECINITSID_INIT; /* also clear the exec_sid just in case */ new_tsec->exec_sid = 0; return 0; } if (old_tsec->exec_sid) { new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ new_tsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ rc = security_transition_sid(old_tsec->sid, isec->sid, SECCLASS_PROCESS, NULL, &new_tsec->sid); if (rc) return rc; /* * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) new_tsec->sid = old_tsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; if (new_tsec->sid == old_tsec->sid) { rc = avc_has_perm(old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; rc = avc_has_perm(new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) return -EPERM; } /* Make sure that anyone attempting to ptrace over a task that * changes its SID has the appropriate permit */ if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { rc = avc_has_perm(ptsid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) return -EPERM; } } /* Clear any possibly unsafe personality bits on exec: */ bprm->per_clear |= PER_CLEAR_ON_SETID; /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; } return 0; } static int match_file(const void *p, struct file *file, unsigned fd) { return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0; } /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) { struct file *file, *devnull = NULL; struct tty_struct *tty; int drop_tty = 0; unsigned n; tty = get_current_tty(); if (tty) { spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; /* Revalidate access to controlling tty. Use file_path_has_perm on the tty path directly rather than using file_has_perm, as this particular open file may belong to another process and we are only interested in the inode-based check here. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); } /* Reset controlling tty. */ if (drop_tty) no_tty(); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, cred); if (!n) /* none found? */ return; devnull = dentry_open(&selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); if (devnull) fput(devnull); } /* * Prepare a process for imminent new credential changes due to exec */ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) { struct task_security_struct *new_tsec; struct rlimit *rlim, *initrlim; int rc, i; new_tsec = selinux_cred(bprm->cred); if (new_tsec->sid == new_tsec->osid) return; /* Close files for which the new task SID is not authorized. */ flush_unauthorized_files(bprm->cred, current->files); /* Always clear parent death signal on SID transitions. */ current->pdeath_signal = 0; /* Check whether the new SID can inherit resource limits from the old * SID. If not, reset all soft limits to the lower of the current * task's hard limit and the init task's soft limit. * * Note that the setting of hard limits (even to lower them) can be * controlled by the setrlimit check. The inclusion of the init task's * soft limit into the computation is to avoid resetting soft limits * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ task_lock(current); for (i = 0; i < RLIM_NLIMITS; i++) { rlim = current->signal->rlim + i; initrlim = init_task.signal->rlim + i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } task_unlock(current); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(current, rlimit(RLIMIT_CPU)); } } /* * Clean up the process immediately after the installation of new credentials * due to exec */ static void selinux_bprm_committed_creds(const struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 osid, sid; int rc; osid = tsec->osid; sid = tsec->sid; if (sid == osid) return; /* Check whether the new SID can inherit signal state from the old SID. * If not, clear itimers to avoid subsequent signal generation and * flush and unblock signals. * * This must occur _after_ the task SID has been updated so that any * kill done after the flush will be checked against the new SID. */ rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { clear_itimer(); spin_lock_irq(&unrcu_pointer(current->sighand)->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); flush_sigqueue(¤t->signal->shared_pending); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); } spin_unlock_irq(&unrcu_pointer(current->sighand)->siglock); } /* Wake up the parent if it is waiting so that it can recheck * wait permission to the new task SID. */ read_lock(&tasklist_lock); __wake_up_parent(current, unrcu_pointer(current->real_parent)); read_unlock(&tasklist_lock); } /* superblock security operations */ static int selinux_sb_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec = selinux_superblock(sb); mutex_init(&sbsec->lock); INIT_LIST_HEAD(&sbsec->isec_head); spin_lock_init(&sbsec->isec_lock); sbsec->sid = SECINITSID_UNLABELED; sbsec->def_sid = SECINITSID_FILE; sbsec->mntpoint_sid = SECINITSID_UNLABELED; return 0; } static inline int opt_len(const char *s) { bool open_quote = false; int len; char c; for (len = 0; (c = s[len]) != '\0'; len++) { if (c == '"') open_quote = !open_quote; if (c == ',' && !open_quote) break; } return len; } static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) { char *from = options; char *to = options; bool first = true; int rc; while (1) { int len = opt_len(from); int token; char *arg = NULL; token = match_opt_prefix(from, len, &arg); if (token != Opt_error) { char *p, *q; /* strip quotes */ if (arg) { for (p = q = arg; p < from + len; p++) { char c = *p; if (c != '"') *q++ = c; } arg = kmemdup_nul(arg, q - arg, GFP_KERNEL); if (!arg) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, arg, mnt_opts); kfree(arg); arg = NULL; if (unlikely(rc)) { goto free_opt; } } else { if (!first) { // copy with preceding comma from--; len++; } if (to != from) memmove(to, from, len); to += len; first = false; } if (!from[len]) break; from += len + 1; } *to = '\0'; return 0; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); /* * Superblock not initialized (i.e. no options) - reject if any * options specified, otherwise accept. */ if (!(sbsec->flags & SE_SBINITIALIZED)) return opts ? 1 : 0; /* * Superblock initialized and no options specified - reject if * superblock has any options set, otherwise accept. */ if (!opts) return (sbsec->flags & SE_MNTMASK) ? 1 : 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) return 1; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) return 1; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) return 1; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) return 1; } return 0; } static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = selinux_superblock(sb); if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!opts) return 0; if (opts->fscontext_sid) { if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, opts->fscontext_sid)) goto out_bad_option; } if (opts->context_sid) { if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, opts->context_sid)) goto out_bad_option; } if (opts->rootcontext_sid) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, opts->rootcontext_sid)) goto out_bad_option; } if (opts->defcontext_sid) { if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, opts->defcontext_sid)) goto out_bad_option; } return 0; out_bad_option: pr_warn("SELinux: unable to change security options " "during remount (dev %s, type=%s)\n", sb->s_id, sb->s_type->name); return -EINVAL; } static int selinux_sb_kern_mount(const struct super_block *sb) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = sb->s_root; return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry->d_sb->s_root; return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { const struct cred *cred = current_cred(); if (flags & MS_REMOUNT) return superblock_has_perm(cred, path->dentry->d_sb, FILESYSTEM__REMOUNT, NULL); else return path_has_perm(cred, path, FILE__MOUNTON); } static int selinux_move_mount(const struct path *from_path, const struct path *to_path) { const struct cred *cred = current_cred(); return path_has_perm(cred, to_path, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { const struct cred *cred = current_cred(); return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } static int selinux_fs_context_submount(struct fs_context *fc, struct super_block *reference) { const struct superblock_security_struct *sbsec = selinux_superblock(reference); struct selinux_mnt_opts *opts; /* * Ensure that fc->security remains NULL when no options are set * as expected by selinux_set_mnt_opts(). */ if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT))) return 0; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; if (sbsec->flags & FSCONTEXT_MNT) opts->fscontext_sid = sbsec->sid; if (sbsec->flags & CONTEXT_MNT) opts->context_sid = sbsec->mntpoint_sid; if (sbsec->flags & DEFCONTEXT_MNT) opts->defcontext_sid = sbsec->def_sid; fc->security = opts; return 0; } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { const struct selinux_mnt_opts *src = src_fc->security; if (!src) return 0; fc->security = kmemdup(src, sizeof(*src), GFP_KERNEL); return fc->security ? 0 : -ENOMEM; } static const struct fs_parameter_spec selinux_fs_parameters[] = { fsparam_string(CONTEXT_STR, Opt_context), fsparam_string(DEFCONTEXT_STR, Opt_defcontext), fsparam_string(FSCONTEXT_STR, Opt_fscontext), fsparam_string(ROOTCONTEXT_STR, Opt_rootcontext), fsparam_flag (SECLABEL_STR, Opt_seclabel), {} }; static int selinux_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; int opt; opt = fs_parse(fc, selinux_fs_parameters, param, &result); if (opt < 0) return opt; return selinux_add_opt(opt, param->string, &fc->security); } /* inode security operations */ static int selinux_inode_alloc_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; return 0; } static void selinux_inode_free_security(struct inode *inode) { inode_free_security(inode); } static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) { u32 newsid; int rc; rc = selinux_determine_inode_label(selinux_cred(current_cred()), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; if (xattr_name) *xattr_name = XATTR_NAME_SELINUX; return security_sid_to_context(newsid, (char **)ctx, ctxlen); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { u32 newsid; int rc; struct task_security_struct *tsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; tsec = selinux_cred(new); tsec->create_sid = newsid; return 0; } static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); u32 newsid, clen; u16 newsclass; int rc; char *context; sbsec = selinux_superblock(dir->i_sb); newsid = tsec->create_sid; newsclass = inode_mode_to_security_class(inode->i_mode); rc = selinux_determine_inode_label(tsec, dir, qstr, newsclass, &newsid); if (rc) return rc; /* Possibly defer initialization to selinux_complete_init. */ if (sbsec->flags & SE_SBINITIALIZED) { struct inode_security_struct *isec = selinux_inode(inode); isec->sclass = newsclass; isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; } if (!selinux_initialized() || !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (xattr) { rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; xattr->value = context; xattr->value_len = clen; xattr->name = XATTR_SELINUX_SUFFIX; } return 0; } static int selinux_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { u32 sid = current_sid(); struct common_audit_data ad; struct inode_security_struct *isec; int rc; if (unlikely(!selinux_initialized())) return 0; isec = selinux_inode(inode); /* * We only get here once per ephemeral inode. The inode has * been initialized via inode_alloc_security but is otherwise * untouched. */ if (context_inode) { struct inode_security_struct *context_isec = selinux_inode(context_inode); if (context_isec->initialized != LABEL_INITIALIZED) { pr_err("SELinux: context_inode is not initialized\n"); return -EACCES; } isec->sclass = context_isec->sclass; isec->sid = context_isec->sid; } else { isec->sclass = SECCLASS_ANON_INODE; rc = security_transition_sid( sid, sid, isec->sclass, name, &isec->sid); if (rc) return rc; } isec->initialized = LABEL_INITIALIZED; /* * Now that we've initialized security, check whether we're * allowed to actually create this type of anonymous inode. */ ad.type = LSM_AUDIT_DATA_ANONINODE; ad.u.anonclass = name ? (const char *)name->name : "?"; return avc_has_perm(sid, isec->sid, isec->sclass, FILE__CREATE, &ad); } static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { return may_create(dir, dentry, SECCLASS_FILE); } static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { return may_link(dir, old_dentry, MAY_LINK); } static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_UNLINK); } static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name) { return may_create(dir, dentry, SECCLASS_LNK_FILE); } static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask) { return may_create(dir, dentry, SECCLASS_DIR); } static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_RMDIR); } static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return may_create(dir, dentry, inode_mode_to_security_class(mode)); } static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry, struct inode *new_inode, struct dentry *new_dentry) { return may_rename(old_inode, old_dentry, new_inode, new_dentry); } static int selinux_inode_readlink(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { struct common_audit_data ad; struct inode_security_struct *isec; u32 sid = current_sid(); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = inode_security_rcu(inode, rcu); if (IS_ERR(isec)) return PTR_ERR(isec); return avc_has_perm(sid, isec->sid, isec->sclass, FILE__READ, &ad); } static noinline int audit_inode_permission(struct inode *inode, u32 perms, u32 audited, u32 denied, int result) { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; return slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); } static int selinux_inode_permission(struct inode *inode, int mask) { u32 perms; bool from_access; bool no_block = mask & MAY_NOT_BLOCK; struct inode_security_struct *isec; u32 sid = current_sid(); struct av_decision avd; int rc, rc2; u32 audited, denied; from_access = mask & MAY_ACCESS; mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND); /* No permission to check. Existence test. */ if (!mask) return 0; if (unlikely(IS_PRIVATE(inode))) return 0; perms = file_mask_to_av(inode->i_mode, mask); isec = inode_security_rcu(inode, no_block); if (IS_ERR(isec)) return PTR_ERR(isec); rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; return rc; } static int selinux_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; __u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE | ATTR_FORCE); if (!ia_valid) return 0; } if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC && (ia_valid & ATTR_SIZE) && !(ia_valid & ATTR_FILE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); } static int selinux_inode_getattr(const struct path *path) { return path_has_perm(current_cred(), path, FILE__GETATTR); } static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } /** * selinux_inode_xattr_skipcap - Skip the xattr capability checks? * @name: name of the xattr * * Returns 1 to indicate that SELinux "owns" the access control rights to xattrs * named @name; the LSM layer should avoid enforcing any traditional * capability based access controls on this xattr. Returns 0 to indicate that * SELinux does not "own" the access control rights to xattrs named @name and is * deferring to the LSM layer for further access controls, including capability * based controls. */ static int selinux_inode_xattr_skipcap(const char *name) { /* require capability check if not a selinux xattr */ return !strcmp(name, XATTR_NAME_SELINUX); } static int selinux_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; struct superblock_security_struct *sbsec; struct common_audit_data ad; u32 newsid, sid = current_sid(); int rc = 0; /* if not a selinux xattr, only check the ordinary setattr perm */ if (strcmp(name, XATTR_NAME_SELINUX)) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); if (!selinux_initialized()) return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM); sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = backing_inode_security(dentry); rc = avc_has_perm(sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (value) { const char *str = value; if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; } else { audit_size = 0; } ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return rc; audit_log_format(ab, "op=setxattr invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return rc; } rc = security_context_to_sid_force(value, size, &newsid); } if (rc) return rc; rc = avc_has_perm(sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; rc = security_validate_transition(isec->sid, newsid, sid, isec->sclass); if (rc) return rc; return avc_has_perm(newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } static int selinux_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static int selinux_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__GETATTR); } static int selinux_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; u32 newsid; int rc; if (strcmp(name, XATTR_NAME_SELINUX)) { /* Not an attribute we recognize, so nothing to do. */ return; } if (!selinux_initialized()) { /* If we haven't even been initialized, then we can't validate * against a policy, so leave the label as invalid. It may * resolve to a valid label on the next revalidation try if * we've since initialized. */ return; } rc = security_context_to_sid_force(value, size, &newsid); if (rc) { pr_err("SELinux: unable to map context to SID" "for (%s, %lu), rc=%d\n", inode->i_sb->s_id, inode->i_ino, -rc); return; } isec = backing_inode_security(dentry); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { /* if not a selinux xattr, only check the ordinary setattr perm */ if (strcmp(name, XATTR_NAME_SELINUX)) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); if (!selinux_initialized()) return 0; /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; } static int selinux_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { int ret; u32 perm; struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; /* * Set permission needed based on the type of mark being set. * Performs an additional check for sb watches. */ switch (obj_type) { case FSNOTIFY_OBJ_TYPE_VFSMOUNT: perm = FILE__WATCH_MOUNT; break; case FSNOTIFY_OBJ_TYPE_SB: perm = FILE__WATCH_SB; ret = superblock_has_perm(current_cred(), path->dentry->d_sb, FILESYSTEM__WATCH, &ad); if (ret) return ret; break; case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; default: return -EINVAL; } /* blocking watches require the file:watch_with_perm permission */ if (mask & (ALL_FSNOTIFY_PERM_EVENTS)) perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); } /* * Copy the inode security context value to the user. * * Permission check is handled by selinux_inode_getxattr hook. */ static int selinux_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { u32 size; int error; char *context = NULL; struct inode_security_struct *isec; /* * If we're not initialized yet, then we can't validate contexts, so * just let vfs_getxattr fall back to using the on-disk xattr. */ if (!selinux_initialized() || strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; /* * If the caller has CAP_MAC_ADMIN, then get the raw context * value even if it is not defined by current policy; otherwise, * use the in-core value under current policy. * Use the non-auditing forms of the permission checks since * getxattr may be called by unprivileged processes commonly * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ isec = inode_security(inode); if (has_cap_mac_admin(false)) error = security_sid_to_context_force(isec->sid, &context, &size); else error = security_sid_to_context(isec->sid, &context, &size); if (error) return error; error = size; if (alloc) { *buffer = context; goto out_nofree; } kfree(context); out_nofree: return error; } static int selinux_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct inode_security_struct *isec = inode_security_novalidate(inode); struct superblock_security_struct *sbsec; u32 newsid; int rc; if (strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; sbsec = selinux_superblock(inode->i_sb); if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!value || !size) return -EACCES; rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL); if (rc) return rc; spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return 0; } static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { const int len = sizeof(XATTR_NAME_SELINUX); if (!selinux_initialized()) return 0; if (buffer && len <= buffer_size) memcpy(buffer, XATTR_NAME_SELINUX, len); return len; } static void selinux_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop) { struct inode_security_struct *isec = inode_security_novalidate(inode); prop->selinux.secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { struct lsm_prop prop; struct task_security_struct *tsec; struct cred *new_creds = *new; if (new_creds == NULL) { new_creds = prepare_creds(); if (!new_creds) return -ENOMEM; } tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getlsmprop(d_inode(src), &prop); tsec->create_sid = prop.selinux.secid; *new = new_creds; return 0; } static int selinux_inode_copy_up_xattr(struct dentry *dentry, const char *name) { /* The copy_up hook above sets the initial context on an inode, but we * don't then want to overwrite it by blindly copying all the lower * xattrs up. Instead, filter out SELinux-related xattrs following * policy load. */ if (selinux_initialized() && !strcmp(name, XATTR_NAME_SELINUX)) return -ECANCELED; /* Discard */ /* * Any other attribute apart from SELINUX is not claimed, supported * by selinux. */ return -EOPNOTSUPP; } /* kernfs node operations */ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0); if (rc == -ENODATA) return 0; else if (rc < 0) return rc; clen = (u32)rc; context = kmalloc(clen, GFP_KERNEL); if (!context) return -ENOMEM; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen); if (rc < 0) { kfree(context); return rc; } rc = security_context_to_sid(context, clen, &parent_sid, GFP_KERNEL); kfree(context); if (rc) return rc; if (tsec->create_sid) { newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); struct qstr q; q.name = kn->name; q.hash_len = hashlen_string(kn_dir, kn->name); rc = security_transition_sid(tsec->sid, parent_sid, secclass, &q, &newsid); if (rc) return rc; } rc = security_sid_to_context_force(newsid, &context, &clen); if (rc) return rc; rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen, XATTR_CREATE); kfree(context); return rc; } /* file security operations */ static int selinux_revalidate_file_permission(struct file *file, int mask) { const struct cred *cred = current_cred(); struct inode *inode = file_inode(file); /* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */ if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; return file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); } static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file_inode(file); struct file_security_struct *fsec = selinux_file(file); struct inode_security_struct *isec; u32 sid = current_sid(); if (!mask) /* No permission to check. Existence test. */ return 0; isec = inode_security(inode); if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno()) /* No change since file_open check. */ return 0; return selinux_revalidate_file_permission(file, mask); } static int selinux_file_alloc_security(struct file *file) { struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); fsec->sid = sid; fsec->fown_sid = sid; return 0; } /* * Check whether a task has the ioctl permission and cmd * operation to an inode. */ static int ioctl_has_perm(const struct cred *cred, struct file *file, u32 requested, u16 cmd) { struct common_audit_data ad; struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct inode_security_struct *isec; struct lsm_ioctlop_audit ioctl; u32 ssid = cred_sid(cred); int rc; u8 driver = cmd >> 8; u8 xperm = cmd & 0xff; ad.type = LSM_AUDIT_DATA_IOCTL_OP; ad.u.op = &ioctl; ad.u.op->cmd = cmd; ad.u.op->path = file->f_path; if (ssid != fsec->sid) { rc = avc_has_perm(ssid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } if (unlikely(IS_PRIVATE(inode))) return 0; isec = inode_security(inode); rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, driver, xperm, &ad); out: return rc; } static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int error = 0; switch (cmd) { case FIONREAD: case FIBMAP: case FIGETBSZ: case FS_IOC_GETFLAGS: case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: case FIOASYNC: error = file_has_perm(cred, file, 0); break; case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, CAP_OPT_NONE, true); break; case FIOCLEX: case FIONCLEX: if (!selinux_policycap_ioctl_skip_cloexec()) error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); break; /* default case assumes that the command will go * to the file's ioctl() function. */ default: error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); } return error; } static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { /* * If we are in a 64-bit kernel running 32-bit userspace, we need to * make sure we don't compare 32-bit flags to 64-bit flags. */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; break; case FS_IOC32_SETFLAGS: cmd = FS_IOC_SETFLAGS; break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case FS_IOC32_SETVERSION: cmd = FS_IOC_SETVERSION; break; default: break; } return selinux_file_ioctl(file, cmd, arg); } static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); int rc = 0; if (default_noexec && (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) || (!shared && (prot & PROT_WRITE)))) { /* * We are making executable an anonymous mapping or a * private file mapping that will also be writable. * This has an additional check. */ rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM, NULL); if (rc) goto error; } if (file) { /* read access is always possible with a mapping */ u32 av = FILE__READ; /* write access only matters if the mapping is shared */ if (shared && (prot & PROT_WRITE)) av |= FILE__WRITE; if (prot & PROT_EXEC) av |= FILE__EXECUTE; return file_has_perm(cred, file, av); } error: return rc; } static int selinux_mmap_addr(unsigned long addr) { int rc = 0; if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { u32 sid = current_sid(); rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); } return rc; } static int selinux_mmap_file(struct file *file, unsigned long reqprot __always_unused, unsigned long prot, unsigned long flags) { struct common_audit_data ad; int rc; if (file) { ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; rc = inode_has_perm(current_cred(), file_inode(file), FILE__MAP, &ad); if (rc) return rc; } return file_map_prot_check(file, prot, (flags & MAP_TYPE) == MAP_SHARED); } static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot __always_unused, unsigned long prot) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; /* * We don't use the vma_is_initial_heap() helper as it has * a history of problems and is currently broken on systems * where there is no heap, e.g. brk == start_brk. Before * replacing the conditional below with vma_is_initial_heap(), * or something similar, please ensure that the logic is the * same as what we have below or you have tested every possible * corner case you can think to test. */ if (vma->vm_start >= vma->vm_mm->start_brk && vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || vma_is_stack_for_current(vma))) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECSTACK, NULL); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has * had some COW done. Since pages might have been * written, check ability to execute the possibly * modified content. This typically should only * occur for text relocations. */ rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; } return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED); } static int selinux_file_lock(struct file *file, unsigned int cmd) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int err = 0; switch (cmd) { case F_SETFL: if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { err = file_has_perm(cred, file, FILE__WRITE); break; } fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: case F_GETOWN: case F_GETSIG: case F_GETOWNER_UIDS: /* Just check FD__USE permission */ err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: case F_SETLKW: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: case F_SETLKW64: #endif err = file_has_perm(cred, file, FILE__LOCK); break; } return err; } static void selinux_file_set_fowner(struct file *file) { struct file_security_struct *fsec; fsec = selinux_file(file); fsec->fown_sid = current_sid(); } static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; u32 sid = task_sid_obj(tsk); u32 perm; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = fown->file; fsec = selinux_file(file); if (!signum) perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */ else perm = signal_to_av(signum); return avc_has_perm(fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, file_to_av(file)); } static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; fsec = selinux_file(file); isec = inode_security(file_inode(file)); /* * Save inode label and policy sequence number * at open-time so that selinux_file_permission * can determine whether revalidation is necessary. * Task label is already saved in the file security * struct as its SID. */ fsec->isid = isec->sid; fsec->pseqno = avc_policy_seqno(); /* * Since the inode label or policy seqno may have changed * between the selinux_inode_permission check and the saving * of state above, recheck that access is still permitted. * Otherwise, access might never be revalidated against the * new inode label or new policy. * This check is not redundant - do not remove. */ return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ static int selinux_task_alloc(struct task_struct *task, unsigned long clone_flags) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; return 0; } /* * transfer the SELinux data to a blank set of creds */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) { *secid = cred_sid(c); } static void selinux_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop) { prop->selinux.secid = cred_sid(c); } /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, secid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { tsec->sid = secid; tsec->create_sid = 0; tsec->keycreate_sid = 0; tsec->sockcreate_sid = 0; } return ret; } /* * set the file creation context in a security record to the same as the * objective context of the specified inode */ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(sid, isec->sid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, NULL); if (ret == 0) tsec->create_sid = isec->sid; return ret; } static int selinux_kernel_module_request(char *kmod_name) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_KMOD; ad.u.kmod_name = kmod_name; return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, &ad); } static int selinux_kernel_module_from_file(struct file *file) { struct common_audit_data ad; struct inode_security_struct *isec; struct file_security_struct *fsec; u32 sid = current_sid(); int rc; /* init_module */ if (file == NULL) return avc_has_perm(sid, sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, NULL); /* finit_module */ ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; fsec = selinux_file(file); if (sid != fsec->sid) { rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } isec = inode_security(file_inode(file)); return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, &ad); } static int selinux_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int rc = 0; switch (id) { case READING_MODULE: rc = selinux_kernel_module_from_file(contents ? file : NULL); break; default: break; } return rc; } static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents) { int rc = 0; switch (id) { case LOADING_MODULE: rc = selinux_kernel_module_from_file(NULL); break; default: break; } return rc; } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETPGID, NULL); } static int selinux_task_getpgid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETPGID, NULL); } static int selinux_task_getsid(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSESSION, NULL); } static void selinux_current_getlsmprop_subj(struct lsm_prop *prop) { prop->selinux.secid = current_sid(); } static void selinux_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop) { prop->selinux.secid = task_sid_obj(p); } static int selinux_task_setnice(struct task_struct *p, int nice) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getioprio(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { u32 av = 0; if (!flags) return 0; if (flags & LSM_PRLIMIT_WRITE) av |= PROCESS__SETRLIMIT; if (flags & LSM_PRLIMIT_READ) av |= PROCESS__GETRLIMIT; return avc_has_perm(cred_sid(cred), cred_sid(tcred), SECCLASS_PROCESS, av, NULL); } static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { struct rlimit *old_rlim = p->signal->rlim + resource; /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL); return 0; } static int selinux_task_setscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getscheduler(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_movememory(struct task_struct *p) { return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; u32 perm; if (!sig) perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); if (!cred) secid = current_sid(); else secid = cred_sid(cred); return avc_has_perm(secid, task_sid_obj(p), SECCLASS_PROCESS, perm, NULL); } static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = task_sid_obj(p); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = sid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } static int selinux_userns_create(const struct cred *cred) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_USER_NAMESPACE, USER_NAMESPACE__CREATE, NULL); } /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ihlen, ret = -EINVAL; struct iphdr _iph, *ih; offset = skb_network_offset(skb); ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) goto out; ihlen = ih->ihl * 4; if (ihlen < sizeof(_iph)) goto out; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; ret = 0; if (proto) *proto = ih->protocol; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif default: break; } out: return ret; } #if IS_ENABLED(CONFIG_IPV6) /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv6(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { u8 nexthdr; int ret = -EINVAL, offset; struct ipv6hdr _ipv6h, *ip6; __be16 frag_off; offset = skb_network_offset(skb); ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (ip6 == NULL) goto out; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; ret = 0; nexthdr = ip6->nexthdr; offset += sizeof(_ipv6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) goto out; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif /* includes fragments */ default: break; } out: return ret; } #endif /* IPV6 */ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad, char **_addrp, int src, u8 *proto) { char *addrp; int ret; switch (ad->u.net->family) { case PF_INET: ret = selinux_parse_skb_ipv4(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v4info.saddr : &ad->u.net->v4info.daddr); goto okay; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: ret = selinux_parse_skb_ipv6(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v6info.saddr : &ad->u.net->v6info.daddr); goto okay; #endif /* IPV6 */ default: addrp = NULL; goto okay; } parse_error: pr_warn( "SELinux: failure in selinux_parse_skb()," " unable to parse packet\n"); return ret; okay: if (_addrp) *_addrp = addrp; return 0; } /** * selinux_skb_peerlbl_sid - Determine the peer label of a packet * @skb: the packet * @family: protocol family * @sid: the packet's peer label SID * * Description: * Check the various different forms of network peer labeling and determine * the peer label/SID for the packet; most of the magic actually occurs in * the security server function security_net_peersid_cmp(). The function * returns zero if the value in @sid is valid (although it may be SECSID_NULL) * or -EACCES if @sid is invalid due to inconsistencies with the different * peer labels. * */ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) { int err; u32 xfrm_sid; u32 nlbl_sid; u32 nlbl_type; err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); if (unlikely(err)) return -EACCES; err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid); if (unlikely(err)) { pr_warn( "SELinux: failure in selinux_skb_peerlbl_sid()," " unable to determine packet's peer label\n"); return -EACCES; } return 0; } /** * selinux_conn_sid - Determine the child socket label for a connection * @sk_sid: the parent socket's SID * @skb_sid: the packet's SID * @conn_sid: the resulting connection SID * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) { int err = 0; if (skb_sid != SECSID_NULL) err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid); else *conn_sid = sk_sid; return err; } /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, u16 secclass, u32 *socksid) { if (tsec->sockcreate_sid > SECSID_NULL) { *socksid = tsec->sockcreate_sid; return 0; } return security_transition_sid(tsec->sid, tsec->sid, secclass, NULL, socksid); } static bool sock_skip_has_perm(u32 sid) { if (sid == SECINITSID_KERNEL) return true; /* * Before POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT, sockets that * inherited the kernel context from early boot used to be skipped * here, so preserve that behavior unless the capability is set. * * By setting the capability the policy signals that it is ready * for this quirk to be fixed. Note that sockets created by a kernel * thread or a usermode helper executed without a transition will * still be skipped in this check regardless of the policycap * setting. */ if (!selinux_policycap_userspace_initial_context() && sid == SECINITSID_INIT) return true; return false; } static int sock_has_perm(struct sock *sk, u32 perms) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; if (sock_skip_has_perm(sksec->sid)) return 0; ad_net_init_from_sk(&ad, &net, sk); return avc_has_perm(current_sid(), sksec->sid, sksec->sclass, perms, &ad); } static int selinux_socket_create(int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; if (kern) return 0; secclass = socket_type_to_security_class(family, type, protocol); rc = socket_sockcreate_sid(tsec, secclass, &newsid); if (rc) return rc; return avc_has_perm(tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); u32 sid = SECINITSID_KERNEL; int err = 0; if (!kern) { err = socket_sockcreate_sid(tsec, sclass, &sid); if (err) return err; } isec->sclass = sclass; isec->sid = sid; isec->initialized = LABEL_INITIALIZED; if (sock->sk) { sksec = selinux_sock(sock->sk); sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) sksec->sctp_assoc_state = SCTP_ASSOC_UNSET; err = selinux_netlbl_socket_post_create(sock->sk, family); } return err; } static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { struct sk_security_struct *sksec_a = selinux_sock(socka->sk); struct sk_security_struct *sksec_b = selinux_sock(sockb->sk); sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; return 0; } /* Range of port numbers used to automatically bind. Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = selinux_sock(sk); u16 family; int err; err = sock_has_perm(sk, SOCKET__BIND); if (err) goto out; /* If PF_INET or PF_INET6, check name_bind permission for the port. */ family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; u16 family_sa; unsigned short snum; u32 sid, node_perm; /* * sctp_bindx(3) calls via selinux_sctp_bind_connect() * that validates multiple binding addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; family_sa = address->sa_family; switch (family_sa) { case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { if (family == PF_INET6) { /* Length check from inet6_bind_sk() */ if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; /* Family check from __inet6_bind() */ goto err_af; } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) goto err_af; family_sa = AF_INET; } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; case AF_INET6: if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; addr6 = (struct sockaddr_in6 *)address; snum = ntohs(addr6->sin6_port); addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: goto err_af; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sport = htons(snum); ad.u.net->family = family_sa; if (snum) { int low, high; inet_get_local_port_range(sock_net(sk), &low, &high); if (inet_port_requires_bind_service(sock_net(sk), snum) || snum < low || snum > high) { err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) goto out; err = avc_has_perm(sksec->sid, sid, sksec->sclass, SOCKET__NAME_BIND, &ad); if (err) goto out; } } switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: node_perm = TCP_SOCKET__NODE_BIND; break; case SECCLASS_UDP_SOCKET: node_perm = UDP_SOCKET__NODE_BIND; break; case SECCLASS_DCCP_SOCKET: node_perm = DCCP_SOCKET__NODE_BIND; break; case SECCLASS_SCTP_SOCKET: node_perm = SCTP_SOCKET__NODE_BIND; break; default: node_perm = RAWIP_SOCKET__NODE_BIND; break; } err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; err = avc_has_perm(sksec->sid, sid, sksec->sclass, node_perm, &ad); if (err) goto out; } out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = selinux_sock(sk); int err; err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* connect(AF_UNSPEC) has special handling, as it is a documented * way to disconnect the socket */ if (address->sa_family == AF_UNSPEC) return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission * for the port. */ if (sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_DCCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) { struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; unsigned short snum; u32 sid, perm; /* sctp_connectx(3) calls via selinux_sctp_bind_connect() * that validates multiple connect addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; snum = ntohs(addr4->sin_port); break; case AF_INET6: addr6 = (struct sockaddr_in6 *)address; if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; snum = ntohs(addr6->sin6_port); break; default: /* Note that SCTP services expect -EINVAL, whereas * others expect -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; else return -EAFNOSUPPORT; } err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) return err; switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: perm = TCP_SOCKET__NAME_CONNECT; break; case SECCLASS_DCCP_SOCKET: perm = DCCP_SOCKET__NAME_CONNECT; break; case SECCLASS_SCTP_SOCKET: perm = SCTP_SOCKET__NAME_CONNECT; break; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); ad.u.net->family = address->sa_family; err = avc_has_perm(sksec->sid, sid, sksec->sclass, perm, &ad); if (err) return err; } return 0; } /* Supports connect(2), see comments in selinux_socket_connect_helper() */ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { int err; struct sock *sk = sock->sk; err = selinux_socket_connect_helper(sock, address, addrlen); if (err) return err; return selinux_netlbl_socket_connect(sk, address); } static int selinux_socket_listen(struct socket *sock, int backlog) { return sock_has_perm(sock->sk, SOCKET__LISTEN); } static int selinux_socket_accept(struct socket *sock, struct socket *newsock) { int err; struct inode_security_struct *isec; struct inode_security_struct *newisec; u16 sclass; u32 sid; err = sock_has_perm(sock->sk, SOCKET__ACCEPT); if (err) return err; isec = inode_security_novalidate(SOCK_INODE(sock)); spin_lock(&isec->lock); sclass = isec->sclass; sid = isec->sid; spin_unlock(&isec->lock); newisec = inode_security_novalidate(SOCK_INODE(newsock)); newisec->sclass = sclass; newisec->sid = sid; newisec->initialized = LABEL_INITIALIZED; return 0; } static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return sock_has_perm(sock->sk, SOCKET__WRITE); } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return sock_has_perm(sock->sk, SOCKET__READ); } static int selinux_socket_getsockname(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_getpeername(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_setsockopt(struct socket *sock, int level, int optname) { int err; err = sock_has_perm(sock->sk, SOCKET__SETOPT); if (err) return err; return selinux_netlbl_socket_setsockopt(sock, level, optname); } static int selinux_socket_getsockopt(struct socket *sock, int level, int optname) { return sock_has_perm(sock->sk, SOCKET__GETOPT); } static int selinux_socket_shutdown(struct socket *sock, int how) { return sock_has_perm(sock->sk, SOCKET__SHUTDOWN); } static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { struct sk_security_struct *sksec_sock = selinux_sock(sock); struct sk_security_struct *sksec_other = selinux_sock(other); struct sk_security_struct *sksec_new = selinux_sock(newsk); struct common_audit_data ad; struct lsm_network_audit net; int err; ad_net_init_from_sk(&ad, &net, other); err = avc_has_perm(sksec_sock->sid, sksec_other->sid, sksec_other->sclass, UNIX_STREAM_SOCKET__CONNECTTO, &ad); if (err) return err; /* server child socket */ sksec_new->peer_sid = sksec_sock->sid; err = security_sid_mls_copy(sksec_other->sid, sksec_sock->sid, &sksec_new->sid); if (err) return err; /* connecting socket */ sksec_sock->peer_sid = sksec_new->sid; return 0; } static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { struct sk_security_struct *ssec = selinux_sock(sock->sk); struct sk_security_struct *osec = selinux_sock(other->sk); struct common_audit_data ad; struct lsm_network_audit net; ad_net_init_from_sk(&ad, &net, other->sk); return avc_has_perm(ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO, &ad); } static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex, char *addrp, u16 family, u32 peer_sid, struct common_audit_data *ad) { int err; u32 if_sid; u32 node_sid; err = sel_netif_sid(ns, ifindex, &if_sid); if (err) return err; err = avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__INGRESS, ad); if (err) return err; err = sel_netnode_sid(addrp, family, &node_sid); if (err) return err; return avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__RECVFROM, ad); } static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; struct sk_security_struct *sksec = selinux_sock(sk); u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (selinux_secmark_enabled()) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad); if (err) return err; err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad); return err; } static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err, peerlbl_active, secmark_active; struct sk_security_struct *sksec = selinux_sock(sk); u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; if (family != PF_INET && family != PF_INET6) return 0; /* Handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_sock_rcv_skb_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_sock_rcv_skb_compat(sk, skb, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return 0; ad_net_init_from_iif(&ad, &net, skb->skb_iif, family); err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (peerlbl_active) { u32 peer_sid; err = selinux_skb_peerlbl_sid(skb, family, &peer_sid); if (err) return err; err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } } if (secmark_active) { err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } return err; } static int selinux_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { int err = 0; char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = selinux_sock(sock->sk); u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) peer_sid = sksec->peer_sid; if (peer_sid == SECSID_NULL) return -ENOPROTOOPT; err = security_sid_to_context(peer_sid, &scontext, &scontext_len); if (err) return err; if (scontext_len > len) { err = -ERANGE; goto out_len; } if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; out_len: if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; } static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { u32 peer_secid = SECSID_NULL; u16 family; if (skb && skb->protocol == htons(ETH_P_IP)) family = PF_INET; else if (skb && skb->protocol == htons(ETH_P_IPV6)) family = PF_INET6; else if (sock) family = sock->sk->sk_family; else { *secid = SECSID_NULL; return -EINVAL; } if (sock && family == PF_UNIX) { struct inode_security_struct *isec; isec = inode_security_novalidate(SOCK_INODE(sock)); peer_secid = isec->sid; } else if (skb) selinux_skb_peerlbl_sid(skb, family, &peer_secid); *secid = peer_secid; if (peer_secid == SECSID_NULL) return -ENOPROTOOPT; return 0; } static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *sksec = selinux_sock(sk); sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); return 0; } static void selinux_sk_free_security(struct sock *sk) { struct sk_security_struct *sksec = selinux_sock(sk); selinux_netlbl_sk_security_free(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = selinux_sock(sk); struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; newsksec->sclass = sksec->sclass; selinux_netlbl_sk_security_reset(newsksec); } static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { const struct sk_security_struct *sksec = selinux_sock(sk); *secid = sksec->sid; } } static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); struct sk_security_struct *sksec = selinux_sock(sk); if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; } /* * Determines peer_secid for the asoc and updates socket's peer label * if it's the first association on the socket. */ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, struct sk_buff *skb) { struct sock *sk = asoc->base.sk; u16 family = sk->sk_family; struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; int err; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; if (selinux_peerlbl_enabled()) { asoc->peer_secid = SECSID_NULL; /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ err = selinux_skb_peerlbl_sid(skb, family, &asoc->peer_secid); if (err) return err; if (asoc->peer_secid == SECSID_NULL) asoc->peer_secid = SECINITSID_UNLABELED; } else { asoc->peer_secid = SECINITSID_UNLABELED; } if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) { sksec->sctp_assoc_state = SCTP_ASSOC_SET; /* Here as first association on socket. As the peer SID * was allowed by peer recv (and the netif/node checks), * then it is approved by policy and used as the primary * peer SID for getpeercon(3). */ sksec->peer_sid = asoc->peer_secid; } else if (sksec->peer_sid != asoc->peer_secid) { /* Other association peer SIDs are checked to enforce * consistency among the peer SIDs. */ ad_net_init_from_sk(&ad, &net, asoc->base.sk); err = avc_has_perm(sksec->peer_sid, asoc->peer_secid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); if (err) return err; } return 0; } /* Called whenever SCTP receives an INIT or COOKIE ECHO chunk. This * happens on an incoming connect(2), sctp_connectx(3) or * sctp_sendmsg(3) (with no association already present). */ static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); u32 conn_sid; int err; if (!selinux_policycap_extsockclass()) return 0; err = selinux_sctp_process_new_assoc(asoc, skb); if (err) return err; /* Compute the MLS component for the connection and store * the information in asoc. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. */ err = selinux_conn_sid(sksec->sid, asoc->peer_secid, &conn_sid); if (err) return err; asoc->secid = conn_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ return selinux_netlbl_sctp_assoc_request(asoc, skb); } /* Called when SCTP receives a COOKIE ACK chunk as the final * response to an association request (initited by us). */ static int selinux_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); if (!selinux_policycap_extsockclass()) return 0; /* Inherit secid from the parent socket - this will be picked up * by selinux_sctp_sk_clone() if the association gets peeled off * into a new socket. */ asoc->secid = sksec->sid; return selinux_sctp_process_new_assoc(asoc, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting * based on their @optname. */ static int selinux_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { if (walk_size + sizeof(sa_family_t) > addrlen) return -EINVAL; addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; case AF_INET6: len = sizeof(struct sockaddr_in6); break; default: return -EINVAL; } if (walk_size + len > addrlen) return -EINVAL; err = -EINVAL; switch (optname) { /* Bind checks */ case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: err = selinux_socket_bind(sock, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: err = selinux_socket_connect_helper(sock, addr, len); if (err) return err; /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new * primary address is selected. * Note that an SCTP connect(2) call happens before * the SCTP protocol layer and is handled via * selinux_socket_connect(). */ err = selinux_netlbl_socket_connect_locked(sk, addr); break; } if (err) return err; addr_buf += len; walk_size += len; } return 0; } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = selinux_sock(sk); struct sk_security_struct *newsksec = selinux_sock(newsk); /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. */ if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); newsksec->sid = asoc->secid; newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { struct sk_security_struct *ssksec = selinux_sock(ssk); struct sk_security_struct *sksec = selinux_sock(sk); ssksec->sclass = sksec->sclass; ssksec->sid = sksec->sid; /* replace the existing subflow label deleting the existing one * and re-recreating a new label using the updated context */ selinux_netlbl_sk_security_free(ssksec); return selinux_netlbl_socket_post_create(ssk, ssk->sk_family); } static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct sk_security_struct *sksec = selinux_sock(sk); int err; u16 family = req->rsk_ops->family; u32 connsid; u32 peersid; err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; err = selinux_conn_sid(sksec->sid, peersid, &connsid); if (err) return err; req->secid = connsid; req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; /* NOTE: Ideally, we should also get the isec->sid for the new socket in sync, but we don't have the isec available yet. So we will wait until sock_graft to do it, by which time it will have been created and available. */ /* We don't need to take any sort of lock here as we are the only * thread with access to newsksec */ selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family); } static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = selinux_sock(sk); /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } static int selinux_secmark_relabel_packet(u32 sid) { return avc_has_perm(current_sid(), sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } static void selinux_secmark_refcount_inc(void) { atomic_inc(&selinux_secmark_refcount); } static void selinux_secmark_refcount_dec(void) { atomic_dec(&selinux_secmark_refcount); } static void selinux_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { flic->flowic_secid = req->secid; } static int selinux_tun_dev_alloc_security(void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); tunsec->sid = current_sid(); return 0; } static int selinux_tun_dev_create(void) { u32 sid = current_sid(); /* we aren't taking into account the "sockcreate" SID since the socket * that is being created here is not a socket in the traditional sense, * instead it is a private sock, accessible only to the kernel, and * representing a wide range of network traffic spanning multiple * connections unlike traditional sockets - check the TUN driver to * get a better understanding of why this socket is special */ return avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE, NULL); } static int selinux_tun_dev_attach_queue(void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); } static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); struct sk_security_struct *sksec = selinux_sock(sk); /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply * labeling without the support of the TUN user the resulting labeled * traffic from the other end of the connection would almost certainly * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; return 0; } static int selinux_tun_dev_open(void *security) { struct tun_security_struct *tunsec = selinux_tun_dev(security); u32 sid = current_sid(); int err; err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; err = avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELTO, NULL); if (err) return err; tunsec->sid = sid; return 0; } #ifdef CONFIG_NETFILTER static unsigned int selinux_ip_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int ifindex; u16 family; char *addrp; u32 peer_sid; struct common_audit_data ad; struct lsm_network_audit net; int secmark_active, peerlbl_active; if (!selinux_policycap_netpeer()) return NF_ACCEPT; secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; family = state->pf; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0) return NF_DROP; ifindex = state->in->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0) return NF_DROP; if (peerlbl_active) { int err; err = selinux_inet_sys_rcv_skb(state->net, ifindex, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 1); return NF_DROP; } } if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; if (netlbl_enabled()) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH * protection */ if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; u32 sid; if (!netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ sk = sk_to_full_sk(skb->sk); if (sk) { struct sk_security_struct *sksec; if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and * not the parent socket. unfortunately, we can't * lookup the request_sock yet as it isn't queued on * the parent socket until after the SYN-ACK is sent. * the "solution" is to simply pass the packet as-is * as any IP option based labeling should be copied * from the initial connection request (in the IP * layer). it is far from ideal, but until we get a * security label in the packet itself this is the * best we can do. */ return NF_ACCEPT; /* standard practice, label using the parent socket */ sksec = selinux_sock(sk); sid = sksec->sid; } else sid = SECINITSID_KERNEL; if (selinux_netlbl_skbuff_setsid(skb, state->pf, sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk; struct sk_security_struct *sksec; struct common_audit_data ad; struct lsm_network_audit net; u8 proto = 0; sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; sksec = selinux_sock(sk); ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf); if (selinux_parse_skb(skb, &ad, NULL, 0, &proto)) return NF_DROP; if (selinux_secmark_enabled()) if (avc_has_perm(sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) return NF_DROP_ERR(-ECONNREFUSED); return NF_ACCEPT; } static unsigned int selinux_ip_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { u16 family; u32 secmark_perm; u32 peer_sid; int ifindex; struct sock *sk; struct common_audit_data ad; struct lsm_network_audit net; char *addrp; int secmark_active, peerlbl_active; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_ip_postroute_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_ip_postroute_compat(skb, state); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; sk = skb_to_full_sk(skb); #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. * NOTE: if this is a local socket (skb->sk != NULL) that is in the * TCP listening state we cannot wait until the XFRM processing * is done as we will miss out on the SA label if we do; * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && !(sk && sk_listener(sk))) return NF_ACCEPT; #endif family = state->pf; if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet * to determine which and if the packet is being forwarded * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) return NF_DROP; } else { secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned * to the connection/request_sock but unfortunately we can't * query the request_sock as it isn't queued on the parent * socket until after the SYN-ACK packet is sent; the only * viable choice is to regenerate the label like we do in * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; struct sk_security_struct *sksec; sksec = selinux_sock(sk); if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL * and the packet has been through at least one XFRM * transformation then we must be dealing with the "final" * form of labeled IPsec packet; since we've already applied * all of our access controls on this packet we can safely * pass the packet. */ if (skb_sid == SECSID_NULL) { switch (family) { case PF_INET: if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; case PF_INET6: if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; default: return NF_DROP_ERR(-ECONNREFUSED); } } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; } else { /* Locally generated packet, fetch the security label from the * associated socket. */ struct sk_security_struct *sksec = selinux_sock(sk); peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } ifindex = state->out->ifindex; ad_net_init_from_iif(&ad, &net, ifindex, family); if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL)) return NF_DROP; if (secmark_active) if (avc_has_perm(peer_sid, skb->secmark, SECCLASS_PACKET, secmark_perm, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (peerlbl_active) { u32 if_sid; u32 node_sid; if (sel_netif_sid(state->net, ifindex, &if_sid)) return NF_DROP; if (avc_has_perm(peer_sid, if_sid, SECCLASS_NETIF, NETIF__EGRESS, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (sel_netnode_sid(addrp, family, &node_sid)) return NF_DROP; if (avc_has_perm(peer_sid, node_sid, SECCLASS_NODE, NODE__SENDTO, &ad)) return NF_DROP_ERR(-ECONNREFUSED); } return NF_ACCEPT; } #endif /* CONFIG_NETFILTER */ static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_type) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net; u8 driver; u8 xperm; if (sock_skip_has_perm(sksec->sid)) return 0; ad_net_init_from_sk(&ad, &net, sk); driver = nlmsg_type >> 8; xperm = nlmsg_type & 0xff; return avc_has_extended_perms(current_sid(), sksec->sid, sksec->sclass, perms, driver, xperm, &ad); } static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { int rc = 0; unsigned int msg_len; unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = selinux_sock(sk); u16 sclass = sksec->sclass; u32 perm; while (data_len >= nlmsg_total_size(0)) { nlh = (struct nlmsghdr *)data; /* NOTE: the nlmsg_len field isn't reliably set by some netlink * users which means we can't reject skb's with bogus * length fields; our solution is to follow what * netlink_rcv_skb() does and simply skip processing at * messages with length fields that are clearly junk */ if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) return 0; rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); if (rc == 0) { if (selinux_policycap_netlink_xperm()) { rc = nlmsg_sock_has_extended_perms( sk, perm, nlh->nlmsg_type); } else { rc = sock_has_perm(sk, perm); } if (rc) return rc; } else if (rc == -EINVAL) { /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" " message: protocol=%hu nlmsg_type=%hu sclass=%s" " pid=%d comm=%s\n", sk->sk_protocol, nlh->nlmsg_type, secclass_map[sclass - 1].name, task_pid_nr(current), current->comm); if (enforcing_enabled() && !security_get_allow_unknown()) return rc; rc = 0; } else if (rc == -ENOENT) { /* -ENOENT is a missing socket/class mapping, ignore */ rc = 0; } else { return rc; } /* move to the next message after applying netlink padding */ msg_len = NLMSG_ALIGN(nlh->nlmsg_len); if (msg_len >= data_len) return 0; data_len -= msg_len; data += msg_len; } return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { isec->sclass = sclass; isec->sid = current_sid(); } static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(ipc_perms); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = ipc_perms->key; return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; return 0; } /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case MSG_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: perms = MSGQ__GETATTR | MSGQ__ASSOCIATE; break; case IPC_SET: perms = MSGQ__SETATTR; break; case IPC_RMID: perms = MSGQ__DESTROY; break; default: return 0; } return ipc_has_perm(msq, perms); } static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); /* * First time through, need to assign label to the message */ if (msec->sid == SECINITSID_UNLABELED) { /* * Compute new sid based on current process and * message queue this message will be stored in */ rc = security_transition_sid(sid, isec->sid, SECCLASS_MSG, NULL, &msec->sid); if (rc) return rc; } ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; /* Can this process write to the queue? */ rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ rc = avc_has_perm(msec->sid, isec->sid, SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); return rc; } static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = task_sid_obj(target); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } /* Note, at this point, shp is locked down */ static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { u32 perms; switch (cmd) { case IPC_INFO: case SHM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case SHM_STAT: case SHM_STAT_ANY: perms = SHM__GETATTR | SHM__ASSOCIATE; break; case IPC_SET: perms = SHM__SETATTR; break; case SHM_LOCK: case SHM_UNLOCK: perms = SHM__LOCK; break; case IPC_RMID: perms = SHM__DESTROY; break; default: return 0; } return ipc_has_perm(shp, perms); } static int selinux_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { u32 perms; if (shmflg & SHM_RDONLY) perms = SHM__READ; else perms = SHM__READ | SHM__WRITE; return ipc_has_perm(shp, perms); } /* Semaphore security operations */ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } /* Note, at this point, sma is locked down */ static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd) { int err; u32 perms; switch (cmd) { case IPC_INFO: case SEM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case GETPID: case GETNCNT: case GETZCNT: perms = SEM__GETATTR; break; case GETVAL: case GETALL: perms = SEM__READ; break; case SETVAL: case SETALL: perms = SEM__WRITE; break; case IPC_RMID: perms = SEM__DESTROY; break; case IPC_SET: perms = SEM__SETATTR; break; case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: perms = SEM__GETATTR | SEM__ASSOCIATE; break; default: return 0; } err = ipc_has_perm(sma, perms); return err; } static int selinux_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { u32 perms; if (alter) perms = SEM__READ | SEM__WRITE; else perms = SEM__READ; return ipc_has_perm(sma, perms); } static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { u32 av = 0; av = 0; if (flag & S_IRUGO) av |= IPC__UNIX_READ; if (flag & S_IWUGO) av |= IPC__UNIX_WRITE; if (av == 0) return 0; return ipc_has_perm(ipcp, av); } static void selinux_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop) { struct ipc_security_struct *isec = selinux_ipc(ipcp); prop->selinux.secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) { if (inode) inode_doinit_with_dentry(inode, dentry); } static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p, char **value) { const struct task_security_struct *tsec; int error; u32 sid; u32 len; rcu_read_lock(); tsec = selinux_cred(__task_cred(p)); if (p != current) { error = avc_has_perm(current_sid(), tsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto err_unlock; } switch (attr) { case LSM_ATTR_CURRENT: sid = tsec->sid; break; case LSM_ATTR_PREV: sid = tsec->osid; break; case LSM_ATTR_EXEC: sid = tsec->exec_sid; break; case LSM_ATTR_FSCREATE: sid = tsec->create_sid; break; case LSM_ATTR_KEYCREATE: sid = tsec->keycreate_sid; break; case LSM_ATTR_SOCKCREATE: sid = tsec->sockcreate_sid; break; default: error = -EOPNOTSUPP; goto err_unlock; } rcu_read_unlock(); if (sid == SECSID_NULL) { *value = NULL; return 0; } error = security_sid_to_context(sid, value, &len); if (error) return error; return len; err_unlock: rcu_read_unlock(); return error; } static int selinux_lsm_setattr(u64 attr, void *value, size_t size) { struct task_security_struct *tsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; char *str = value; /* * Basic control over ability to set these attributes at all. */ switch (attr) { case LSM_ATTR_EXEC: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETEXEC, NULL); break; case LSM_ATTR_FSCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETFSCREATE, NULL); break; case LSM_ATTR_KEYCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETKEYCREATE, NULL); break; case LSM_ATTR_SOCKCREATE: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, NULL); break; case LSM_ATTR_CURRENT: error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS, PROCESS__SETCURRENT, NULL); break; default: error = -EOPNOTSUPP; break; } if (error) return error; /* Obtain a SID for the context, if one was specified. */ if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; } error = security_context_to_sid(value, size, &sid, GFP_KERNEL); if (error == -EINVAL && attr == LSM_ATTR_FSCREATE) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, * otherwise the context contains a nul and * we should audit that */ if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) return error; audit_log_format(ab, "op=fscreate invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return error; } error = security_context_to_sid_force(value, size, &sid); } if (error) return error; } new = prepare_creds(); if (!new) return -ENOMEM; /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ tsec = selinux_cred(new); if (attr == LSM_ATTR_EXEC) { tsec->exec_sid = sid; } else if (attr == LSM_ATTR_FSCREATE) { tsec->create_sid = sid; } else if (attr == LSM_ATTR_KEYCREATE) { if (sid) { error = avc_has_perm(mysid, sid, SECCLASS_KEY, KEY__CREATE, NULL); if (error) goto abort_change; } tsec->keycreate_sid = sid; } else if (attr == LSM_ATTR_SOCKCREATE) { tsec->sockcreate_sid = sid; } else if (attr == LSM_ATTR_CURRENT) { error = -EINVAL; if (sid == 0) goto abort_change; if (!current_is_single_threaded()) { error = security_bounded_transition(tsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ error = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = ptrace_parent_sid(); if (ptsid != 0) { error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (error) goto abort_change; } tsec->sid = sid; } else { error = -EINVAL; goto abort_change; } commit_creds(new); return size; abort_change: abort_creds(new); return error; } /** * selinux_getselfattr - Get SELinux current task attributes * @attr: the requested attribute * @ctx: buffer to receive the result * @size: buffer size (input), buffer size used (output) * @flags: unused * * Fill the passed user space @ctx with the details of the requested * attribute. * * Returns the number of attributes on success, an error code otherwise. * There will only ever be one attribute. */ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, u32 *size, u32 flags) { int rc; char *val = NULL; int val_len; val_len = selinux_lsm_getattr(attr, current, &val); if (val_len < 0) return val_len; rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0); kfree(val); return (!rc ? 1 : rc); } static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) { int rc; rc = selinux_lsm_setattr(attr, ctx->ctx, ctx->ctx_len); if (rc > 0) return 0; return rc; } static int selinux_getprocattr(struct task_struct *p, const char *name, char **value) { unsigned int attr = lsm_name_to_attr(name); int rc; if (attr) { rc = selinux_lsm_getattr(attr, p, value); if (rc != -EOPNOTSUPP) return rc; } return -EINVAL; } static int selinux_setprocattr(const char *name, void *value, size_t size) { int attr = lsm_name_to_attr(name); if (attr) return selinux_lsm_setattr(attr, value, size); return -EINVAL; } static int selinux_ismaclabel(const char *name) { return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return security_sid_to_context(secid, secdata, seclen); } static int selinux_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, u32 *seclen) { return selinux_secid_to_secctx(prop->selinux.secid, secdata, seclen); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) { kfree(secdata); } static void selinux_inode_invalidate_secctx(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); spin_lock(&isec->lock); isec->initialized = LABEL_INVALID; spin_unlock(&isec->lock); } /* * called with inode->i_mutex locked */ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, ctxlen, 0); /* Do not return error when suppressing label (SBLABEL_MNT not set). */ return rc == -EOPNOTSUPP ? 0 : rc; } /* * called with inode->i_mutex locked */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0, NULL); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; return 0; } #ifdef CONFIG_KEYS static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; struct key_security_struct *ksec = selinux_key(k); tsec = selinux_cred(cred); if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; return 0; } static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; struct key_security_struct *ksec; u32 perm, sid; switch (need_perm) { case KEY_NEED_VIEW: perm = KEY__VIEW; break; case KEY_NEED_READ: perm = KEY__READ; break; case KEY_NEED_WRITE: perm = KEY__WRITE; break; case KEY_NEED_SEARCH: perm = KEY__SEARCH; break; case KEY_NEED_LINK: perm = KEY__LINK; break; case KEY_NEED_SETATTR: perm = KEY__SETATTR; break; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: return 0; default: WARN_ON(1); return -EPERM; } sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); ksec = selinux_key(key); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { struct key_security_struct *ksec = selinux_key(key); char *context = NULL; unsigned len; int rc; rc = security_sid_to_context(ksec->sid, &context, &len); if (!rc) rc = len; *_buffer = context; return rc; } #ifdef CONFIG_KEY_NOTIFICATIONS static int selinux_watch_key(struct key *key) { struct key_security_struct *ksec = selinux_key(key); u32 sid = current_sid(); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL); } #endif #endif #ifdef CONFIG_SECURITY_INFINIBAND static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibpkey_audit ibpkey; err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBPKEY; ibpkey.subnet_prefix = subnet_prefix; ibpkey.pkey = pkey_val; ad.u.ibpkey = &ibpkey; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_PKEY, INFINIBAND_PKEY__ACCESS, &ad); } static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, u8 port_num) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibendport_audit ibendport; err = security_ib_endport_sid(dev_name, port_num, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; ibendport.dev_name = dev_name; ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(sec->sid, sid, SECCLASS_INFINIBAND_ENDPORT, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } static int selinux_ib_alloc_security(void *ib_sec) { struct ib_security_struct *sec = selinux_ib(ib_sec); sec->sid = current_sid(); return 0; } #endif #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, unsigned int size) { u32 sid = current_sid(); int ret; switch (cmd) { case BPF_MAP_CREATE: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); break; case BPF_PROG_LOAD: ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); break; default: ret = 0; break; } return ret; } static u32 bpf_map_fmode_to_av(fmode_t fmode) { u32 av = 0; if (fmode & FMODE_READ) av |= BPF__MAP_READ; if (fmode & FMODE_WRITE) av |= BPF__MAP_WRITE; return av; } /* This function will check the file pass through unix socket or binder to see * if it is a bpf related object. And apply corresponding checks on the bpf * object based on the type. The bpf maps and programs, not like other files and * socket, are using a shared anonymous inode inside the kernel as their inode. * So checking that inode cannot identify if the process have privilege to * access the bpf object and that's why we have to add this additional check in * selinux_file_receive and selinux_binder_transfer_files. */ static int bpf_fd_pass(const struct file *file, u32 sid) { struct bpf_security_struct *bpfsec; struct bpf_prog *prog; struct bpf_map *map; int ret; if (file->f_op == &bpf_map_fops) { map = file->private_data; bpfsec = map->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(file->f_mode), NULL); if (ret) return ret; } else if (file->f_op == &bpf_prog_fops) { prog = file->private_data; bpfsec = prog->aux->security; ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); if (ret) return ret; } return 0; } static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = map->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(fmode), NULL); } static int selinux_bpf_prog(struct bpf_prog *prog) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = prog->aux->security; return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); } static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); map->security = bpfsec; return 0; } static void selinux_bpf_map_free(struct bpf_map *map) { struct bpf_security_struct *bpfsec = map->security; map->security = NULL; kfree(bpfsec); } static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); prog->aux->security = bpfsec; return 0; } static void selinux_bpf_prog_free(struct bpf_prog *prog) { struct bpf_security_struct *bpfsec = prog->aux->security; prog->aux->security = NULL; kfree(bpfsec); } static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, const struct path *path) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); token->security = bpfsec; return 0; } static void selinux_bpf_token_free(struct bpf_token *token) { struct bpf_security_struct *bpfsec = token->security; token->security = NULL; kfree(bpfsec); } #endif struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_key = sizeof(struct key_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), #ifdef CONFIG_PERF_EVENTS .lbs_perf_event = sizeof(struct perf_event_security_struct), #endif .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, .lbs_tun_dev = sizeof(struct tun_security_struct), .lbs_ib = sizeof(struct ib_security_struct), }; #ifdef CONFIG_PERF_EVENTS static int selinux_perf_event_open(struct perf_event_attr *attr, int type) { u32 requested, sid = current_sid(); if (type == PERF_SECURITY_OPEN) requested = PERF_EVENT__OPEN; else if (type == PERF_SECURITY_CPU) requested = PERF_EVENT__CPU; else if (type == PERF_SECURITY_KERNEL) requested = PERF_EVENT__KERNEL; else if (type == PERF_SECURITY_TRACEPOINT) requested = PERF_EVENT__TRACEPOINT; else return -EINVAL; return avc_has_perm(sid, sid, SECCLASS_PERF_EVENT, requested, NULL); } static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; perfsec = selinux_perf_event(event->security); perfsec->sid = current_sid(); return 0; } static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); } static int selinux_perf_event_write(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); } #endif #ifdef CONFIG_IO_URING /** * selinux_uring_override_creds - check the requested cred override * @new: the target creds * * Check to see if the current task is allowed to override it's credentials * to service an io_uring operation. */ static int selinux_uring_override_creds(const struct cred *new) { return avc_has_perm(current_sid(), cred_sid(new), SECCLASS_IO_URING, IO_URING__OVERRIDE_CREDS, NULL); } /** * selinux_uring_sqpoll - check if a io_uring polling thread can be created * * Check to see if the current task is allowed to create a new io_uring * kernel polling thread. */ static int selinux_uring_sqpoll(void) { u32 sid = current_sid(); return avc_has_perm(sid, sid, SECCLASS_IO_URING, IO_URING__SQPOLL, NULL); } /** * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed * @ioucmd: the io_uring command structure * * Check to see if the current domain is allowed to execute an * IORING_OP_URING_CMD against the device/file specified in @ioucmd. * */ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) { struct file *file = ioucmd->file; struct inode *inode = file_inode(file); struct inode_security_struct *isec = selinux_inode(inode); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return avc_has_perm(current_sid(), isec->sid, SECCLASS_IO_URING, IO_URING__CMD, &ad); } #endif /* CONFIG_IO_URING */ static const struct lsm_id selinux_lsmid = { .name = "selinux", .id = LSM_ID_SELINUX, }; /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, * 2. hooks that both access structures allocated by other hooks, and allocate * structures that can be later accessed by other hooks (mostly "cloning" * hooks), * 3. hooks that only allocate structures that can be later accessed by other * hooks ("allocating" hooks). * * Please follow block comment delimiters in the list to keep this order. */ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder), LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file), LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme), LSM_HOOK_INIT(capget, selinux_capget), LSM_HOOK_INIT(capset, selinux_capset), LSM_HOOK_INIT(capable, selinux_capable), LSM_HOOK_INIT(quotactl, selinux_quotactl), LSM_HOOK_INIT(quota_on, selinux_quota_on), LSM_HOOK_INIT(syslog, selinux_syslog), LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory), LSM_HOOK_INIT(netlink_send, selinux_netlink_send), LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds), LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts), LSM_HOOK_INIT(sb_mnt_opts_compat, selinux_sb_mnt_opts_compat), LSM_HOOK_INIT(sb_remount, selinux_sb_remount), LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount), LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options), LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs), LSM_HOOK_INIT(sb_mount, selinux_mount), LSM_HOOK_INIT(sb_umount, selinux_umount), LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts), LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts), LSM_HOOK_INIT(move_mount, selinux_move_mount), LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security), LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as), LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security), LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security), LSM_HOOK_INIT(inode_init_security_anon, selinux_inode_init_security_anon), LSM_HOOK_INIT(inode_create, selinux_inode_create), LSM_HOOK_INIT(inode_link, selinux_inode_link), LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink), LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink), LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir), LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir), LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod), LSM_HOOK_INIT(inode_rename, selinux_inode_rename), LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink), LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link), LSM_HOOK_INIT(inode_permission, selinux_inode_permission), LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr), LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr), LSM_HOOK_INIT(inode_xattr_skipcap, selinux_inode_xattr_skipcap), LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr), LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr), LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr), LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr), LSM_HOOK_INIT(inode_set_acl, selinux_inode_set_acl), LSM_HOOK_INIT(inode_get_acl, selinux_inode_get_acl), LSM_HOOK_INIT(inode_remove_acl, selinux_inode_remove_acl), LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), LSM_HOOK_INIT(inode_getlsmprop, selinux_inode_getlsmprop), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security), LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), LSM_HOOK_INIT(file_lock, selinux_file_lock), LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl), LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner), LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask), LSM_HOOK_INIT(file_receive, selinux_file_receive), LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), LSM_HOOK_INIT(cred_getlsmprop, selinux_cred_getlsmprop), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data), LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), LSM_HOOK_INIT(current_getlsmprop_subj, selinux_current_getlsmprop_subj), LSM_HOOK_INIT(task_getlsmprop_obj, selinux_task_getlsmprop_obj), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit), LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit), LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler), LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler), LSM_HOOK_INIT(task_movememory, selinux_task_movememory), LSM_HOOK_INIT(task_kill, selinux_task_kill), LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode), LSM_HOOK_INIT(userns_create, selinux_userns_create), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), LSM_HOOK_INIT(ipc_getlsmprop, selinux_ipc_getlsmprop), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate), LSM_HOOK_INIT(getselfattr, selinux_getselfattr), LSM_HOOK_INIT(setselfattr, selinux_setselfattr), LSM_HOOK_INIT(getprocattr, selinux_getprocattr), LSM_HOOK_INIT(setprocattr, selinux_setprocattr), LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel), LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid), LSM_HOOK_INIT(release_secctx, selinux_release_secctx), LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx), LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx), LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send), LSM_HOOK_INIT(socket_create, selinux_socket_create), LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create), LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair), LSM_HOOK_INIT(socket_bind, selinux_socket_bind), LSM_HOOK_INIT(socket_connect, selinux_socket_connect), LSM_HOOK_INIT(socket_listen, selinux_socket_listen), LSM_HOOK_INIT(socket_accept, selinux_socket_accept), LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown), LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb), LSM_HOOK_INIT(socket_getpeersec_stream, selinux_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security), LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security), LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid), LSM_HOOK_INIT(sock_graft, selinux_sock_graft), LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established), LSM_HOOK_INIT(mptcp_add_subflow, selinux_mptcp_add_subflow), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet), LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete), LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free), LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete), LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup), LSM_HOOK_INIT(xfrm_state_pol_flow_match, selinux_xfrm_state_pol_flow_match), LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS LSM_HOOK_INIT(watch_key, selinux_watch_key), #endif #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll), LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd), #endif /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ LSM_HOOK_INIT(fs_context_submount, selinux_fs_context_submount), LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif /* * PUT "ALLOCATING" HOOKS HERE */ LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), LSM_HOOK_INIT(lsmprop_to_secctx, selinux_lsmprop_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc), LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc), LSM_HOOK_INIT(xfrm_state_alloc_acquire, selinux_xfrm_state_alloc_acquire), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, selinux_key_alloc), #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), #endif }; static __init int selinux_init(void) { pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(selinux_enforcing_boot); selinux_avc_init(); mutex_init(&selinux_state.status_lock); mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); if (!default_noexec) pr_notice("SELinux: virtual memory is executable by default\n"); avc_init(); avtab_cache_init(); ebitmap_cache_init(); hashtab_cache_init(); security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), &selinux_lsmid); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC LSM notifier callback\n"); if (selinux_enforcing_boot) pr_debug("SELinux: Starting in enforcing mode\n"); else pr_debug("SELinux: Starting in permissive mode\n"); fs_validate_description("selinux", selinux_fs_parameters); return 0; } static void delayed_superblock_init(struct super_block *sb, void *unused) { selinux_set_mnt_opts(sb, NULL, 0, NULL); } void selinux_complete_init(void) { pr_debug("SELinux: Completing initialization.\n"); /* Set up any superblocks initialized prior to the policy load. */ pr_debug("SELinux: Setting up existing superblocks.\n"); iterate_supers(delayed_superblock_init, NULL); } /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled_boot, .blobs = &selinux_blob_sizes, .init = selinux_init, }; #if defined(CONFIG_NETFILTER) static const struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = selinux_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ip_forward, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, }, { .hook = selinux_ip_output, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif /* IPV6 */ }; static int __net_init selinux_nf_register(struct net *net) { return nf_register_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static void __net_exit selinux_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, }; static int __init selinux_nf_ip_init(void) { int err; if (!selinux_enabled_boot) return 0; pr_debug("SELinux: Registering netfilter hooks\n"); err = register_pernet_subsys(&selinux_net_ops); if (err) panic("SELinux: register_pernet_subsys: error %d\n", err); return 0; } __initcall(selinux_nf_ip_init); #endif /* CONFIG_NETFILTER */ |
| 179 179 179 179 179 179 178 178 178 179 179 179 179 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include <linux/jump_label.h> #include <linux/string_choices.h> #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/csd.h> #undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ __flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } static __always_inline void send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void send_call_function_ipi_mask(struct cpumask *mask) { trace_ipi_send_cpumask(mask, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } static __always_inline void csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) { trace_csd_function_entry(func, csd); func(info); trace_csd_function_exit(func, csd); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); /* * Parse the csdlock_debug= kernel boot parameter. * * If you need to restore the old "ext" value that once provided * additional debugging information, reapply the following commits: * * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") */ static int __init csdlock_debug(char *str) { int ret; unsigned int val = 0; ret = get_option(&str, &val); if (ret) { if (val) static_branch_enable(&csdlock_debug_enabled); else static_branch_disable(&csdlock_debug_enabled); } return 1; } __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ module_param(panic_on_ipistall, int, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(call_single_data_t *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline void csd_lock_record(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } static int csd_lock_wait_getcpu(call_single_data_t *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } static atomic_t n_csd_lock_stuck; /** * csd_lock_is_stuck - Has a CSD-lock acquisition been stuck too long? * * Returns @true if a CSD-lock acquisition is stuck and has been stuck * long enough for a "non-responsive CSD lock" message to be printed. */ bool csd_lock_is_stuck(void) { return !!atomic_read(&n_csd_lock_stuck); } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id, unsigned long *nmessages) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); atomic_dec(&n_csd_lock_stuck); return true; } ts2 = ktime_get_mono_fast_ns(); /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns * (*nmessages + 1) * (!*nmessages ? 1 : (ilog2(num_online_cpus()) / 2 + 1)) || csd_lock_timeout_ns == 0)) return false; if (ts0 > ts2) { /* Our own sched_clock went backward; don't blame another CPU. */ ts_delta = ts0 - ts2; pr_alert("sched_clock on CPU %d went backward by %llu ns\n", raw_smp_processor_id(), ts_delta); *ts1 = ts2; return false; } firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ /* How long since this CSD lock was stuck. */ ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta, cpu, csd->func, csd->info); (*nmessages)++; if (firsttime) atomic_inc(&n_csd_lock_stuck); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering * on underflows when the TSC is out of sync between sockets. */ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } if (firsttime) dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static void __csd_lock_wait(call_single_data_t *csd) { unsigned long nmessages = 0; int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = ktime_get_mono_fast_ns(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } static __always_inline void csd_lock_wait(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); return; } smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else static void csd_lock_record(call_single_data_t *csd) { } static __always_inline void csd_lock_wait(call_single_data_t *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(call_single_data_t *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(call_single_data_t *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->node.u_flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * We have to check the type of the CSD before queueing it, because * once queued it can have its flags cleared by * flush_smp_call_function_queue() * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; csd = container_of(node, call_single_data_t, node.llist); func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* * The list addition should be visible to the target CPU when it pops * the head of the list to pull the entry off it in the IPI handler * because of normal cache coherency rules implied by the underlying * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, call_single_data_t *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->node.llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { __flush_smp_call_function_queue(true); } /** * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; atomic_t *tbt; lockdep_assert_irqs_disabled(); /* Allow waiters to send backtrace NMI from here onwards */ tbt = this_cpu_ptr(&trigger_backtrace); atomic_set_release(tbt, 1); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, node.llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } csd_lock_record(csd); csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->node.llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->node.llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) { csd = llist_entry(entry, typeof(*csd), node.llist); csd_do_func(sched_ttwu_pending, entry, csd); } } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * from task context (idle, migration thread) * * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to * handle queued SMP function calls before scheduling. * * The migration thread has to ensure that an eventually pending wakeup has * been handled before it migrates a task. */ void flush_smp_call_function_queue(void) { unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); __flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async() - Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. * * Return: %0 on success or negative errno value on error */ int smp_call_function_single_async(int cpu, call_single_data_t *csd) { int err = 0; preempt_disable(); if (csd->node.u_flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->node.u_flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /* * Flags to be used as scf_flags argument of smp_call_function_many_cond(). * * %SCF_WAIT: Wait until function execution is completed * %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask */ #define SCF_WAIT (1U << 0) #define SCF_RUN_LOCAL (1U << 1) static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, unsigned int scf_flags, smp_cond_func_t cond_func) { int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; int nr_cpus = 0; bool run_remote = false; bool run_local = false; lockdep_assert_preemption_disabled(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ if (cpu_online(this_cpu) && !oops_in_progress && !early_boot_irqs_disabled) lockdep_assert_irqs_enabled(); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Check if we need local execution. */ if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask)) run_local = true; /* Check if we need remote execution, i.e., any CPU excluding this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (cpu < nr_cpu_ids) run_remote = true; if (run_remote) { cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask); continue; } csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } } /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { unsigned long flags; local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags); } if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait * (atomically) until function has completed on other CPUs. If * %SCF_RUN_LOCAL is set, the function will also be run locally * if the local CPU is set in the @cpumask. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) set_nr_cpu_ids(nr_cpus); return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, str_plural(num_nodes), num_cpus, str_plural(num_cpus)); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { unsigned int scf_flags = SCF_RUN_LOCAL; if (wait) scf_flags |= SCF_WAIT; preempt_disable(); smp_call_function_many_cond(mask, func, info, scf_flags, cond_func); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; for_each_possible_cpu(cpu) { preempt_disable(); if (cpu != smp_processor_id() && cpu_online(cpu)) wake_up_if_idle(cpu); preempt_enable(); } } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * struct smp_call_on_cpu_struct - Call a function on a specific CPU * @work: &work_struct * @done: &completion to signal * @func: function to call * @data: function's data argument * @ret: return value from @func * @cpu: target CPU (%-1 for any CPU) * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); destroy_work_on_stack(&sscs.work); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 417 182 173 170 254 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/fanotify.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_SETELEM_RESET, AUDIT_NFT_OP_RULE_RESET, AUDIT_NFT_OP_INVALID, }; extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_uring_entry(u8 op) { /* * We intentionally check audit_context() before audit_enabled as most * Linux systems (as of ~2021) rely on systemd which forces audit to * be enabled regardless of the user's audit configuration. */ if (unlikely(audit_context() && audit_enabled)) __audit_uring_entry(op); } static inline void audit_uring_exit(int success, long code) { if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_openat2_how(struct open_how *how) { if (unlikely(!audit_dummy_context())) __audit_openat2_how(how); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (!audit_dummy_context()) __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) { } static inline void audit_uring_exit(int success, long code) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_openat2_how(struct open_how *how) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 17 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ #define LOOKUP_DIRECTORY 0x0002 /* require a directory */ #define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ #define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ #define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ #define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN 0x0100 /* ... in open */ #define LOOKUP_CREATE 0x0200 /* ... in object creation */ #define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ #define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ /* internal use only */ #define LOOKUP_PARENT 0x0010 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ #define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 534 534 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fault-inject.h> #include <linux/debugfs.h> #include <linux/error-injection.h> #include <linux/mm.h> static struct { struct fault_attr attr; bool ignore_gfp_highmem; bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_reclaim = true, .ignore_gfp_highmem = true, .min_order = 1, }; static int __init setup_fail_page_alloc(char *str) { return setup_fault_attr(&fail_page_alloc.attr, str); } __setup("fail_page_alloc=", setup_fail_page_alloc); bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { int flags = 0; if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; if (fail_page_alloc.ignore_gfp_reclaim && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) flags |= FAULT_NOWARN; return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_page_alloc_debugfs(void) { umode_t mode = S_IFREG | 0600; struct dentry *dir; dir = fault_create_debugfs_attr("fail_page_alloc", NULL, &fail_page_alloc.attr); debugfs_create_bool("ignore-gfp-wait", mode, dir, &fail_page_alloc.ignore_gfp_reclaim); debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem); debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); return 0; } late_initcall(fail_page_alloc_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ |
| 1212 1214 32 32 1215 1214 1213 338 1213 1 1 656 655 655 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #define RCU_NOCB_LOCKDEP_WARN(c, s) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU // Bits for ->trc_reader_special.b.need_qs field. #define TRC_NEED_QS 0x1 // Task needs a quiescent state. #define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); void rcu_tasks_trace_qs_blkd(struct task_struct *t); # define rcu_tasks_trace_qs(t) \ do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs(t); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data..unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) // See RCU_LOCKDEP_WARN() for an explanation of the double call to // debug_lockdep_rcu_enabled(). static inline bool lockdep_assert_rcu_helper(bool c) { return debug_lockdep_rcu_enabled() && (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && debug_lockdep_rcu_enabled(); } /** * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() * * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. */ #define lockdep_assert_in_rcu_read_lock() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) /** * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() * * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. * Note that local_bh_disable() and friends do not suffice here, instead an * actual rcu_read_lock_bh() is required. */ #define lockdep_assert_in_rcu_read_lock_bh() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) /** * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() * * Splats if lockdep is enabled and there is no rcu_read_lock_sched() * in effect. Note that preempt_disable() and friends do not suffice here, * instead an actual rcu_read_lock_sched() is required. */ #define lockdep_assert_in_rcu_read_lock_sched() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) /** * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader * * Splats if lockdep is enabled and there is no RCU reader of any * type in effect. Note that regions of code protected by things like * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify * as RCU readers. * * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY * kernels that are not also built with PREEMPT_COUNT. But if you have * lockdep enabled, you might as well also enable PREEMPT_COUNT. */ #define lockdep_assert_in_rcu_reader() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ !lock_is_held(&rcu_bh_lock_map) && \ !lock_is_held(&rcu_sched_lock_map) && \ preemptible())) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #define lockdep_assert_in_rcu_read_lock() do { } while (0) #define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) #define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) #define lockdep_assert_in_rcu_reader() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, local) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)); \ }) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as is * the case in the context of the RCU callback that is freeing up the data, * or after a synchronize_rcu() returns. This can be useful when tearing * down multi-linked structures after a grace period has elapsed. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also * wait for regions of code with preemption disabled, including regions of * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which * define synchronize_sched(), only code enclosed within rcu_read_lock() * and rcu_read_unlock() are guaranteed to be waited for. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. * In recent kernels that have consolidated synchronize_sched() and * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity * also extends to the scheduler's runqueue and priority-inheritance * spinlocks, courtesy of the quiescent-state deferral that is carried * out when rcu_read_unlock() is invoked with interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * The object to be freed can be allocated either by kmalloc() or * kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, do { rcu_read_lock(); /* * sparse doesn't call the cleanup function, * so just release immediately and don't track * the context. We don't need to anyway, since * the whole point of the guard is to not need * the explicit unlock. */ __release(RCU); } while (0), rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ |
| 492 492 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * A generic implementation of binary search for the Linux kernel * * Copyright (C) 2008-2009 Ksplice, Inc. * Author: Tim Abbott <tabbott@ksplice.com> */ #include <linux/export.h> #include <linux/bsearch.h> #include <linux/kprobes.h> /* * bsearch - binary search an array of elements * @key: pointer to item being searched for * @base: pointer to first element to search * @num: number of elements * @size: size of each element * @cmp: pointer to comparison function * * This function does a binary search on the given array. The * contents of the array should already be in ascending sorted order * under the provided comparison function. * * Note that the key need not have the same type as the elements in * the array, e.g. key could be a string and the comparison function * could compare the string with the struct's name field. However, if * the key and elements in the array are of the same type, you can use * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { return __inline_bsearch(key, base, num, size, cmp); } EXPORT_SYMBOL(bsearch); NOKPROBE_SYMBOL(bsearch); |
| 87 87 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_STATE_H #define _LINUX_CONTEXT_TRACKING_STATE_H #include <linux/percpu.h> #include <linux/static_key.h> #include <linux/context_tracking_irq.h> /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ #define CT_NESTING_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { CT_STATE_DISABLED = -1, /* returned by ct_state() if unknown */ CT_STATE_KERNEL = 0, CT_STATE_IDLE = 1, CT_STATE_USER = 2, CT_STATE_GUEST = 3, CT_STATE_MAX = 4, }; /* Odd value for watching, else even. */ #define CT_RCU_WATCHING CT_STATE_MAX #define CT_STATE_MASK (CT_STATE_MAX - 1) #define CT_RCU_WATCHING_MASK (~CT_STATE_MASK) struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING_USER /* * When active is false, probes are unset in order * to minimize overhead: TIF flags are cleared * and calls to user_enter/exit are ignored. This * may be further optimized using static keys. */ bool active; int recursion; #endif #ifdef CONFIG_CONTEXT_TRACKING atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE long nesting; /* Track process nesting level. */ long nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); #endif #ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; } #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE static __always_inline int ct_rcu_watching(void) { return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK; } static __always_inline int ct_rcu_watching_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read(&ct->state) & CT_RCU_WATCHING_MASK; } static __always_inline int ct_rcu_watching_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read_acquire(&ct->state) & CT_RCU_WATCHING_MASK; } static __always_inline long ct_nesting(void) { return __this_cpu_read(context_tracking.nesting); } static __always_inline long ct_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->nesting; } static __always_inline long ct_nmi_nesting(void) { return __this_cpu_read(context_tracking.nmi_nesting); } static __always_inline long ct_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->nmi_nesting; } #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ #ifdef CONFIG_CONTEXT_TRACKING_USER extern struct static_key_false context_tracking_key; static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } static __always_inline bool context_tracking_enabled_this_cpu(void) { return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } /** * ct_state() - return the current context tracking state if known * * Returns the current cpu's context tracking state if context tracking * is enabled. If context tracking is disabled, returns * CT_STATE_DISABLED. This should be used primarily for debugging. */ static __always_inline int ct_state(void) { int ret; if (!context_tracking_enabled()) return CT_STATE_DISABLED; preempt_disable(); ret = __ct_state(); preempt_enable(); return ret; } #else static __always_inline bool context_tracking_enabled(void) { return false; } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING_USER */ #endif |
| 26 260 260 292 292 373 373 169 129 129 128 129 122 123 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } /** * folio_ref_count - The reference count on this folio. * @folio: The folio. * * The refcount is usually incremented by calls to folio_get() and * decremented by calls to folio_put(). Some typical users of the * folio refcount: * * - Each reference from a page table * - The page cache * - Filesystem private data * - The LRU list * - Pipes * - Direct IO which references this page in the process address space * * Return: The number of references to this folio. */ static inline int folio_ref_count(const struct folio *folio) { return page_ref_count(&folio->page); } static inline int page_count(const struct page *page) { return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } static inline void folio_set_count(struct folio *folio, int v) { set_page_count(&folio->page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void folio_ref_add(struct folio *folio, int nr) { page_ref_add(&folio->page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline void folio_ref_sub(struct folio *folio, int nr) { page_ref_sub(&folio->page, nr); } static inline int folio_ref_sub_return(struct folio *folio, int nr) { int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void folio_ref_inc(struct folio *folio) { page_ref_inc(&folio->page); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline void folio_ref_dec(struct folio *folio) { page_ref_dec(&folio->page); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int folio_ref_sub_and_test(struct folio *folio, int nr) { return page_ref_sub_and_test(&folio->page, nr); } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int folio_ref_inc_return(struct folio *folio) { return page_ref_inc_return(&folio->page); } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int folio_ref_dec_and_test(struct folio *folio) { return page_ref_dec_and_test(&folio->page); } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int folio_ref_dec_return(struct folio *folio) { return page_ref_dec_return(&folio->page); } static inline bool page_ref_add_unless(struct page *page, int nr, int u) { bool ret = false; rcu_read_lock(); /* avoid writing to the vmemmap area being remapped */ if (!page_is_fake_head(page) && page_ref_count(page) != u) ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) { return page_ref_add_unless(&folio->page, nr, u); } /** * folio_try_get - Attempt to increase the refcount on a folio. * @folio: The folio. * * If you do not already have a reference to a folio, you can attempt to * get one using this function. It may fail if, for example, the folio * has been freed since you found a pointer to it, or it is frozen for * the purposes of splitting or migration. * * Return: True if the reference count was successfully incremented. */ static inline bool folio_try_get(struct folio *folio) { return folio_ref_add_unless(folio, 1, 0); } static inline bool folio_ref_try_add(struct folio *folio, int count) { return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline int folio_ref_freeze(struct folio *folio, int count) { return page_ref_freeze(&folio->page, count); } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } static inline void folio_ref_unfreeze(struct folio *folio, int count) { page_ref_unfreeze(&folio->page, count); } #endif |
| 37 364 67 37 88 63 37 171 55 60 17 25 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGEMAP_H #define _LINUX_PAGEMAP_H /* * Copyright 1995 Linus Torvalds */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/gfp.h> #include <linux/bitops.h> #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> struct folio_batch; unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) invalidate_mapping_pages(inode->i_mapping, 0, -1); } int invalidate_inode_pages2(struct address_space *mapping); int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait); int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { return filemap_fdatawait_range(mapping, 0, LLONG_MAX); } bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc); int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) { return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); } /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error * @err: error to be set in mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { /* Fastpath for common case of no error */ if (unlikely(err)) __filemap_set_wb_err(mapping, err); } /** * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * * Grab the errseq_t value from the mapping, and see if it has changed "since" * the given value was sampled. * * If it has then report the latest error set, otherwise return 0. */ static inline int filemap_check_wb_err(struct address_space *mapping, errseq_t since) { return errseq_check(&mapping->wb_err, since); } /** * filemap_sample_wb_err - sample the current errseq_t to test for later errors * @mapping: mapping to be sampled * * Writeback errors are always reported relative to a particular sample point * in the past. This function provides those sample points. */ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) { return errseq_sample(&mapping->wb_err); } /** * file_sample_sb_err - sample the current errseq_t to test for later errors * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. */ static inline errseq_t file_sample_sb_err(struct file *file) { return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } /* * Flush file data before changing attributes. Caller must hold any locks * required to prevent further writes to this file until we're done setting * flags. */ static inline int inode_drain_writes(struct inode *inode) { inode_dio_wait(inode); return filemap_write_and_wait(inode->i_mapping); } static inline bool mapping_empty(struct address_space *mapping) { return xa_empty(&mapping->i_pages); } /* * mapping_shrinkable - test if page cache state allows inode reclaim * @mapping: the page cache mapping * * This checks the mapping's cache state for the pupose of inode * reclaim and LRU management. * * The caller is expected to hold the i_lock, but is not required to * hold the i_pages lock, which usually protects cache state. That's * because the i_lock and the list_lru lock that protect the inode and * its LRU state don't nest inside the irq-safe i_pages lock. * * Cache deletions are performed under the i_lock, which ensures that * when an inode goes empty, it will reliably get queued on the LRU. * * Cache additions do not acquire the i_lock and may race with this * check, in which case we'll report the inode as shrinkable when it * has cache pages. This is okay: the shrinker also checks the * refcount and the referenced bit, which will be elevated or set in * the process of adding new cache pages to an inode. */ static inline bool mapping_shrinkable(struct address_space *mapping) { void *head; /* * On highmem systems, there could be lowmem pressure from the * inodes before there is highmem pressure from the page * cache. Make inodes shrinkable regardless of cache state. */ if (IS_ENABLED(CONFIG_HIGHMEM)) return true; /* Cache completely empty? Shrink away. */ head = rcu_access_pointer(mapping->i_pages.xa_head); if (!head) return true; /* * The xarray stores single offset-0 entries directly in the * head pointer, which allows non-resident page cache entries * to escape the shadow shrinker's list of xarray nodes. The * inode shrinker needs to pick them up under memory pressure. */ if (!xa_is_node(head) && xa_is_value(head)) return true; return false; } /* * Bits in mapping->flags. */ enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; #define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) #define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) #define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) #define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set * @error: the error to set in the mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */ static inline void mapping_set_error(struct address_space *mapping, int error) { if (likely(!error)) return; /* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error); /* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_clear_unevictable(struct address_space *mapping) { clear_bit(AS_UNEVICTABLE, &mapping->flags); } static inline bool mapping_unevictable(struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_set_exiting(struct address_space *mapping) { set_bit(AS_EXITING, &mapping->flags); } static inline int mapping_exiting(struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } static inline void mapping_set_no_writeback_tags(struct address_space *mapping) { set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline int mapping_use_writeback_tags(struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline bool mapping_release_always(const struct address_space *mapping) { return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_set_release_always(struct address_space *mapping) { set_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_clear_release_always(struct address_space *mapping) { clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline bool mapping_stable_writes(const struct address_space *mapping) { return test_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_stable_writes(struct address_space *mapping) { set_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_clear_stable_writes(struct address_space *mapping) { clear_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_inaccessible(struct address_space *mapping) { /* * It's expected inaccessible mappings are also unevictable. Compaction * migrate scanner (isolate_migratepages_block()) relies on this to * reduce page locking. */ set_bit(AS_UNEVICTABLE, &mapping->flags); set_bit(AS_INACCESSIBLE, &mapping->flags); } static inline bool mapping_inaccessible(struct address_space *mapping) { return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { m->gfp_mask = mask; } /* * There are some parts of the kernel which assume that PMD entries * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, * limit the maximum allocation order to PMD size. I'm not aware of any * assumptions about maximum order if THP are disabled, but 8 seems like * a good order (that's 1MB if you're using 4kB pages) */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER #else #define PREFERRED_MAX_PAGECACHE_ORDER 8 #endif /* * xas_split_alloc() does not support arbitrary orders. This implies no * 512MB THP on ARM64 with 64KB base page size. */ #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) /* * mapping_max_folio_size_supported() - Check the max folio size supported * * The filesystem should call this function at mount time if there is a * requirement on the folio mapping size in the page cache. */ static inline size_t mapping_max_folio_size_supported(void) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); return PAGE_SIZE; } /* * mapping_set_folio_order_range() - Set the orders supported by a file. * @mapping: The address space of the file. * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). * * The filesystem should call this function in its inode constructor to * indicate which base size (min) and maximum size (max) of folio the VFS * can use to cache the contents of the file. This should only be used * if the filesystem needs special handling of folio sizes (ie there is * something the core cannot know). * Do not tune it based on, eg, i_size. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_folio_order_range(struct address_space *mapping, unsigned int min, unsigned int max) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; if (min > MAX_PAGECACHE_ORDER) min = MAX_PAGECACHE_ORDER; if (max > MAX_PAGECACHE_ORDER) max = MAX_PAGECACHE_ORDER; if (max < min) max = min; mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); } static inline void mapping_set_folio_min_order(struct address_space *mapping, unsigned int min) { mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); } /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of * the file. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_large_folios(struct address_space *mapping) { mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); } static inline unsigned int mapping_max_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; } static inline unsigned int mapping_min_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } static inline unsigned long mapping_min_folio_nrpages(struct address_space *mapping) { return 1UL << mapping_min_folio_order(mapping); } /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. * @index: The page index. * * The index of a folio must be naturally aligned. If you are adding a * new folio to the page cache and need to know what index to give it, * call this function. */ static inline pgoff_t mapping_align_index(struct address_space *mapping, pgoff_t index) { return round_down(index, mapping_min_folio_nrpages(mapping)); } /* * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. */ static inline bool mapping_large_folio_support(struct address_space *mapping) { /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, "Anonymous mapping always supports large folio"); return mapping_max_folio_order(mapping) > 0; } /* Return the maximum folio size for this pagecache mapping, in bytes. */ static inline size_t mapping_max_folio_size(const struct address_space *mapping) { return PAGE_SIZE << mapping_max_folio_order(mapping); } static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); #else return 0; #endif } static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); /** * folio_file_mapping - Find the mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Folios in the swap cache return the mapping of the * swap file or swap device where the data is stored. This is different * from the mapping returned by folio_mapping(). The only reason to * use it is if, like NFS, you return 0 from ->activate_swapfile. * * Do not call this for folios which aren't in the page cache or swap cache. */ static inline struct address_space *folio_file_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return swapcache_mapping(folio); return folio->mapping; } /** * folio_flush_mapping - Find the file mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Anonymous folios return NULL, even if they're in * the swap cache. Other kinds of folio also return NULL. * * This is ONLY used by architecture cache flushing code. If you aren't * writing cache flushing code, you want either folio_mapping() or * folio_file_mapping(). */ static inline struct address_space *folio_flush_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return NULL; return folio_mapping(folio); } static inline struct address_space *page_file_mapping(struct page *page) { return folio_file_mapping(page_folio(page)); } /** * folio_inode - Get the host inode for this folio. * @folio: The folio. * * For folios which are in the page cache, return the inode that this folio * belongs to. * * Do not call this for folios which aren't in the page cache. */ static inline struct inode *folio_inode(struct folio *folio) { return folio->mapping->host; } /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. * @data: Data to attach to folio. * * Attaching private data to a folio increments the page's reference count. * The data must be detached before the folio will be freed. */ static inline void folio_attach_private(struct folio *folio, void *data) { folio_get(folio); folio->private = data; folio_set_private(folio); } /** * folio_change_private - Change private data on a folio. * @folio: Folio to change the data on. * @data: Data to set on the folio. * * Change the private data attached to a folio and return the old * data. The page must previously have had data attached and the data * must be detached before the folio will be freed. * * Return: Data that was previously attached to the folio. */ static inline void *folio_change_private(struct folio *folio, void *data) { void *old = folio_get_private(folio); folio->private = data; return old; } /** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. * * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * * Return: Data that was attached to the folio. */ static inline void *folio_detach_private(struct folio *folio) { void *data = folio_get_private(folio); if (!folio_test_private(folio)) return NULL; folio_clear_private(folio); folio->private = NULL; folio_put(folio); return data; } static inline void attach_page_private(struct page *page, void *data) { folio_attach_private(page_folio(page), data); } static inline void *detach_page_private(struct page *page) { return folio_detach_private(page_folio(page)); } #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { return folio_alloc_noprof(gfp, order); } #endif #define filemap_alloc_folio(...) \ alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0)->page; } static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); /** * typedef fgf_t - Flags for getting folios from the page cache. * * Most users of the page cache will not need to use these flags; * there are convenience functions such as filemap_get_folio() and * filemap_lock_folio(). For users which need more control over exactly * what is done with the folios, these flags to __filemap_get_folio() * are available. * * * %FGP_ACCESSED - The folio will be marked accessed. * * %FGP_LOCK - The folio is returned locked. * * %FGP_CREAT - If no folio is present then a new folio is allocated, * added to the page cache and the VM's LRU list. The folio is * returned locked. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * folio is already in cache. If the folio was allocated, unlock it * before returning so the caller can do the same dance. * * %FGP_WRITE - The folio will be written to by the caller. * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ typedef unsigned int __bitwise fgf_t; #define FGP_ACCESSED ((__force fgf_t)0x00000001) #define FGP_LOCK ((__force fgf_t)0x00000002) #define FGP_CREAT ((__force fgf_t)0x00000004) #define FGP_WRITE ((__force fgf_t)0x00000008) #define FGP_NOFS ((__force fgf_t)0x00000010) #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. * * The caller of __filemap_get_folio() can use this to suggest a preferred * size for the folio that is created. If there is already a folio at * the index, it will be returned, no matter what its size. If a folio * is freshly created, it may be of a different size than requested * due to alignment constraints, memory pressure, or the presence of * other folios at nearby indices. */ static inline fgf_t fgf_set_order(size_t size) { unsigned int shift = ilog2(size); if (shift <= PAGE_SHIFT) return 0; return (__force fgf_t)((shift - PAGE_SHIFT) << 26); } void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); /** * filemap_get_folio - Find and get a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, 0, 0); } /** * filemap_lock_folio - Find and lock a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned locked with an increased refcount. * * Context: May sleep. * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK, 0); } /** * filemap_grab_folio - grab a folio from the page cache * @mapping: The address space to search * @index: The page index * * Looks up the page cache entry at @mapping & @index. If no folio is found, * a new folio is created. The folio is locked, marked as accessed, and * returned. * * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_mask(mapping)); } /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */ static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, fgf_t fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */ static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK, 0); } /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */ static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask); } /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Same as grab_cache_page(), but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); } extern pgoff_t __folio_swap_cache_index(struct folio *folio); /** * folio_index - File index of a folio. * @folio: The folio. * * For a folio which is either in the page cache or the swap cache, * return its index within the address_space it belongs to. If you know * the page is definitely in the page cache, you can look at the folio's * index directly. * * Return: The index (offset in units of pages) of a folio in its file. */ static inline pgoff_t folio_index(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return __folio_swap_cache_index(folio); return folio->index; } /** * folio_next_index - Get the index of the next folio. * @folio: The current folio. * * Return: The index of the folio which follows this folio in the file. */ static inline pgoff_t folio_next_index(struct folio *folio) { return folio->index + folio_nr_pages(folio); } /** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. * * Sometimes after looking up a folio in the page cache, we need to * obtain the specific page for an index (eg a page fault). * * Return: The page containing the file data for this index. */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } /** * folio_contains - Does this folio contain this index? * @folio: The folio. * @index: The page index within the file. * * Context: The caller should have the page locked in order to prevent * (eg) shmem from moving the page between the page cache and swap cache * and changing its index in the middle of the operation. * Return: true or false. */ static inline bool folio_contains(struct folio *folio, pgoff_t index) { return index - folio_index(folio) < folio_nr_pages(folio); } /* * Given the page we found in the page cache, return the page corresponding * to this index in the file */ static inline struct page *find_subpage(struct page *head, pgoff_t index) { /* HugeTLBfs wants the head page regardless */ if (PageHuge(head)) return head; return head + (index & (thp_nr_pages(head) - 1)); } unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. */ static inline struct page *grab_cache_page(struct address_space *mapping, pgoff_t index) { return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index, gfp_t flags); struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_page(mapping, index, NULL, file); } static inline struct folio *read_mapping_folio(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_folio(mapping, index, NULL, file); } /** * page_pgoff - Calculate the logical page offset of this page. * @folio: The folio containing this page. * @page: The page which we need the offset of. * * For file pages, this is the offset from the beginning of the file * in units of PAGE_SIZE. For anonymous pages, this is the offset from * the beginning of the anon_vma in units of PAGE_SIZE. This will * return nonsense for KSM pages. * * Context: Caller must have a reference on the folio or otherwise * prevent it from being split or freed. * * Return: The offset in units of PAGE_SIZE. */ static inline pgoff_t page_pgoff(const struct folio *folio, const struct page *page) { return folio->index + folio_page_idx(folio, page); } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { return ((loff_t)page->index) << PAGE_SHIFT; } /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. */ static inline loff_t folio_pos(struct folio *folio) { return page_offset(&folio->page); } /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ static inline pgoff_t folio_pgoff(struct folio *folio) { return folio->index; } static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { pgoff_t pgoff; pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; } struct wait_page_key { struct folio *folio; int bit_nr; int page_match; }; struct wait_page_queue { struct folio *folio; int bit_nr; wait_queue_entry_t wait; }; static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { if (wait_page->folio != key->folio) return false; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return false; return true; } void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); /** * folio_trylock() - Attempt to lock a folio. * @folio: The folio to attempt to lock. * * Sometimes it is undesirable to wait for a folio to be unlocked (eg * when the locks are being taken in the wrong order, or if making * progress through a batch of folios is more important than processing * them in order). Usually folio_lock() is the correct function to call. * * Context: Any context. * Return: Whether the lock was successfully acquired. */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); } /* * Return true if the page was successfully locked */ static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } /** * folio_lock() - Lock this folio. * @folio: The folio to lock. * * The folio lock protects against many things, probably more than it * should. It is primarily held while a folio is being brought uptodate, * either from its backing file or from swap. It is also held while a * folio is being truncated from its address_space, so holding the lock * is sufficient to keep folio->mapping stable. * * The folio lock is also held while write() is modifying the page to * provide POSIX atomicity guarantees (as long as the write does not * cross a page boundary). Other modifications to the data in the folio * do not hold the folio lock and can race with writes, eg DMA and stores * to mapped pages. * * Context: May sleep. If you need to acquire the locks of two or * more folios, they must be in order of ascending index, if they are * in the same address_space. If they are in different address_spaces, * acquire the lock of the folio which belongs to the address_space which * has the lowest address in memory first. */ static inline void folio_lock(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) __folio_lock(folio); } /** * lock_page() - Lock the folio containing this page. * @page: The page to lock. * * See folio_lock() for a description of what the lock protects. * This is a legacy function and new code should probably use folio_lock() * instead. * * Context: May sleep. Pages in the same folio share a lock, so do not * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { struct folio *folio; might_sleep(); folio = page_folio(page); if (!folio_trylock(folio)) __folio_lock(folio); } /** * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. * @folio: The folio to lock. * * Attempts to lock the folio, like folio_lock(), except that the sleep * to acquire the lock is interruptible by a fatal signal. * * Context: May sleep; see folio_lock(). * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_killable(folio); return 0; } /* * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ static inline vm_fault_t folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_or_retry(folio, vmf); return 0; } /* * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */ void folio_wait_bit(struct folio *folio, int bit_nr); int folio_wait_bit_killable(struct folio *folio, int bit_nr); /* * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, * ie with increased folio reference count so that the folio won't * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { if (folio_test_locked(folio)) folio_wait_bit(folio, PG_locked); } static inline int folio_wait_locked_killable(struct folio *folio) { if (!folio_test_locked(folio)) return 0; return folio_wait_bit_killable(folio, PG_locked); } static inline void wait_on_page_locked(struct page *page) { folio_wait_locked(page_folio(page)); } void folio_end_read(struct folio *folio, bool success); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); #else #define filemap_migrate_folio NULL #endif void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); /* * Add an arbitrary waiter to a page's wait queue */ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); /* * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); void filemap_remove_folio(struct folio *folio); void __filemap_remove_folio(struct folio *folio, void *shadow); void replace_page_cache_folio(struct folio *old, struct folio *new); void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch); bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); /* Must be non-static for BPF error injection */ int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte); /** * filemap_range_needs_writeback - check if range potentially needs writeback * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. Used by O_DIRECT * read/write with IOCB_NOWAIT, to see if the caller needs to do * filemap_write_and_wait_range() before proceeding. * * Return: %true if the caller should do filemap_write_and_wait_range() before * doing O_DIRECT to a page in this range, %false otherwise. */ static inline bool filemap_range_needs_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { if (!mapping->nrpages) return false; if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) return false; return filemap_range_has_writeback(mapping, start_byte, end_byte); } /** * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which * implement the ->readahead method should call readahead_page() or * readahead_page_batch() in a loop and attempt to start I/O against * each page in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. * @ra: File readahead state. May be NULL. */ struct readahead_control { struct file *file; struct address_space *mapping; struct file_ra_state *ra; /* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; bool _workingset; unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ struct readahead_control ractl = { \ .file = f, \ .mapping = m, \ .ra = r, \ ._index = i, \ } #define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ static inline void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); page_cache_sync_ra(&ractl, req_count); } /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct folio *folio, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) { struct folio *folio; BUG_ON(ractl->_batch_count > ractl->_nr_pages); ractl->_nr_pages -= ractl->_batch_count; ractl->_index += ractl->_batch_count; if (!ractl->_nr_pages) { ractl->_batch_count = 0; return NULL; } folio = xa_load(&ractl->mapping->i_pages, ractl->_index); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); ractl->_batch_count = folio_nr_pages(folio); return folio; } /** * readahead_page - Get the next page to read. * @ractl: The current readahead request. * * Context: The page is locked and has an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: A pointer to the next page, or %NULL if we are done. */ static inline struct page *readahead_page(struct readahead_control *ractl) { struct folio *folio = __readahead_folio(ractl); return &folio->page; } /** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * * Context: The folio is locked. The caller should unlock the folio once * all I/O to that folio has completed. * Return: A pointer to the next folio, or %NULL if we are done. */ static inline struct folio *readahead_folio(struct readahead_control *ractl) { struct folio *folio = __readahead_folio(ractl); if (folio) folio_put(folio); return folio; } static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz) { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct page *page; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; rac->_batch_count = 0; xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, page)) continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * readahead_page_batch - Get a batch of pages to read. * @rac: The current readahead request. * @array: An array of pointers to struct page. * * Context: The pages are locked and have an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: The number of pages placed in the array. 0 indicates the request * is complete. */ #define readahead_page_batch(rac, array) \ __readahead_batch(rac, array, ARRAY_SIZE(array)) /** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_pos(struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } /** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ static inline size_t readahead_length(struct readahead_control *rac) { return rac->_nr_pages * PAGE_SIZE; } /** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ static inline pgoff_t readahead_index(struct readahead_control *rac) { return rac->_index; } /** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ static inline unsigned int readahead_count(struct readahead_control *rac) { return rac->_nr_pages; } /** * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ static inline size_t readahead_batch_length(struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } static inline unsigned long dir_pages(struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; } /** * folio_mkwrite_check_truncate - check if folio was truncated * @folio: the folio to check * @inode: the inode to check the folio against * * Return: the number of bytes in the folio up to EOF, * or -EFAULT if the folio was truncated. */ static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; size_t offset = offset_in_folio(folio, size); if (!folio->mapping) return -EFAULT; /* folio is wholly inside EOF */ if (folio_next_index(folio) - 1 < index) return folio_size(folio); /* folio is wholly past EOF */ if (folio->index > index || !offset) return -EFAULT; /* folio is partially inside EOF */ return offset; } /** * page_mkwrite_check_truncate - check if page was truncated * @page: the page to check * @inode: the inode to check the page against * * Returns the number of bytes in the page up to EOF, * or -EFAULT if the page was truncated. */ static inline int page_mkwrite_check_truncate(struct page *page, struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; int offset = offset_in_page(size); if (page->mapping != inode->i_mapping) return -EFAULT; /* page is wholly inside EOF */ if (page->index < index) return PAGE_SIZE; /* page is wholly past EOF */ if (page->index > index || !offset) return -EFAULT; /* page is partially inside EOF */ return offset; } /** * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. * @folio: The folio. * * If the block size is larger than the size of this folio, return zero. * * Context: The caller should hold a refcount on the folio to prevent it * from being split. * Return: The number of filesystem blocks covered by this folio. */ static inline unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } #endif /* _LINUX_PAGEMAP_H */ |
| 9 9 302 213 121 122 41 1 1 1 217 124 306 5 258 306 6 306 217 45 124 3 124 14 116 118 12 142 7 138 1 138 216 120 40 6 34 303 303 301 1 305 302 172 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/fault.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 1995-2004 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/extable.h> #include <linux/kfence.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/highmem.h> #include <linux/perf_event.h> #include <linux/pkeys.h> #include <linux/preempt.h> #include <linux/hugetlb.h> #include <asm/acpi.h> #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> #include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kprobes.h> #include <asm/mte.h> #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/tlbflush.h> #include <asm/traps.h> struct fault_info { int (*fn)(unsigned long far, unsigned long esr, struct pt_regs *regs); int sig; int code; const char *name; }; static const struct fault_info fault_info[]; static struct fault_info debug_fault_info[]; static inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } static inline const struct fault_info *esr_to_debug_fault_info(unsigned long esr) { return debug_fault_info + DBG_ESR_EVT(esr); } static void data_abort_decode(unsigned long esr) { unsigned long iss2 = ESR_ELx_ISS2(esr); pr_alert("Data abort info:\n"); if (esr & ESR_ELx_ISV) { pr_alert(" Access size = %u byte(s)\n", 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT)); pr_alert(" SSE = %lu, SRT = %lu\n", (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT, (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT); pr_alert(" SF = %lu, AR = %lu\n", (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { pr_alert(" ISV = 0, ISS = 0x%08lx, ISS2 = 0x%08lx\n", esr & ESR_ELx_ISS_MASK, iss2); } pr_alert(" CM = %lu, WnR = %lu, TnD = %lu, TagAccess = %lu\n", (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT, (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT, (iss2 & ESR_ELx_TnD) >> ESR_ELx_TnD_SHIFT, (iss2 & ESR_ELx_TagAccess) >> ESR_ELx_TagAccess_SHIFT); pr_alert(" GCS = %ld, Overlay = %lu, DirtyBit = %lu, Xs = %llu\n", (iss2 & ESR_ELx_GCS) >> ESR_ELx_GCS_SHIFT, (iss2 & ESR_ELx_Overlay) >> ESR_ELx_Overlay_SHIFT, (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT, (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT); } static void mem_abort_decode(unsigned long esr) { pr_alert("Mem abort info:\n"); pr_alert(" ESR = 0x%016lx\n", esr); pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); pr_alert(" SET = %lu, FnV = %lu\n", (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT, (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT); pr_alert(" EA = %lu, S1PTW = %lu\n", (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT, (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT); pr_alert(" FSC = 0x%02lx: %s\n", (esr & ESR_ELx_FSC), esr_to_fault_info(esr)->name); if (esr_is_data_abort(esr)) data_abort_decode(esr); } static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ if (mm == &init_mm) return __pa_symbol(mm->pgd); return (unsigned long)virt_to_phys(mm->pgd); } /* * Dump out the page tables associated with 'addr' in the currently active mm. */ static void show_pte(unsigned long addr) { struct mm_struct *mm; pgd_t *pgdp; pgd_t pgd; if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { pr_alert("[%016lx] user address but active_mm is swapper\n", addr); return; } } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { pr_alert("[%016lx] address between user and kernel address ranges\n", addr); return; } pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; if (pgd_none(pgd) || pgd_bad(pgd)) break; p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; ptep = pte_offset_map(pmdp, addr); if (!ptep) break; pte = __ptep_get(ptep); pr_cont(", pte=%016llx", pte_val(pte)); pte_unmap(ptep); } while(0); pr_cont("\n"); } /* * This function sets the access flags (dirty, accessed), as well as write * permission, and only to a more permissive setting. * * It needs to cope with hardware update of the accessed/dirty state by other * agents in the system and can safely skip the __sync_icache_dcache() call as, * like __set_ptes(), the PTE is never changed from no-exec to exec here. * * Returns whether or not the PTE actually changed. */ int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { pteval_t old_pteval, pteval; pte_t pte = __ptep_get(ptep); if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; /* * Setting the flags must be done atomically to avoid racing with the * hardware update of the access/dirty state. The PTE_RDONLY bit must * be set to the most permissive (lowest value) of *ptep and entry * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; pteval |= pte_val(entry); pteval ^= PTE_RDONLY; pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); /* Invalidate a stale read-only entry */ if (dirty) flush_tlb_page(vma, address); return 1; } static bool is_el1_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; } static bool is_el1_data_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR; } static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; } static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { unsigned long flags; u64 par, dfsc; if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); asm volatile("at s1e1r, %0" :: "r" (addr)); isb(); par = read_sysreg_par(); local_irq_restore(flags); /* * If we now have a valid translation, treat the translation fault as * spurious. */ if (!(par & SYS_PAR_EL1_F)) return true; /* * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, unsigned long esr, struct pt_regs *regs) { bust_spinlocks(1); pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg, addr); kasan_non_canonical_hook(addr); mem_abort_decode(esr); show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS static void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ bool is_write = !!(esr & ESR_ELx_WNR); kasan_report((void *)addr, 0, is_write, regs->pc); } #else /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ static inline void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { } #endif static void do_tag_recovery(unsigned long addr, unsigned long esr, struct pt_regs *regs) { report_tag_fault(addr, esr, regs); /* * Disable MTE Tag Checking on the local CPU for the current EL. * It will be done lazily on the other CPUs when they will hit a * tag fault. */ sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF, NONE)); isb(); } static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) { unsigned long fsc = esr & ESR_ELx_FSC; if (!is_el1_data_abort(esr)) return false; if (fsc == ESR_ELx_FSC_MTE) return true; return false; } static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { const char *msg; /* * Are we prepared to handle this kernel fault? * We are almost certainly not prepared to handle instruction faults. */ if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs), "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) return; if (is_el1_mte_sync_tag_check_fault(esr)) { do_tag_recovery(addr, esr, regs); return; } if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; else if (is_el1_instruction_abort(esr)) msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; } if (efi_runtime_fixup_exception(regs, msg)) return; die_kernel_fault(msg, addr, esr, regs); } static void set_thread_esr(unsigned long address, unsigned long esr) { current->thread.fault_address = address; /* * If the faulting address is in the kernel, we must sanitize the ESR. * From userspace's point of view, kernel-only mappings don't exist * at all, so we report them as level 0 translation faults. * (This is not quite the way that "no mapping there at all" behaves: * an alignment fault not caused by the memory type would take * precedence over translation fault for a real access to empty * space. Unfortunately we can't easily distinguish "alignment fault * not caused by memory type" from "alignment fault caused by memory * type", so we ignore this wrinkle and just return the translation * fault.) */ if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* * These bits provide only information about the * faulting instruction, which userspace knows already. * We explicitly clear bits which are architecturally * RES0 in case they are given meanings in future. * We always report the ESR as if the fault was taken * to EL1 and so ISV and the bits in ISS[23:14] are * clear. (In fact it always will be a fault to EL1.) */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL | ESR_ELx_CM | ESR_ELx_WNR; esr |= ESR_ELx_FSC_FAULT; break; case ESR_ELx_EC_IABT_LOW: /* * Claim a level 0 translation fault. * All other bits are architecturally RES0 for faults * reported with that DFSC value, so we clear them. */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL; esr |= ESR_ELx_FSC_FAULT; break; default: /* * This should never happen (entry.S only brings us * into this code for insn and data aborts from a lower * exception level). Fail safe by not providing an ESR * context record at all. */ WARN(1, "ESR 0x%lx is not DABT or IABT from EL0\n", esr); esr = 0; break; } } current->thread.fault_code = esr; } static void do_bad_area(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (user_mode(regs)) { const struct fault_info *inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); arm64_force_sig_fault(inf->sig, inf->code, far, inf->name); } else { __do_kernel_fault(addr, esr, regs); } } static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma, unsigned int mm_flags) { unsigned long iss2 = ESR_ELx_ISS2(esr); if (!system_supports_poe()) return false; if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay)) return true; return !arch_vma_access_permitted(vma, mm_flags & FAULT_FLAG_WRITE, mm_flags & FAULT_FLAG_INSTRUCTION, false); } static bool is_gcs_fault(unsigned long esr) { if (!esr_is_data_abort(esr)) return false; return ESR_ELx_ISS2(esr) & ESR_ELx_GCS; } static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } /* * Note: not valid for EL1 DC IVAC, but we never use that such that it * should fault. EL0 cannot issue DC IVAC (undef). */ static bool is_write_abort(unsigned long esr) { return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } static bool is_invalid_gcs_access(struct vm_area_struct *vma, u64 esr) { if (!system_supports_gcs()) return false; if (unlikely(is_gcs_fault(esr))) { /* GCS accesses must be performed on a GCS page */ if (!(vma->vm_flags & VM_SHADOW_STACK)) return true; } else if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) { /* Only GCS operations can write to a GCS page */ return esr_is_data_abort(esr) && is_write_abort(esr); } return false; } static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault; unsigned long vm_flags; unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; int si_code; int pkey = -1; if (kprobe_page_fault(regs, esr)) return 0; /* * If we're in an interrupt or have no user context, we must not take * the fault. */ if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) mm_flags |= FAULT_FLAG_USER; /* * vm_flags tells us what bits we must have in vma->vm_flags * for the fault to be benign, __do_page_fault() would check * vma->vm_flags & vm_flags and returns an error if the * intersection is empty */ if (is_el0_instruction_abort(esr)) { /* It was exec fault */ vm_flags = VM_EXEC; mm_flags |= FAULT_FLAG_INSTRUCTION; } else if (is_gcs_fault(esr)) { /* * The GCS permission on a page implies both read and * write so always handle any GCS fault as a write fault, * we need to trigger CoW even for GCS reads. */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else if (is_write_abort(esr)) { /* It was write fault */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else { /* It was read fault */ vm_flags = VM_READ; /* Write implies read */ vm_flags |= VM_WRITE; /* If EPAN is absent then exec implies read */ if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; } if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { if (is_el1_instruction_abort(esr)) die_kernel_fault("execution of user memory", addr, esr, regs); if (!search_exception_tables(regs->pc)) die_kernel_fault("access to user memory outside uaccess routines", addr, esr, regs); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, addr); if (!vma) goto lock_mmap; if (is_invalid_gcs_access(vma, esr)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } if (fault_from_pkey(esr, vma, mm_flags)) { pkey = vma_pkey(vma); vma_end_read(vma); fault = 0; si_code = SEGV_PKUERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { fault = 0; si_code = SEGV_MAPERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { mmap_read_unlock(mm); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (fault_from_pkey(esr, vma, mm_flags)) { pkey = vma_pkey(vma); mmap_read_unlock(mm); fault = 0; si_code = SEGV_PKUERR; goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return 0; if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: /* Handle the "normal" (no error) case first. */ if (likely(!(fault & VM_FAULT_ERROR))) return 0; si_code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (!user_mode(regs)) goto no_context; if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to * userspace (which will retry the fault, or kill us if we got * oom-killed). */ pagefault_out_of_memory(); return 0; } inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up * this page fault. */ arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name); } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) { unsigned int lsb; lsb = PAGE_SHIFT; if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { /* * The pkey value that we return to userspace can be different * from the pkey that caused the fault. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set POR_EL0 to deny access to pkey=4, touches, page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ /* Something tried to access memory that out of memory map */ if (si_code == SEGV_PKUERR) arm64_force_sig_fault_pkey(far, inf->name, pkey); else arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; no_context: __do_kernel_fault(addr, esr, regs); return 0; } static int __kprobes do_translation_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); if (is_ttbr0_addr(addr)) return do_page_fault(far, esr, regs); do_bad_area(far, esr, regs); return 0; } static int do_alignment_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) && compat_user_mode(regs)) return do_compat_alignment_fixup(far, regs); do_bad_area(far, esr, regs); return 0; } static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs) { return 1; /* "fault" */ } static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; unsigned long siaddr; inf = esr_to_fault_info(esr); if (user_mode(regs) && apei_claim_sea(regs) == 0) { /* * APEI claimed this as a firmware-first notification. * Some processing deferred to task_work before ret_to_user(). */ return 0; } if (esr & ESR_ELx_FnV) { siaddr = 0; } else { /* * The architecture specifies that the tag bits of FAR_EL1 are * UNKNOWN for synchronous external aborts. Mask them out now * so that userspace doesn't see them. */ siaddr = untagged_addr(far); } arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; } static int do_tag_check_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { /* * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN * for tag check faults. Set them to corresponding bits in the untagged * address. */ far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 2 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 3 address size fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 3 (translation table walk)" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 32" }, { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 34" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 35" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 36" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 37" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 47" }, { do_bad, SIGKILL, SI_KERNEL, "TLB conflict abort" }, { do_bad, SIGKILL, SI_KERNEL, "Unsupported atomic hardware update fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 50" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 51" }, { do_bad, SIGKILL, SI_KERNEL, "implementation fault (lockdown abort)" }, { do_bad, SIGBUS, BUS_OBJERR, "implementation fault (unsupported exclusive)" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 54" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 55" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 56" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 57" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 58" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 59" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 60" }, { do_bad, SIGKILL, SI_KERNEL, "section domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "page domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); unsigned long addr = untagged_addr(far); if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) die_kernel_fault(inf->name, addr, esr, regs); /* * At this point we have an unrecognized fault type whose tag bits may * have been defined as UNKNOWN. Therefore we only expose the untagged * address to the signal handler. */ arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr); } NOKPROBE_SYMBOL(do_mem_abort); void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs) { arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); /* * __refdata because early_brk64 is __init, but the reference to it is * clobbered at arch_initcall time. * See traps.c and debug-monitors.c:debug_traps_init(). */ static struct fault_info __refdata debug_fault_info[] = { { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 3" }, { do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" }, { do_bad, SIGKILL, SI_KERNEL, "aarch32 vector catch" }, { early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 7" }, }; void __init hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long, struct pt_regs *), int sig, int code, const char *name) { BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info)); debug_fault_info[nr].fn = fn; debug_fault_info[nr].sig = sig; debug_fault_info[nr].code = code; debug_fault_info[nr].name = name; } /* * In debug exception context, we explicitly disable preemption despite * having interrupts disabled. * This serves two purposes: it makes it much less likely that we would * accidentally schedule in exception context and it will force a warning * if we somehow manage to schedule by accident. */ static void debug_exception_enter(struct pt_regs *regs) { preempt_disable(); /* This code is a bit fragile. Test it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work"); } NOKPROBE_SYMBOL(debug_exception_enter); static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); } NOKPROBE_SYMBOL(debug_exception_exit); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) arm64_apply_bp_hardening(); if (inf->fn(addr_if_watchpoint, esr, regs)) { arm64_notify_die(inf->name, regs, inf->sig, inf->code, pc, esr); } debug_exception_exit(regs); } NOKPROBE_SYMBOL(do_debug_exception); /* * Used during anonymous page fault handling. */ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO; /* * If the page is mapped with PROT_MTE, initialise the tags at the * point of allocation and page zeroing as this is usually faster than * separate DC ZVA and STGM. */ if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; return vma_alloc_folio(flags, 0, vma, vaddr); } void tag_clear_highpage(struct page *page) { /* Newly allocated page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } |
| 52 52 5 26 3 15 17 4 180 71 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically from * the perspective of concurrent readers. It is the caller's responsibility * to synchronize with concurrent updaters, if any. * * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the next element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically from * the perspective of concurrent readers. It is the caller's responsibility * to synchronize with concurrent updaters, if any. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 68 68 68 67 145 68 72 68 68 145 120 145 11 60 145 145 145 144 72 72 68 9 145 145 144 126 145 144 145 145 144 145 214 214 214 71 57 83 83 68 68 68 68 68 68 68 68 68 6 6 70 68 68 68 60 68 68 68 68 67 68 67 68 68 68 59 60 67 68 68 68 60 68 68 68 68 35 35 8 8 6 6 6 6 6 6 35 35 59 57 2 2 2 57 2 2 2 1 1 1 214 214 23 23 1 1 23 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Stand-alone page-table allocator for hyp stage-1 and guest stage-2. * No bombay mix was harmed in the writing of this file. * * Copyright (C) 2020 Google LLC * Author: Will Deacon <will@kernel.org> */ #include <linux/bitfield.h> #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> #define KVM_PTE_TYPE BIT(1) #define KVM_PTE_TYPE_BLOCK 0 #define KVM_PTE_TYPE_PAGE 1 #define KVM_PTE_TYPE_TABLE 1 struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; const u64 start; u64 addr; const u64 end; }; static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx) { return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI); } static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) { return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); } static bool kvm_phys_is_valid(u64 phys) { u64 parange_max = kvm_get_parange_max(); u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max); return phys < BIT(shift); } static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) { u64 granule = kvm_granule_size(ctx->level); if (!kvm_level_supports_block_mapping(ctx->level)) return false; if (granule > (ctx->end - ctx->addr)) return false; if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule)) return false; return IS_ALIGNED(ctx->addr, granule); } static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level) { u64 shift = kvm_granule_shift(level); u64 mask = BIT(PAGE_SHIFT - 3) - 1; return (data->addr >> shift) & mask; } static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) { u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */ u64 mask = BIT(pgt->ia_bits) - 1; return (addr & mask) >> shift; } static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level) { struct kvm_pgtable pgt = { .ia_bits = ia_bits, .start_level = start_level, }; return kvm_pgd_page_idx(&pgt, -1ULL) + 1; } static bool kvm_pte_table(kvm_pte_t pte, s8 level) { if (level == KVM_PGTABLE_LAST_LEVEL) return false; if (!kvm_pte_valid(pte)) return false; return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE; } static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops) { return mm_ops->phys_to_virt(kvm_pte_to_phys(pte)); } static void kvm_clear_pte(kvm_pte_t *ptep) { WRITE_ONCE(*ptep, 0); } static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops) { kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp)); pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE); pte |= KVM_PTE_VALID; return pte; } static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level) { kvm_pte_t pte = kvm_phys_to_pte(pa); u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE : KVM_PTE_TYPE_BLOCK; pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI); pte |= FIELD_PREP(KVM_PTE_TYPE, type); pte |= KVM_PTE_VALID; return pte; } static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id) { return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id); } static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_walker *walker = data->walker; /* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */ WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held()); return walker->cb(ctx, visit); } static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, int r) { /* * Visitor callbacks return EAGAIN when the conditions that led to a * fault are no longer reflected in the page tables due to a race to * update a PTE. In the context of a fault handler this is interpreted * as a signal to retry guest execution. * * Ignore the return code altogether for walkers outside a fault handler * (e.g. write protecting a range of memory) and chug along with the * page table walk. */ if (r == -EAGAIN) return !(walker->flags & KVM_PGTABLE_WALK_HANDLE_FAULT); return !r; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level); static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pteref, s8 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, .start = data->start, .addr = data->addr, .end = data->end, .level = level, .flags = flags, }; int ret = 0; bool reload = false; kvm_pteref_t childp; bool table = kvm_pte_table(ctx.old, level); if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); reload = true; } if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); reload = true; } /* * Reload the page table after invoking the walker callback for leaf * entries or after pre-order traversal, to allow the walker to descend * into a newly installed or replaced table. */ if (reload) { ctx.old = READ_ONCE(*ptep); table = kvm_pte_table(ctx.old, level); } if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (!table) { data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level)); data->addr += kvm_granule_size(level); goto out; } childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); if (!kvm_pgtable_walk_continue(data->walker, ret)) goto out; if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); out: if (kvm_pgtable_walk_continue(data->walker, ret)) return 0; return ret; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level) { u32 idx; int ret = 0; if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL || level > KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) { kvm_pteref_t pteref = &pgtable[idx]; if (data->addr >= data->end) break; ret = __kvm_pgtable_visit(data, mm_ops, pteref, level); if (ret) break; } return ret; } static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data) { u32 idx; int ret = 0; u64 limit = BIT(pgt->ia_bits); if (data->addr > limit || data->end > limit) return -ERANGE; if (!pgt->pgd) return -EINVAL; for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE]; ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level); if (ret) break; } return ret; } int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, }; int r; r = kvm_pgtable_walk_begin(walker); if (r) return r; r = _kvm_pgtable_walk(pgt, &walk_data); kvm_pgtable_walk_end(walker); return r; } struct leaf_walk_data { kvm_pte_t pte; s8 level; }; static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct leaf_walk_data *data = ctx->arg; data->pte = ctx->old; data->level = ctx->level; return 0; } int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, kvm_pte_t *ptep, s8 *level) { struct leaf_walk_data data; struct kvm_pgtable_walker walker = { .cb = leaf_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = &data, }; int ret; ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE), PAGE_SIZE, &walker); if (!ret) { if (ptep) *ptep = data.pte; if (level) *level = data.level; } return ret; } struct hyp_map_data { const u64 phys; kvm_pte_t attr; }; static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) { bool device = prot & KVM_PGTABLE_PROT_DEVICE; u32 mtype = device ? MT_DEVICE_nGnRE : MT_NORMAL; kvm_pte_t attr = FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX, mtype); u32 sh = KVM_PTE_LEAF_ATTR_LO_S1_SH_IS; u32 ap = (prot & KVM_PGTABLE_PROT_W) ? KVM_PTE_LEAF_ATTR_LO_S1_AP_RW : KVM_PTE_LEAF_ATTR_LO_S1_AP_RO; if (!(prot & KVM_PGTABLE_PROT_R)) return -EINVAL; if (prot & KVM_PGTABLE_PROT_X) { if (prot & KVM_PGTABLE_PROT_W) return -EINVAL; if (device) return -EINVAL; if (system_supports_bti_kernel()) attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP; } else { attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN; } attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap); if (!kvm_lpa2_is_enabled()) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF; attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) { enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; u32 ap; if (!kvm_pte_valid(pte)) return prot; if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN)) prot |= KVM_PGTABLE_PROT_X; ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte); if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO) prot |= KVM_PGTABLE_PROT_R; else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW) prot |= KVM_PGTABLE_PROT_RW; return prot; } static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; if (!kvm_block_mapping_supported(ctx, phys)) return false; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; if (!kvm_pte_valid(ctx->old)) ctx->mm_ops->get_page(ctx->ptep); else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) return false; smp_store_release(ctx->ptep, new); return true; } static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp, new; struct hyp_map_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (hyp_map_walker_try_leaf(ctx, data)) return 0; if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL); if (!childp) return -ENOMEM; new = kvm_init_table_pte(childp, mm_ops); mm_ops->get_page(ctx->ptep); smp_store_release(ctx->ptep, new); return 0; } int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot) { int ret; struct hyp_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), }; struct kvm_pgtable_walker walker = { .cb = hyp_map_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; ret = hyp_set_prot_attr(prot, &map_data.attr); if (ret) return ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); isb(); return ret; } static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp = NULL; u64 granule = kvm_granule_size(ctx->level); u64 *unmapped = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EINVAL; if (kvm_pte_table(ctx->old, ctx->level)) { childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), TLBI_TTL_UNKNOWN); } else { if (ctx->end - ctx->addr < granule) return -EINVAL; kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); *unmapped += granule; } dsb(ish); isb(); mm_ops->put_page(ctx->ptep); if (childp) mm_ops->put_page(childp); return 0; } u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { u64 unmapped = 0; struct kvm_pgtable_walker walker = { .cb = hyp_unmap_walker, .arg = &unmapped, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; if (!pgt->mm_ops->page_count) return 0; kvm_pgtable_walk(pgt, addr, size, &walker); return unmapped; } int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops) { s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 - ARM64_HW_PGTABLE_LEVELS(va_bits); if (start_level < KVM_PGTABLE_FIRST_LEVEL || start_level > KVM_PGTABLE_LAST_LEVEL) return -EINVAL; pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL); if (!pgt->pgd) return -ENOMEM; pgt->ia_bits = va_bits; pgt->start_level = start_level; pgt->mm_ops = mm_ops; pgt->mmu = NULL; pgt->force_pte_cb = NULL; return 0; } static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) { struct kvm_pgtable_walker walker = { .cb = hyp_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); pgt->pgd = NULL; } struct stage2_map_data { const u64 phys; kvm_pte_t attr; u8 owner_id; kvm_pte_t *anchor; kvm_pte_t *childp; struct kvm_s2_mmu *mmu; void *memcache; /* Force mappings to page granularity */ bool force_pte; }; u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) { u64 vtcr = VTCR_EL2_FLAGS; s8 lvls; vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT; vtcr |= VTCR_EL2_T0SZ(phys_shift); /* * Use a minimum 2 level page table to prevent splitting * host PMD huge pages at stage2. */ lvls = stage2_pgtable_levels(phys_shift); if (lvls < 2) lvls = 2; /* * When LPA2 is enabled, the HW supports an extra level of translation * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2 * to as an addition to SL0 to enable encoding this extra start level. * However, since we always use concatenated pages for the first level * lookup, we will never need this extra level and therefore do not need * to touch SL2. */ vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls); #ifdef CONFIG_ARM64_HW_AFDBM /* * Enable the Hardware Access Flag management, unconditionally * on all CPUs. In systems that have asymmetric support for the feature * this allows KVM to leverage hardware support on the subset of cores * that implement the feature. * * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by * hardware) on implementations that do not advertise support for the * feature. As such, setting HA unconditionally is safe, unless you * happen to be running on a design that has unadvertised support for * HAFDBS. Here be dragons. */ if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) vtcr |= VTCR_EL2_HA; #endif /* CONFIG_ARM64_HW_AFDBM */ if (kvm_lpa2_is_enabled()) vtcr |= VTCR_EL2_DS; /* Set the vmid bits */ vtcr |= (get_vmid_bits(mmfr1) == 16) ? VTCR_EL2_VS_16BIT : VTCR_EL2_VS_8BIT; return vtcr; } static bool stage2_has_fwb(struct kvm_pgtable *pgt) { if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) return false; return !(pgt->flags & KVM_PGTABLE_S2_NOFWB); } void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, size_t size) { unsigned long pages, inval_pages; if (!system_supports_tlb_range()) { kvm_call_hyp(__kvm_tlb_flush_vmid, mmu); return; } pages = size >> PAGE_SHIFT; while (pages > 0) { inval_pages = min(pages, MAX_TLBI_RANGE_PAGES); kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages); addr += inval_pages << PAGE_SHIFT; pages -= inval_pages; } } #define KVM_S2_MEMATTR(pgt, attr) PAGE_S2_MEMATTR(attr, stage2_has_fwb(pgt)) static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot, kvm_pte_t *ptep) { kvm_pte_t attr; u32 sh = KVM_PTE_LEAF_ATTR_LO_S2_SH_IS; switch (prot & (KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC)) { case KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC: return -EINVAL; case KVM_PGTABLE_PROT_DEVICE: if (prot & KVM_PGTABLE_PROT_X) return -EINVAL; attr = KVM_S2_MEMATTR(pgt, DEVICE_nGnRE); break; case KVM_PGTABLE_PROT_NORMAL_NC: if (prot & KVM_PGTABLE_PROT_X) return -EINVAL; attr = KVM_S2_MEMATTR(pgt, NORMAL_NC); break; default: attr = KVM_S2_MEMATTR(pgt, NORMAL); } if (!(prot & KVM_PGTABLE_PROT_X)) attr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; if (prot & KVM_PGTABLE_PROT_R) attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; if (prot & KVM_PGTABLE_PROT_W) attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; if (!kvm_lpa2_is_enabled()) attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh); attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF; attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; *ptep = attr; return 0; } enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte) { enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; if (!kvm_pte_valid(pte)) return prot; if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R) prot |= KVM_PGTABLE_PROT_R; if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W) prot |= KVM_PGTABLE_PROT_W; if (!(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN)) prot |= KVM_PGTABLE_PROT_X; return prot; } static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new) { if (!kvm_pte_valid(old) || !kvm_pte_valid(new)) return true; return ((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS)); } static bool stage2_pte_is_counted(kvm_pte_t pte) { /* * The refcount tracks valid entries as well as invalid entries if they * encode ownership of a page to another entity than the page-table * owner, whose id is 0. */ return !!pte; } static bool stage2_pte_is_locked(kvm_pte_t pte) { return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED); } static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) { if (!kvm_pgtable_walk_shared(ctx)) { WRITE_ONCE(*ctx->ptep, new); return true; } return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old; } /** * stage2_try_break_pte() - Invalidates a pte according to the * 'break-before-make' requirements of the * architecture. * * @ctx: context of the visited pte. * @mmu: stage-2 mmu * * Returns: true if the pte was successfully broken. * * If the removed pte was valid, performs the necessary serialization and TLB * invalidation for the old value. For counted ptes, drops the reference count * on the containing table page. */ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (stage2_pte_is_locked(ctx->old)) { /* * Should never occur if this walker has exclusive access to the * page tables. */ WARN_ON(!kvm_pgtable_walk_shared(ctx)); return false; } if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED)) return false; if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) { /* * Perform the appropriate TLB invalidation based on the * evicted pte value (if any). */ if (kvm_pte_table(ctx->old, ctx->level)) { u64 size = kvm_granule_size(ctx->level); u64 addr = ALIGN_DOWN(ctx->addr, size); kvm_tlb_flush_vmid_range(mmu, addr, size); } else if (kvm_pte_valid(ctx->old)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } } if (stage2_pte_is_counted(ctx->old)) mm_ops->put_page(ctx->ptep); return true; } static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; WARN_ON(!stage2_pte_is_locked(*ctx->ptep)); if (stage2_pte_is_counted(new)) mm_ops->get_page(ctx->ptep); smp_store_release(ctx->ptep, new); } static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt) { /* * If FEAT_TLBIRANGE is implemented, defer the individual * TLB invalidations until the entire walk is finished, and * then use the range-based TLBI instructions to do the * invalidations. Condition deferred TLB invalidation on the * system supporting FWB as the optimization is entirely * pointless when the unmap walker needs to perform CMOs. */ return system_supports_tlb_range() && stage2_has_fwb(pgt); } static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops) { struct kvm_pgtable *pgt = ctx->arg; /* * Clear the existing PTE, and perform break-before-make if it was * valid. Depending on the system support, defer the TLB maintenance * for the same until the entire unmap walk is completed. */ if (kvm_pte_valid(ctx->old)) { kvm_clear_pte(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, TLBI_TTL_UNKNOWN); } else if (!stage2_unmap_defer_tlb_flush(pgt)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } } mm_ops->put_page(ctx->ptep); } static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte) { u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR; return kvm_pte_valid(pte) && memattr == KVM_S2_MEMATTR(pgt, NORMAL); } static bool stage2_pte_executable(kvm_pte_t pte) { return kvm_pte_valid(pte) && !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, const struct stage2_map_data *data) { u64 phys = data->phys; /* * Stage-2 walks to update ownership data are communicated to the map * walker using an invalid PA. Avoid offsetting an already invalid PA, * which could overflow and make the address valid again. */ if (!kvm_phys_is_valid(phys)) return phys; /* * Otherwise, work out the correct PA based on how far the walk has * gotten. */ return phys + (ctx->addr - ctx->start); } static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { u64 phys = stage2_map_walker_phys_addr(ctx, data); if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL) return false; return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; u64 phys = stage2_map_walker_phys_addr(ctx, data); u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_leaf_mapping_allowed(ctx, data)) return -E2BIG; if (kvm_phys_is_valid(phys)) new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); else new = kvm_init_invalid_leaf_owner(data->owner_id); /* * Skip updating the PTE if we are trying to recreate the exact * same mapping or only change the access permissions. Instead, * the vCPU will exit one more time from guest if still needed * and then go through the path of relaxing permissions. */ if (!stage2_pte_needs_update(ctx->old, new)) return -EAGAIN; /* If we're only changing software bits, then store them and go! */ if (!kvm_pgtable_walk_shared(ctx) && !((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) { bool old_is_counted = stage2_pte_is_counted(ctx->old); if (old_is_counted != stage2_pte_is_counted(new)) { if (old_is_counted) mm_ops->put_page(ctx->ptep); else mm_ops->get_page(ctx->ptep); } WARN_ON_ONCE(!stage2_try_set_pte(ctx, new)); return 0; } if (!stage2_try_break_pte(ctx, data->mmu)) return -EAGAIN; /* Perform CMOs before installation of the guest stage-2 PTE */ if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new)) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops), granule); if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou && stage2_pte_executable(new)) mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule); stage2_make_pte(ctx, new); return 0; } static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops); int ret; if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; ret = stage2_map_walker_try_leaf(ctx, data); if (ret) return ret; mm_ops->free_unlinked_table(childp, ctx->level); return 0; } static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp, new; int ret; ret = stage2_map_walker_try_leaf(ctx, data); if (ret != -E2BIG) return ret; if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) return -EINVAL; if (!data->memcache) return -ENOMEM; childp = mm_ops->zalloc_page(data->memcache); if (!childp) return -ENOMEM; if (!stage2_try_break_pte(ctx, data->mmu)) { mm_ops->put_page(childp); return -EAGAIN; } /* * If we've run into an existing block mapping then replace it with * a table. Accesses beyond 'end' that fall within the new table * will be mapped lazily. */ new = kvm_init_table_pte(childp, mm_ops); stage2_make_pte(ctx, new); return 0; } /* * The TABLE_PRE callback runs for table entries on the way down, looking * for table entries which we could conceivably replace with a block entry * for this mapping. If it finds one it replaces the entry and calls * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table. * * Otherwise, the LEAF callback performs the mapping at the existing leaves * instead. */ static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct stage2_map_data *data = ctx->arg; switch (visit) { case KVM_PGTABLE_WALK_TABLE_PRE: return stage2_map_walk_table_pre(ctx, data); case KVM_PGTABLE_WALK_LEAF: return stage2_map_walk_leaf(ctx, data); default: return -EINVAL; } } int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags) { int ret; struct stage2_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), .mmu = pgt->mmu, .memcache = mc, .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot), }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = flags | KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; if (WARN_ON((pgt->flags & KVM_PGTABLE_S2_IDMAP) && (addr != phys))) return -EINVAL; ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); if (ret) return ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); return ret; } int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc, u8 owner_id) { int ret; struct stage2_map_data map_data = { .phys = KVM_PHYS_INVALID, .mmu = pgt->mmu, .memcache = mc, .owner_id = owner_id, .force_pte = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; if (owner_id > KVM_MAX_OWNER_ID) return -EINVAL; ret = kvm_pgtable_walk(pgt, addr, size, &walker); return ret; } static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable *pgt = ctx->arg; struct kvm_s2_mmu *mmu = pgt->mmu; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = NULL; bool need_flush = false; if (!kvm_pte_valid(ctx->old)) { if (stage2_pte_is_counted(ctx->old)) { kvm_clear_pte(ctx->ptep); mm_ops->put_page(ctx->ptep); } return 0; } if (kvm_pte_table(ctx->old, ctx->level)) { childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; } else if (stage2_pte_cacheable(pgt, ctx->old)) { need_flush = !stage2_has_fwb(pgt); } /* * This is similar to the map() path in that we unmap the entire * block entry and rely on the remaining portions being faulted * back lazily. */ stage2_unmap_put_pte(ctx, mmu, mm_ops); if (need_flush && mm_ops->dcache_clean_inval_poc) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); if (childp) mm_ops->put_page(childp); return 0; } int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { int ret; struct kvm_pgtable_walker walker = { .cb = stage2_unmap_walker, .arg = pgt, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); if (stage2_unmap_defer_tlb_flush(pgt)) /* Perform the deferred TLB invalidations */ kvm_tlb_flush_vmid_range(pgt->mmu, addr, size); return ret; } struct stage2_attr_data { kvm_pte_t attr_set; kvm_pte_t attr_clr; kvm_pte_t pte; s8 level; }; static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t pte = ctx->old; struct stage2_attr_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EAGAIN; data->level = ctx->level; data->pte = pte; pte &= ~data->attr_clr; pte |= data->attr_set; /* * We may race with the CPU trying to set the access flag here, * but worst-case the access flag update gets lost and will be * set on the next access instead. */ if (data->pte != pte) { /* * Invalidate instruction cache before updating the guest * stage-2 PTE if we are going to add executable permission. */ if (mm_ops->icache_inval_pou && stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), kvm_granule_size(ctx->level)); if (!stage2_try_set_pte(ctx, pte)) return -EAGAIN; } return 0; } static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, u64 size, kvm_pte_t attr_set, kvm_pte_t attr_clr, kvm_pte_t *orig_pte, s8 *level, enum kvm_pgtable_walk_flags flags) { int ret; kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI; struct stage2_attr_data data = { .attr_set = attr_set & attr_mask, .attr_clr = attr_clr & attr_mask, }; struct kvm_pgtable_walker walker = { .cb = stage2_attr_walker, .arg = &data, .flags = flags | KVM_PGTABLE_WALK_LEAF, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); if (ret) return ret; if (orig_pte) *orig_pte = data.pte; if (level) *level = data.level; return 0; } int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) { return stage2_update_leaf_attrs(pgt, addr, size, 0, KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W, NULL, NULL, 0); } void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr) { int ret; ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, NULL, NULL, KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); if (!ret) dsb(ishst); } struct stage2_age_data { bool mkold; bool young; }; static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF; struct stage2_age_data *data = ctx->arg; if (!kvm_pte_valid(ctx->old) || new == ctx->old) return 0; data->young = true; /* * stage2_age_walker() is always called while holding the MMU lock for * write, so this will always succeed. Nonetheless, this deliberately * follows the race detection pattern of the other stage-2 walkers in * case the locking mechanics of the MMU notifiers is ever changed. */ if (data->mkold && !stage2_try_set_pte(ctx, new)) return -EAGAIN; /* * "But where's the TLBI?!", you scream. * "Over in the core code", I sigh. * * See the '->clear_flush_young()' callback on the KVM mmu notifier. */ return 0; } bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold) { struct stage2_age_data data = { .mkold = mkold, }; struct kvm_pgtable_walker walker = { .cb = stage2_age_walker, .arg = &data, .flags = KVM_PGTABLE_WALK_LEAF, }; WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); return data.young; } int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot) { int ret; s8 level; kvm_pte_t set = 0, clr = 0; if (prot & KVM_PTE_LEAF_ATTR_HI_SW) return -EINVAL; if (prot & KVM_PGTABLE_PROT_R) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; if (prot & KVM_PGTABLE_PROT_W) set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; if (prot & KVM_PGTABLE_PROT_X) clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN; ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); if (!ret || ret == -EAGAIN) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); return ret; } static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable *pgt = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; if (!stage2_pte_cacheable(pgt, ctx->old)) return 0; if (mm_ops->dcache_clean_inval_poc) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); return 0; } int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) { struct kvm_pgtable_walker walker = { .cb = stage2_flush_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = pgt, }; if (stage2_has_fwb(pgt)) return 0; return kvm_pgtable_walk(pgt, addr, size, &walker); } kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, enum kvm_pgtable_prot prot, void *mc, bool force_pte) { struct stage2_map_data map_data = { .phys = phys, .mmu = pgt->mmu, .memcache = mc, .force_pte = force_pte, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_SKIP_BBM_TLBI | KVM_PGTABLE_WALK_SKIP_CMO, .arg = &map_data, }; /* * The input address (.addr) is irrelevant for walking an * unlinked table. Construct an ambiguous IA range to map * kvm_granule_size(level) worth of memory. */ struct kvm_pgtable_walk_data data = { .walker = &walker, .addr = 0, .end = kvm_granule_size(level), }; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; kvm_pte_t *pgtable; int ret; if (!IS_ALIGNED(phys, kvm_granule_size(level))) return ERR_PTR(-EINVAL); ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); if (ret) return ERR_PTR(ret); pgtable = mm_ops->zalloc_page(mc); if (!pgtable) return ERR_PTR(-ENOMEM); ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable, level + 1); if (ret) { kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level); return ERR_PTR(ret); } return pgtable; } /* * Get the number of page-tables needed to replace a block with a * fully populated tree up to the PTE entries. Note that @level is * interpreted as in "level @level entry". */ static int stage2_block_get_nr_page_tables(s8 level) { switch (level) { case 1: return PTRS_PER_PTE + 1; case 2: return 1; case 3: return 0; default: WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL || level > KVM_PGTABLE_LAST_LEVEL); return -EINVAL; }; } static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; struct kvm_mmu_memory_cache *mc = ctx->arg; struct kvm_s2_mmu *mmu; kvm_pte_t pte = ctx->old, new, *childp; enum kvm_pgtable_prot prot; s8 level = ctx->level; bool force_pte; int nr_pages; u64 phys; /* No huge-pages exist at the last level */ if (level == KVM_PGTABLE_LAST_LEVEL) return 0; /* We only split valid block mappings */ if (!kvm_pte_valid(pte)) return 0; nr_pages = stage2_block_get_nr_page_tables(level); if (nr_pages < 0) return nr_pages; if (mc->nobjs >= nr_pages) { /* Build a tree mapped down to the PTE granularity. */ force_pte = true; } else { /* * Don't force PTEs, so create_unlinked() below does * not populate the tree up to the PTE level. The * consequence is that the call will require a single * page of level 2 entries at level 1, or a single * page of PTEs at level 2. If we are at level 1, the * PTEs will be created recursively. */ force_pte = false; nr_pages = 1; } if (mc->nobjs < nr_pages) return -ENOMEM; mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache); phys = kvm_pte_to_phys(pte); prot = kvm_pgtable_stage2_pte_prot(pte); childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys, level, prot, mc, force_pte); if (IS_ERR(childp)) return PTR_ERR(childp); if (!stage2_try_break_pte(ctx, mmu)) { kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level); return -EAGAIN; } /* * Note, the contents of the page table are guaranteed to be made * visible before the new PTE is assigned because stage2_make_pte() * writes the PTE using smp_store_release(). */ new = kvm_init_table_pte(childp, mm_ops); stage2_make_pte(ctx, new); return 0; } int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc) { struct kvm_pgtable_walker walker = { .cb = stage2_split_walker, .flags = KVM_PGTABLE_WALK_LEAF, .arg = mc, }; int ret; ret = kvm_pgtable_walk(pgt, addr, size, &walker); dsb(ishst); return ret; } int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops, enum kvm_pgtable_stage2_flags flags, kvm_pgtable_force_pte_cb_t force_pte_cb) { size_t pgd_sz; u64 vtcr = mmu->vtcr; u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz); if (!pgt->pgd) return -ENOMEM; pgt->ia_bits = ia_bits; pgt->start_level = start_level; pgt->mm_ops = mm_ops; pgt->mmu = mmu; pgt->flags = flags; pgt->force_pte_cb = force_pte_cb; /* Ensure zeroed PGD pages are visible to the hardware walker */ dsb(ishst); return 0; } size_t kvm_pgtable_stage2_pgd_size(u64 vtcr) { u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; } static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_pte_is_counted(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); if (kvm_pte_table(ctx->old, ctx->level)) mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { size_t pgd_sz; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) { kvm_pteref_t ptep = (kvm_pteref_t)pgtable; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; struct kvm_pgtable_walk_data data = { .walker = &walker, /* * At this point the IPA really doesn't matter, as the page * table being traversed has already been removed from the stage * 2. Set an appropriate range to cover the entire page table. */ .addr = 0, .end = kvm_granule_size(level), }; WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1)); WARN_ON(mm_ops->page_count(pgtable) != 1); mm_ops->put_page(pgtable); } |
| 155 176 175 80 155 155 155 68 90 59 79 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/flush.c * * Copyright (C) 1995-2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/libnvdimm.h> #include <linux/pagemap.h> #include <asm/cacheflush.h> #include <asm/cache.h> #include <asm/tlbflush.h> void sync_icache_aliases(unsigned long start, unsigned long end) { if (icache_is_aliasing()) { dcache_clean_pou(start, end); icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ caches_clean_inval_pou(start, end); } } static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_flags & VM_EXEC) sync_icache_aliases(start, end); } /* * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { memcpy(dst, src, len); flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) { struct folio *folio = page_folio(pte_page(pte)); if (!test_bit(PG_dcache_clean, &folio->flags)) { sync_icache_aliases((unsigned long)folio_address(folio), (unsigned long)folio_address(folio) + folio_size(folio)); set_bit(PG_dcache_clean, &folio->flags); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ void flush_dcache_folio(struct folio *folio) { if (test_bit(PG_dcache_clean, &folio->flags)) clear_bit(PG_dcache_clean, &folio->flags); } EXPORT_SYMBOL(flush_dcache_folio); void flush_dcache_page(struct page *page) { flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif |
| 149 151 149 297 30 154 422 419 59 421 423 422 421 422 422 421 60 60 59 7 59 25 412 413 413 413 36 36 37 1 10 36 454 1026 1026 1 1034 1032 1043 1035 51 441 1004 967 1010 4 4 50 8 57 57 55 8 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include "internal.h" /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); WARN_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; unsigned n; spin_lock(&files->file_lock); n = last_fd(files_fdtable(files)); max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || file->f_op->iterate_shared); } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (file && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt, flags & O_CLOEXEC); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { put_unused_fd(new_fd); return error; } } fd_install(new_fd, get_file(file)); __receive_sock(file); return new_fd; } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for queueing packets and communicating with * userspace via nfnetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2007 by Patrick McHardy <kaber@trash.net> * * Based on the old ipv4-only ip_queue.c: * (C) 2000-2002 James Morris <jmorris@intercode.com.au> * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/proc_fs.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_queue.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/list.h> #include <linux/cgroup-defs.h> #include <net/gso.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/netfilter/nf_queue.h> #include <net/netns/generic.h> #include <linux/atomic.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #define NFQNL_QMAX_DEFAULT 1024 /* We're using struct nlattr which has 16bit nla_len. Note that nla_len * includes the header length. Thus, the maximum packet length that we * support is 65531 bytes. We send truncated packets if the specified length * is larger than that. Userspace can check for presence of NFQA_CAP_LEN * attribute to detect truncation. */ #define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN) struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; u32 peer_portid; unsigned int queue_maxlen; unsigned int copy_range; unsigned int queue_dropped; unsigned int queue_user_dropped; u_int16_t queue_num; /* number of this queue */ u_int8_t copy_mode; u_int32_t flags; /* Set using NFQA_CFG_FLAGS */ /* * Following fields are dirtied for each queued packet, * keep them in same cache line if possible. */ spinlock_t lock ____cacheline_aligned_in_smp; unsigned int queue_total; unsigned int id_sequence; /* 'sequence' of pkt ids */ struct list_head queue_list; /* packets in queue */ }; typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long); static unsigned int nfnl_queue_net_id __read_mostly; #define INSTANCE_BUCKETS 16 struct nfnl_queue_net { spinlock_t instances_lock; struct hlist_head instance_table[INSTANCE_BUCKETS]; }; static struct nfnl_queue_net *nfnl_queue_pernet(struct net *net) { return net_generic(net, nfnl_queue_net_id); } static inline u_int8_t instance_hashfn(u_int16_t queue_num) { return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS; } static struct nfqnl_instance * instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num) { struct hlist_head *head; struct nfqnl_instance *inst; head = &q->instance_table[instance_hashfn(queue_num)]; hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->queue_num == queue_num) return inst; } return NULL; } static struct nfqnl_instance * instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid) { struct nfqnl_instance *inst; unsigned int h; int err; spin_lock(&q->instances_lock); if (instance_lookup(q, queue_num)) { err = -EEXIST; goto out_unlock; } inst = kzalloc(sizeof(*inst), GFP_ATOMIC); if (!inst) { err = -ENOMEM; goto out_unlock; } inst->queue_num = queue_num; inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; inst->copy_range = NFQNL_MAX_COPY_RANGE; inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); if (!try_module_get(THIS_MODULE)) { err = -EAGAIN; goto out_free; } h = instance_hashfn(queue_num); hlist_add_head_rcu(&inst->hlist, &q->instance_table[h]); spin_unlock(&q->instances_lock); return inst; out_free: kfree(inst); out_unlock: spin_unlock(&q->instances_lock); return ERR_PTR(err); } static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data); static void instance_destroy_rcu(struct rcu_head *head) { struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); rcu_read_lock(); nfqnl_flush(inst, NULL, 0); rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } static void __instance_destroy(struct nfqnl_instance *inst) { hlist_del_rcu(&inst->hlist); call_rcu(&inst->rcu, instance_destroy_rcu); } static void instance_destroy(struct nfnl_queue_net *q, struct nfqnl_instance *inst) { spin_lock(&q->instances_lock); __instance_destroy(inst); spin_unlock(&q->instances_lock); } static inline void __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { list_add_tail(&entry->list, &queue->queue_list); queue->queue_total++; } static void __dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { list_del(&entry->list); queue->queue_total--; } static struct nf_queue_entry * find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) { struct nf_queue_entry *entry = NULL, *i; spin_lock_bh(&queue->lock); list_for_each_entry(i, &queue->queue_list, list) { if (i->id == id) { entry = i; break; } } if (entry) __dequeue_entry(queue, entry); spin_unlock_bh(&queue->lock); return entry; } static unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *hooks, unsigned int *index) { const struct nf_hook_entry *hook; unsigned int verdict, i = *index; while (i < hooks->num_hook_entries) { hook = &hooks->hooks[i]; repeat: verdict = nf_hook_entry_hookfn(hook, skb, state); if (verdict != NF_ACCEPT) { *index = i; if (verdict != NF_REPEAT) return verdict; goto repeat; } i++; } *index = i; return NF_ACCEPT; } static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) { switch (pf) { #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: return rcu_dereference(net->nf.hooks_bridge[hooknum]); #endif case NFPROTO_IPV4: return rcu_dereference(net->nf.hooks_ipv4[hooknum]); case NFPROTO_IPV6: return rcu_dereference(net->nf.hooks_ipv6[hooknum]); default: WARN_ON_ONCE(1); return NULL; } return NULL; } static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) { #ifdef CONFIG_INET const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); if (!(iph->tos == rt_info->tos && skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) return ip_route_me_harder(entry->state.net, entry->state.sk, skb, RTN_UNSPEC); } #endif return 0; } static int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) { const struct nf_ipv6_ops *v6ops; int ret = 0; switch (entry->state.pf) { case AF_INET: ret = nf_ip_reroute(skb, entry); break; case AF_INET6: v6ops = rcu_dereference(nf_ipv6_ops); if (v6ops) ret = v6ops->reroute(skb, entry); break; } return ret; } /* caller must hold rcu read-side lock */ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_hook_entry *hook_entry; const struct nf_hook_entries *hooks; struct sk_buff *skb = entry->skb; const struct net *net; unsigned int i; int err; u8 pf; net = entry->state.net; pf = entry->state.pf; hooks = nf_hook_entries_head(net, pf, entry->state.hook); i = entry->hook_index; if (!hooks || i >= hooks->num_hook_entries) { kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); nf_queue_entry_free(entry); return; } hook_entry = &hooks->hooks[i]; /* Continue traversal iff userspace said ok... */ if (verdict == NF_REPEAT) verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); if (verdict == NF_ACCEPT) { if (nf_reroute(skb, entry) < 0) verdict = NF_DROP; } if (verdict == NF_ACCEPT) { next_hook: ++i; verdict = nf_iterate(skb, &entry->state, hooks, &i); } switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_STOP: local_bh_disable(); entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: err = nf_queue(skb, &entry->state, i, verdict); if (err == 1) goto next_hook; break; case NF_STOLEN: break; default: kfree_skb(skb); } nf_queue_entry_free(entry); } static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { unsigned int ct_verdict = verdict; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_verdict = ct_hook->update(entry->state.net, entry->skb); rcu_read_unlock(); switch (ct_verdict & NF_VERDICT_MASK) { case NF_ACCEPT: /* follow userspace verdict, could be REPEAT */ break; case NF_STOLEN: nf_queue_entry_free(entry); return; default: verdict = ct_verdict & NF_VERDICT_MASK; break; } } nf_reinject(entry, verdict); } static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) { struct nf_queue_entry *entry, *next; spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, next, &queue->queue_list, list) { if (!cmpfn || cmpfn(entry, data)) { list_del(&entry->list); queue->queue_total--; nfqnl_reinject(entry, NF_DROP); } } spin_unlock_bh(&queue->lock); } static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, bool csum_verify) { __u32 flags = 0; if (packet->ip_summed == CHECKSUM_PARTIAL) flags = NFQA_SKB_CSUMNOTREADY; else if (csum_verify) flags = NFQA_SKB_CSUM_NOTVERIFIED; if (skb_is_gso(packet)) flags |= NFQA_SKB_GSO; return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0; } static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk) { const struct cred *cred; if (!sk_fullsock(sk)) return 0; read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { cred = sk->sk_socket->file->f_cred; if (nla_put_be32(skb, NFQA_UID, htonl(from_kuid_munged(&init_user_ns, cred->fsuid)))) goto nla_put_failure; if (nla_put_be32(skb, NFQA_GID, htonl(from_kgid_munged(&init_user_ns, cred->fsgid)))) goto nla_put_failure; } read_unlock_bh(&sk->sk_callback_lock); return 0; nla_put_failure: read_unlock_bh(&sk->sk_callback_lock); return -1; } static int nfqnl_put_sk_classid(struct sk_buff *skb, struct sock *sk) { #if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID) if (sk && sk_fullsock(sk)) { u32 classid = sock_cgroup_classid(&sk->sk_cgrp_data); if (classid && nla_put_be32(skb, NFQA_CGROUP_CLASSID, htonl(classid))) return -1; } #endif return 0; } static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, char **secdata) { u32 seclen = 0; #if IS_ENABLED(CONFIG_NETWORK_SECMARK) if (!skb || !sk_fullsock(skb->sk)) return 0; read_lock_bh(&skb->sk->sk_callback_lock); if (skb->secmark) security_secid_to_secctx(skb->secmark, secdata, &seclen); read_unlock_bh(&skb->sk->sk_callback_lock); #endif return seclen; } static u32 nfqnl_get_bridge_size(struct nf_queue_entry *entry) { struct sk_buff *entskb = entry->skb; u32 nlalen = 0; if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb)) return 0; if (skb_vlan_tag_present(entskb)) nlalen += nla_total_size(nla_total_size(sizeof(__be16)) + nla_total_size(sizeof(__be16))); if (entskb->network_header > entskb->mac_header) nlalen += nla_total_size((entskb->network_header - entskb->mac_header)); return nlalen; } static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) { struct sk_buff *entskb = entry->skb; if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb)) return 0; if (skb_vlan_tag_present(entskb)) { struct nlattr *nest; nest = nla_nest_start(skb, NFQA_VLAN); if (!nest) goto nla_put_failure; if (nla_put_be16(skb, NFQA_VLAN_TCI, htons(entskb->vlan_tci)) || nla_put_be16(skb, NFQA_VLAN_PROTO, entskb->vlan_proto)) goto nla_put_failure; nla_nest_end(skb, nest); } if (entskb->mac_header < entskb->network_header) { int len = (int)(entskb->network_header - entskb->mac_header); if (nla_put(skb, NFQA_L2HDR, len, skb_mac_header(entskb))) goto nla_put_failure; } return 0; nla_put_failure: return -1; } static int nf_queue_checksum_help(struct sk_buff *entskb) { if (skb_csum_is_sctp(entskb)) return skb_crc32c_csum_help(entskb); return skb_checksum_help(entskb); } static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, __be32 **packet_id_ptr) { size_t size; size_t data_len = 0, cap_len = 0; unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; struct nlmsghdr *nlh; struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; struct nf_conn *ct = NULL; enum ip_conntrack_info ctinfo = 0; const struct nfnl_ct_hook *nfnl_ct; bool csum_verify; char *secdata = NULL; u32 seclen = 0; ktime_t tstamp; size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(u_int32_t)) /* priority */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) + nla_total_size(sizeof(u_int32_t)) /* skbinfo */ #if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID) + nla_total_size(sizeof(u_int32_t)) /* classid */ #endif + nla_total_size(sizeof(u_int32_t)); /* cap_len */ tstamp = skb_tstamp_cond(entskb, false); if (tstamp) size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)); size += nfqnl_get_bridge_size(entry); if (entry->state.hook <= NF_INET_FORWARD || (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL)) csum_verify = !skb_csum_unnecessary(entskb); else csum_verify = false; outdev = entry->state.out; switch ((enum nfqnl_config_mode)READ_ONCE(queue->copy_mode)) { case NFQNL_COPY_META: case NFQNL_COPY_NONE: break; case NFQNL_COPY_PACKET: if (!(queue->flags & NFQA_CFG_F_GSO) && entskb->ip_summed == CHECKSUM_PARTIAL && nf_queue_checksum_help(entskb)) return NULL; data_len = READ_ONCE(queue->copy_range); if (data_len > entskb->len) data_len = entskb->len; hlen = skb_zerocopy_headlen(entskb); hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; break; } nfnl_ct = rcu_dereference(nfnl_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (queue->flags & NFQA_CFG_F_CONNTRACK) { if (nfnl_ct != NULL) { ct = nf_ct_get(entskb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } #endif if (queue->flags & NFQA_CFG_F_UID_GID) { size += (nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t))); /* gid */ } if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) { seclen = nfqnl_get_sk_secctx(entskb, &secdata); if (seclen) size += nla_total_size(seclen); } skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); goto nlmsg_failure; } nlh = nfnl_msg_put(skb, 0, 0, nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), 0, entry->state.pf, NFNETLINK_V0, htons(queue->queue_num)); if (!nlh) { skb_tx_error(entskb); kfree_skb(skb); goto nlmsg_failure; } nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); pmsg = nla_data(nla); pmsg->hw_protocol = entskb->protocol; pmsg->hook = entry->state.hook; *packet_id_ptr = &pmsg->packet_id; indev = entry->state.in; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else if (entry->state.pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; physinif = nf_bridge_get_physinif(entskb); if (physinif && nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(physinif))) goto nla_put_failure; } #endif } if (outdev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else if (entry->state.pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { int physoutif; /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; physoutif = nf_bridge_get_physoutif(entskb); if (physoutif && nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(physoutif))) goto nla_put_failure; } #endif } if (entskb->mark && nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) goto nla_put_failure; if (entskb->priority && nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority))) goto nla_put_failure; if (indev && entskb->dev && skb_mac_header_was_set(entskb) && skb_mac_header_len(entskb) != 0) { struct nfqnl_msg_packet_hw phw; int len; memset(&phw, 0, sizeof(phw)); len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) goto nla_put_failure; } } if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure; if (entry->state.hook <= NF_INET_FORWARD && tstamp) { struct nfqnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(tstamp); ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; } if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk && nfqnl_put_sk_uidgid(skb, entskb->sk) < 0) goto nla_put_failure; if (nfqnl_put_sk_classid(skb, entskb->sk) < 0) goto nla_put_failure; if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata)) goto nla_put_failure; if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0) goto nla_put_failure; if (cap_len > data_len && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) goto nla_put_failure; if (nfqnl_put_packet_info(skb, entskb, csum_verify)) goto nla_put_failure; if (data_len) { struct nlattr *nla; if (skb_tailroom(skb) < sizeof(*nla) + hlen) goto nla_put_failure; nla = skb_put(skb, sizeof(*nla)); nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); if (skb_zerocopy(skb, entskb, data_len, hlen)) goto nla_put_failure; } nlh->nlmsg_len = skb->len; if (seclen) security_release_secctx(secdata, seclen); return skb; nla_put_failure: skb_tx_error(entskb); kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); nlmsg_failure: if (seclen) security_release_secctx(secdata, seclen); return NULL; } static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; struct nf_conn *ct = (void *)skb_nfct(entry->skb); unsigned long status; unsigned int use; if (!ct) return false; status = READ_ONCE(ct->status); if ((status & flags) == IPS_DYING) return true; if (status & IPS_CONFIRMED) return false; /* in some cases skb_clone() can occur after initial conntrack * pickup, but conntrack assumes exclusive skb->_nfct ownership for * unconfirmed entries. * * This happens for br_netfilter and with ip multicast routing. * We can't be solved with serialization here because one clone could * have been queued for local delivery. */ use = refcount_read(&ct->ct_general.use); if (likely(use == 1)) return false; /* Can't decrement further? Exclusive ownership. */ if (!refcount_dec_not_one(&ct->ct_general.use)) return false; skb_set_nfct(entry->skb, 0); /* No nf_ct_put(): we already decremented .use and it cannot * drop down to 0. */ return true; #endif return false; } static int __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry) { struct sk_buff *nskb; int err = -ENOBUFS; __be32 *packet_id_ptr; int failopen = 0; nskb = nfqnl_build_packet_message(net, queue, entry, &packet_id_ptr); if (nskb == NULL) { err = -ENOMEM; goto err_out; } spin_lock_bh(&queue->lock); if (nf_ct_drop_unconfirmed(entry)) goto err_out_free_nskb; if (queue->queue_total >= queue->queue_maxlen) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; } else { queue->queue_dropped++; net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", queue->queue_total); } goto err_out_free_nskb; } entry->id = ++queue->id_sequence; *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; } else { queue->queue_user_dropped++; } goto err_out_unlock; } __enqueue_entry(queue, entry); spin_unlock_bh(&queue->lock); return 0; err_out_free_nskb: kfree_skb(nskb); err_out_unlock: spin_unlock_bh(&queue->lock); if (failopen) nfqnl_reinject(entry, NF_ACCEPT); err_out: return err; } static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); if (!entry) return NULL; if (nf_queue_entry_get_refs(entry)) return entry; kfree(entry); return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* When called from bridge netfilter, skb->data must point to MAC header * before calling skb_gso_segment(). Else, original MAC header is lost * and segmented skbs will be sent to wrong destination. */ static void nf_bridge_adjust_skb_data(struct sk_buff *skb) { if (nf_bridge_info_get(skb)) __skb_push(skb, skb->network_header - skb->mac_header); } static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) { if (nf_bridge_info_get(skb)) __skb_pull(skb, skb->network_header - skb->mac_header); } #else #define nf_bridge_adjust_skb_data(s) do {} while (0) #define nf_bridge_adjust_segmented_data(s) do {} while (0) #endif static int __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, struct sk_buff *skb, struct nf_queue_entry *entry) { int ret = -ENOMEM; struct nf_queue_entry *entry_seg; nf_bridge_adjust_segmented_data(skb); if (skb->next == NULL) { /* last packet, no need to copy entry */ struct sk_buff *gso_skb = entry->skb; entry->skb = skb; ret = __nfqnl_enqueue_packet(net, queue, entry); if (ret) entry->skb = gso_skb; return ret; } skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { entry_seg->skb = skb; ret = __nfqnl_enqueue_packet(net, queue, entry_seg); if (ret) nf_queue_entry_free(entry_seg); } return ret; } static int nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { unsigned int queued; struct nfqnl_instance *queue; struct sk_buff *skb, *segs, *nskb; int err = -ENOBUFS; struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); /* rcu_read_lock()ed by nf_hook_thresh */ queue = instance_lookup(q, queuenum); if (!queue) return -ESRCH; if (queue->copy_mode == NFQNL_COPY_NONE) return -EINVAL; skb = entry->skb; switch (entry->state.pf) { case NFPROTO_IPV4: skb->protocol = htons(ETH_P_IP); break; case NFPROTO_IPV6: skb->protocol = htons(ETH_P_IPV6); break; } if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ESRCH to * mean 'ignore this hook'. */ if (IS_ERR_OR_NULL(segs)) goto out_err; queued = 0; err = 0; skb_list_walk_safe(segs, segs, nskb) { if (err == 0) err = __nfqnl_enqueue_packet_gso(net, queue, segs, entry); if (err == 0) queued++; else kfree_skb(segs); } if (queued) { if (err) /* some segments are already queued */ nf_queue_entry_free(entry); kfree_skb(skb); return 0; } out_err: nf_bridge_adjust_segmented_data(skb); return err; } static int nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; if (diff < 0) { unsigned int min_len = skb_transport_offset(e->skb); if (data_len < min_len) return -EINVAL; if (pskb_trim(e->skb, data_len)) return -ENOMEM; } else if (diff > 0) { if (data_len > 0xFFFF) return -EINVAL; if (diff > skb_tailroom(e->skb)) { nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), diff, GFP_ATOMIC); if (!nskb) return -ENOMEM; kfree_skb(e->skb); e->skb = nskb; } skb_put(e->skb, diff); } if (skb_ensure_writable(e->skb, data_len)) return -ENOMEM; skb_copy_to_linear_data(e->skb, data, data_len); e->skb->ip_summed = CHECKSUM_NONE; return 0; } static int nfqnl_set_mode(struct nfqnl_instance *queue, unsigned char mode, unsigned int range) { int status = 0; spin_lock_bh(&queue->lock); switch (mode) { case NFQNL_COPY_NONE: case NFQNL_COPY_META: queue->copy_mode = mode; queue->copy_range = 0; break; case NFQNL_COPY_PACKET: queue->copy_mode = mode; if (range == 0 || range > NFQNL_MAX_COPY_RANGE) queue->copy_range = NFQNL_MAX_COPY_RANGE; else queue->copy_range = range; break; default: status = -EINVAL; } spin_unlock_bh(&queue->lock); return status; } static int dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int physinif, physoutif; physinif = nf_bridge_get_physinif(entry->skb); physoutif = nf_bridge_get_physoutif(entry->skb); if (physinif == ifindex || physoutif == ifindex) return 1; #endif if (entry->state.in) if (entry->state.in->ifindex == ifindex) return 1; if (entry->state.out) if (entry->state.out->ifindex == ifindex) return 1; return 0; } /* drop all packets with either indev or outdev == ifindex from all queue * instances */ static void nfqnl_dev_drop(struct net *net, int ifindex) { int i; struct nfnl_queue_net *q = nfnl_queue_pernet(net); rcu_read_lock(); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, dev_cmp, ifindex); } rcu_read_unlock(); } static int nfqnl_rcv_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Drop any packets associated with the downed device */ if (event == NETDEV_DOWN) nfqnl_dev_drop(dev_net(dev), dev->ifindex); return NOTIFY_DONE; } static struct notifier_block nfqnl_dev_notifier = { .notifier_call = nfqnl_rcv_dev_event, }; static void nfqnl_nf_hook_drop(struct net *net) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); int i; /* This function is also called on net namespace error unwind, * when pernet_ops->init() failed and ->exit() functions of the * previous pernet_ops gets called. * * This may result in a call to nfqnl_nf_hook_drop() before * struct nfnl_queue_net was allocated. */ if (!q) return; for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, NULL, 0); } } static int nfqnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct nfnl_queue_net *q = nfnl_queue_pernet(n->net); if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this portid */ spin_lock(&q->instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *t2; struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_safe(inst, t2, head, hlist) { if (n->portid == inst->peer_portid) __instance_destroy(inst); } } spin_unlock(&q->instances_lock); } return NOTIFY_DONE; } static struct notifier_block nfqnl_rtnl_notifier = { .notifier_call = nfqnl_rcv_nl_event, }; static const struct nla_policy nfqa_vlan_policy[NFQA_VLAN_MAX + 1] = { [NFQA_VLAN_TCI] = { .type = NLA_U16}, [NFQA_VLAN_PROTO] = { .type = NLA_U16}, }; static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, [NFQA_CT] = { .type = NLA_UNSPEC }, [NFQA_EXP] = { .type = NLA_UNSPEC }, [NFQA_VLAN] = { .type = NLA_NESTED }, [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static struct nfqnl_instance * verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, u32 nlportid) { struct nfqnl_instance *queue; queue = instance_lookup(q, queue_num); if (!queue) return ERR_PTR(-ENODEV); if (queue->peer_portid != nlportid) return ERR_PTR(-EPERM); return queue; } static struct nfqnl_msg_verdict_hdr* verdicthdr_get(const struct nlattr * const nfqa[]) { struct nfqnl_msg_verdict_hdr *vhdr; unsigned int verdict; if (!nfqa[NFQA_VERDICT_HDR]) return NULL; vhdr = nla_data(nfqa[NFQA_VERDICT_HDR]); verdict = ntohl(vhdr->verdict) & NF_VERDICT_MASK; if (verdict > NF_MAX_VERDICT || verdict == NF_STOLEN) return NULL; return vhdr; } static int nfq_id_after(unsigned int id, unsigned int max) { return (int)(id - max) > 0; } static int nfqnl_recv_verdict_batch(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u16 queue_num = ntohs(info->nfmsg->res_id); struct nf_queue_entry *entry, *tmp; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; unsigned int verdict, maxid; LIST_HEAD(batch_list); queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); vhdr = verdicthdr_get(nfqa); if (!vhdr) return -EINVAL; verdict = ntohl(vhdr->verdict); maxid = ntohl(vhdr->id); spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, tmp, &queue->queue_list, list) { if (nfq_id_after(entry->id, maxid)) break; __dequeue_entry(queue, entry); list_add_tail(&entry->list, &batch_list); } spin_unlock_bh(&queue->lock); if (list_empty(&batch_list)) return -ENOENT; list_for_each_entry_safe(entry, tmp, &batch_list, list) { if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); if (nfqa[NFQA_PRIORITY]) entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); nfqnl_reinject(entry, verdict); } return 0; } static struct nf_conn *nfqnl_ct_parse(const struct nfnl_ct_hook *nfnl_ct, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[], struct nf_queue_entry *entry, enum ip_conntrack_info *ctinfo) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conn *ct; ct = nf_ct_get(entry->skb, ctinfo); if (ct == NULL) return NULL; if (nfnl_ct->parse(nfqa[NFQA_CT], ct) < 0) return NULL; if (nfqa[NFQA_EXP]) nfnl_ct->attach_expect(nfqa[NFQA_EXP], ct, NETLINK_CB(entry->skb).portid, nlmsg_report(nlh)); return ct; #else return NULL; #endif } static int nfqa_parse_bridge(struct nf_queue_entry *entry, const struct nlattr * const nfqa[]) { if (nfqa[NFQA_VLAN]) { struct nlattr *tb[NFQA_VLAN_MAX + 1]; int err; err = nla_parse_nested_deprecated(tb, NFQA_VLAN_MAX, nfqa[NFQA_VLAN], nfqa_vlan_policy, NULL); if (err < 0) return err; if (!tb[NFQA_VLAN_TCI] || !tb[NFQA_VLAN_PROTO]) return -EINVAL; __vlan_hwaccel_put_tag(entry->skb, nla_get_be16(tb[NFQA_VLAN_PROTO]), ntohs(nla_get_be16(tb[NFQA_VLAN_TCI]))); } if (nfqa[NFQA_L2HDR]) { int mac_header_len = entry->skb->network_header - entry->skb->mac_header; if (mac_header_len != nla_len(nfqa[NFQA_L2HDR])) return -EINVAL; else if (mac_header_len > 0) memcpy(skb_mac_header(entry->skb), nla_data(nfqa[NFQA_L2HDR]), mac_header_len); } return 0; } static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); const struct nfnl_ct_hook *nfnl_ct; struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; struct nf_queue_entry *entry; struct nf_conn *ct = NULL; unsigned int verdict; int err; queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); vhdr = verdicthdr_get(nfqa); if (!vhdr) return -EINVAL; verdict = ntohl(vhdr->verdict); entry = find_dequeue_entry(queue, ntohl(vhdr->id)); if (entry == NULL) return -ENOENT; /* rcu lock already held from nfnl->call_rcu. */ nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfqa[NFQA_CT]) { if (nfnl_ct != NULL) ct = nfqnl_ct_parse(nfnl_ct, info->nlh, nfqa, entry, &ctinfo); } if (entry->state.pf == PF_BRIDGE) { err = nfqa_parse_bridge(entry, nfqa); if (err < 0) return err; } if (nfqa[NFQA_PAYLOAD]) { u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); int diff = payload_len - entry->skb->len; if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), payload_len, entry, diff) < 0) verdict = NF_DROP; if (ct && diff) nfnl_ct->seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); if (nfqa[NFQA_PRIORITY]) entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); nfqnl_reinject(entry, verdict); return 0; } static int nfqnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { return -ENOTSUPP; } static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { [NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) }, [NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) }, [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 }, [NFQA_CFG_MASK] = { .type = NLA_U32 }, [NFQA_CFG_FLAGS] = { .type = NLA_U32 }, }; static const struct nf_queue_handler nfqh = { .outfn = nfqnl_enqueue_packet, .nf_hook_drop = nfqnl_nf_hook_drop, }; static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_config_cmd *cmd = NULL; struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; int ret = 0; if (nfqa[NFQA_CFG_CMD]) { cmd = nla_data(nfqa[NFQA_CFG_CMD]); /* Obsolete commands without queue context */ switch (cmd->command) { case NFQNL_CFG_CMD_PF_BIND: return 0; case NFQNL_CFG_CMD_PF_UNBIND: return 0; } } /* Check if we support these flags in first place, dependencies should * be there too not to break atomicity. */ if (nfqa[NFQA_CFG_FLAGS]) { if (!nfqa[NFQA_CFG_MASK]) { /* A mask is needed to specify which flags are being * changed. */ return -EINVAL; } flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS])); mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK])); if (flags >= NFQA_CFG_F_MAX) return -EOPNOTSUPP; #if !IS_ENABLED(CONFIG_NETWORK_SECMARK) if (flags & mask & NFQA_CFG_F_SECCTX) return -EOPNOTSUPP; #endif if ((flags & mask & NFQA_CFG_F_CONNTRACK) && !rcu_access_pointer(nfnl_ct_hook)) { #ifdef CONFIG_MODULES nfnl_unlock(NFNL_SUBSYS_QUEUE); request_module("ip_conntrack_netlink"); nfnl_lock(NFNL_SUBSYS_QUEUE); if (rcu_access_pointer(nfnl_ct_hook)) return -EAGAIN; #endif return -EOPNOTSUPP; } } rcu_read_lock(); queue = instance_lookup(q, queue_num); if (queue && queue->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto err_out_unlock; } if (cmd != NULL) { switch (cmd->command) { case NFQNL_CFG_CMD_BIND: if (queue) { ret = -EBUSY; goto err_out_unlock; } queue = instance_create(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) { ret = PTR_ERR(queue); goto err_out_unlock; } break; case NFQNL_CFG_CMD_UNBIND: if (!queue) { ret = -ENODEV; goto err_out_unlock; } instance_destroy(q, queue); goto err_out_unlock; case NFQNL_CFG_CMD_PF_BIND: case NFQNL_CFG_CMD_PF_UNBIND: break; default: ret = -ENOTSUPP; goto err_out_unlock; } } if (!queue) { ret = -ENODEV; goto err_out_unlock; } if (nfqa[NFQA_CFG_PARAMS]) { struct nfqnl_msg_config_params *params = nla_data(nfqa[NFQA_CFG_PARAMS]); nfqnl_set_mode(queue, params->copy_mode, ntohl(params->copy_range)); } if (nfqa[NFQA_CFG_QUEUE_MAXLEN]) { __be32 *queue_maxlen = nla_data(nfqa[NFQA_CFG_QUEUE_MAXLEN]); spin_lock_bh(&queue->lock); queue->queue_maxlen = ntohl(*queue_maxlen); spin_unlock_bh(&queue->lock); } if (nfqa[NFQA_CFG_FLAGS]) { spin_lock_bh(&queue->lock); queue->flags &= ~mask; queue->flags |= flags & mask; spin_unlock_bh(&queue->lock); } err_out_unlock: rcu_read_unlock(); return ret; } static const struct nfnl_callback nfqnl_cb[NFQNL_MSG_MAX] = { [NFQNL_MSG_PACKET] = { .call = nfqnl_recv_unsupp, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, }, [NFQNL_MSG_VERDICT] = { .call = nfqnl_recv_verdict, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, .policy = nfqa_verdict_policy }, [NFQNL_MSG_CONFIG] = { .call = nfqnl_recv_config, .type = NFNL_CB_MUTEX, .attr_count = NFQA_CFG_MAX, .policy = nfqa_cfg_policy }, [NFQNL_MSG_VERDICT_BATCH] = { .call = nfqnl_recv_verdict_batch, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, .policy = nfqa_verdict_batch_policy }, }; static const struct nfnetlink_subsystem nfqnl_subsys = { .name = "nf_queue", .subsys_id = NFNL_SUBSYS_QUEUE, .cb_count = NFQNL_MSG_MAX, .cb = nfqnl_cb, }; #ifdef CONFIG_PROC_FS struct iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *get_first(struct seq_file *seq) { struct iter_state *st = seq->private; struct net *net; struct nfnl_queue_net *q; if (!st) return NULL; net = seq_file_net(seq); q = nfnl_queue_pernet(net); for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { if (!hlist_empty(&q->instance_table[st->bucket])) return q->instance_table[st->bucket].first; } return NULL; } static struct hlist_node *get_next(struct seq_file *seq, struct hlist_node *h) { struct iter_state *st = seq->private; struct net *net = seq_file_net(seq); h = h->next; while (!h) { struct nfnl_queue_net *q; if (++st->bucket >= INSTANCE_BUCKETS) return NULL; q = nfnl_queue_pernet(net); h = q->instance_table[st->bucket].first; } return h; } static struct hlist_node *get_idx(struct seq_file *seq, loff_t pos) { struct hlist_node *head; head = get_first(seq); if (head) while (pos && (head = get_next(seq, head))) pos--; return pos ? NULL : head; } static void *seq_start(struct seq_file *s, loff_t *pos) __acquires(nfnl_queue_pernet(seq_file_net(s))->instances_lock) { spin_lock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock); return get_idx(s, *pos); } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return get_next(s, v); } static void seq_stop(struct seq_file *s, void *v) __releases(nfnl_queue_pernet(seq_file_net(s))->instances_lock) { spin_unlock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock); } static int seq_show(struct seq_file *s, void *v) { const struct nfqnl_instance *inst = v; seq_printf(s, "%5u %6u %5u %1u %5u %5u %5u %8u %2d\n", inst->queue_num, inst->peer_portid, inst->queue_total, inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); return 0; } static const struct seq_operations nfqnl_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ static int __net_init nfnl_queue_net_init(struct net *net) { unsigned int i; struct nfnl_queue_net *q = nfnl_queue_pernet(net); for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&q->instance_table[i]); spin_lock_init(&q->instances_lock); #ifdef CONFIG_PROC_FS if (!proc_create_net("nfnetlink_queue", 0440, net->nf.proc_netfilter, &nfqnl_seq_ops, sizeof(struct iter_state))) return -ENOMEM; #endif return 0; } static void __net_exit nfnl_queue_net_exit(struct net *net) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); unsigned int i; #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter); #endif for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&q->instance_table[i])); } static struct pernet_operations nfnl_queue_net_ops = { .init = nfnl_queue_net_init, .exit = nfnl_queue_net_exit, .id = &nfnl_queue_net_id, .size = sizeof(struct nfnl_queue_net), }; static int __init nfnetlink_queue_init(void) { int status; status = register_pernet_subsys(&nfnl_queue_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); goto out; } netlink_register_notifier(&nfqnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfqnl_subsys); if (status < 0) { pr_err("failed to create netlink socket\n"); goto cleanup_netlink_notifier; } status = register_netdevice_notifier(&nfqnl_dev_notifier); if (status < 0) { pr_err("failed to register netdevice notifier\n"); goto cleanup_netlink_subsys; } nf_register_queue_handler(&nfqh); return status; cleanup_netlink_subsys: nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); out: return status; } static void __exit nfnetlink_queue_fini(void) { nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_DESCRIPTION("netfilter packet queue handler"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_QUEUE); module_init(nfnetlink_queue_init); module_exit(nfnetlink_queue_fini); |
| 3 3 3 3 3 16 16 454 454 125 125 36 93 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2010 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm_main.c * implements evm_inode_setxattr, evm_inode_post_setxattr, * evm_inode_removexattr, evm_verifyxattr, and evm_inode_set_acl. */ #define pr_fmt(fmt) "EVM: "fmt #include <linux/init.h> #include <linux/audit.h> #include <linux/xattr.h> #include <linux/integrity.h> #include <linux/evm.h> #include <linux/magic.h> #include <linux/posix_acl_xattr.h> #include <linux/lsm_hooks.h> #include <crypto/hash.h> #include <crypto/hash_info.h> #include <crypto/utils.h> #include "evm.h" int evm_initialized; static const char * const integrity_status_msg[] = { "pass", "pass_immutable", "fail", "fail_immutable", "no_label", "no_xattrs", "unknown" }; int evm_hmac_attrs; static struct xattr_list evm_config_default_xattrnames[] = { { .name = XATTR_NAME_SELINUX, .enabled = IS_ENABLED(CONFIG_SECURITY_SELINUX) }, { .name = XATTR_NAME_SMACK, .enabled = IS_ENABLED(CONFIG_SECURITY_SMACK) }, { .name = XATTR_NAME_SMACKEXEC, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKTRANSMUTE, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKMMAP, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_APPARMOR, .enabled = IS_ENABLED(CONFIG_SECURITY_APPARMOR) }, { .name = XATTR_NAME_IMA, .enabled = IS_ENABLED(CONFIG_IMA_APPRAISE) }, { .name = XATTR_NAME_CAPS, .enabled = true }, }; LIST_HEAD(evm_config_xattrnames); static int evm_fixmode __ro_after_init; static int __init evm_set_fixmode(char *str) { if (strncmp(str, "fix", 3) == 0) evm_fixmode = 1; else pr_err("invalid \"%s\" mode", str); return 1; } __setup("evm=", evm_set_fixmode); static void __init evm_init_config(void) { int i, xattrs; xattrs = ARRAY_SIZE(evm_config_default_xattrnames); pr_info("Initialising EVM extended attributes:\n"); for (i = 0; i < xattrs; i++) { pr_info("%s%s\n", evm_config_default_xattrnames[i].name, !evm_config_default_xattrnames[i].enabled ? " (disabled)" : ""); list_add_tail(&evm_config_default_xattrnames[i].list, &evm_config_xattrnames); } #ifdef CONFIG_EVM_ATTR_FSUUID evm_hmac_attrs |= EVM_ATTR_FSUUID; #endif pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs); } static bool evm_key_loaded(void) { return (bool)(evm_initialized & EVM_KEY_MASK); } /* * This function determines whether or not it is safe to ignore verification * errors, based on the ability of EVM to calculate HMACs. If the HMAC key * is not loaded, and it cannot be loaded in the future due to the * EVM_SETUP_COMPLETE initialization flag, allowing an operation despite the * attrs/xattrs being found invalid will not make them valid. */ static bool evm_hmac_disabled(void) { if (evm_initialized & EVM_INIT_HMAC) return false; if (!(evm_initialized & EVM_SETUP_COMPLETE)) return false; return true; } static int evm_find_protected_xattrs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct xattr_list *xattr; int error; int count = 0; if (!(inode->i_opflags & IOP_XATTR)) return -EOPNOTSUPP; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0); if (error < 0) { if (error == -ENODATA) continue; return error; } count++; } return count; } static int is_unsupported_hmac_fs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (inode->i_sb->s_iflags & SB_I_EVM_HMAC_UNSUPPORTED) { pr_info_once("%s not supported\n", inode->i_sb->s_type->name); return 1; } return 0; } /* * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr * * Compute the HMAC on the dentry's protected set of extended attributes * and compare it against the stored security.evm xattr. * * For performance: * - use the previoulsy retrieved xattr value and length to calculate the * HMAC.) * - cache the verification result in the iint, when available. * * Returns integrity status */ static enum integrity_status evm_verify_hmac(struct dentry *dentry, const char *xattr_name, char *xattr_value, size_t xattr_value_len) { struct evm_ima_xattr_data *xattr_data = NULL; struct signature_v2_hdr *hdr; enum integrity_status evm_status = INTEGRITY_PASS; struct evm_digest digest; struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); int rc, xattr_len, evm_immutable = 0; if (iint && (iint->evm_status == INTEGRITY_PASS || iint->evm_status == INTEGRITY_PASS_IMMUTABLE)) return iint->evm_status; /* * On unsupported filesystems without EVM_INIT_X509 enabled, skip * signature verification. */ if (!(evm_initialized & EVM_INIT_X509) && is_unsupported_hmac_fs(dentry)) return INTEGRITY_UNKNOWN; /* if status is not PASS, try to check again - against -ENOMEM */ /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { evm_status = INTEGRITY_FAIL; if (rc == -ENODATA) { rc = evm_find_protected_xattrs(dentry); if (rc > 0) evm_status = INTEGRITY_NOLABEL; else if (rc == 0) evm_status = INTEGRITY_NOXATTRS; /* new file */ } else if (rc == -EOPNOTSUPP) { evm_status = INTEGRITY_UNKNOWN; } goto out; } xattr_len = rc; /* check value type */ switch (xattr_data->type) { case EVM_XATTR_HMAC: if (xattr_len != sizeof(struct evm_xattr)) { evm_status = INTEGRITY_FAIL; goto out; } digest.hdr.algo = HASH_ALGO_SHA1; rc = evm_calc_hmac(dentry, xattr_name, xattr_value, xattr_value_len, &digest, iint); if (rc) break; rc = crypto_memneq(xattr_data->data, digest.digest, SHA1_DIGEST_SIZE); if (rc) rc = -EINVAL; break; case EVM_XATTR_PORTABLE_DIGSIG: evm_immutable = 1; fallthrough; case EVM_IMA_XATTR_DIGSIG: /* accept xattr with non-empty signature field */ if (xattr_len <= sizeof(struct signature_v2_hdr)) { evm_status = INTEGRITY_FAIL; goto out; } hdr = (struct signature_v2_hdr *)xattr_data; digest.hdr.algo = hdr->hash_algo; rc = evm_calc_hash(dentry, xattr_name, xattr_value, xattr_value_len, xattr_data->type, &digest, iint); if (rc) break; rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM, (const char *)xattr_data, xattr_len, digest.digest, digest.hdr.length); if (!rc) { if (xattr_data->type == EVM_XATTR_PORTABLE_DIGSIG) { if (iint) iint->flags |= EVM_IMMUTABLE_DIGSIG; evm_status = INTEGRITY_PASS_IMMUTABLE; } else if (!IS_RDONLY(inode) && !(inode->i_sb->s_readonly_remount) && !IS_IMMUTABLE(inode) && !is_unsupported_hmac_fs(dentry)) { evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } } break; default: rc = -EINVAL; break; } if (rc) { if (rc == -ENODATA) evm_status = INTEGRITY_NOXATTRS; else if (evm_immutable) evm_status = INTEGRITY_FAIL_IMMUTABLE; else evm_status = INTEGRITY_FAIL; } pr_debug("digest: (%d) [%*phN]\n", digest.hdr.length, digest.hdr.length, digest.digest); out: if (iint) iint->evm_status = evm_status; kfree(xattr_data); return evm_status; } static int evm_protected_xattr_common(const char *req_xattr_name, bool all_xattrs) { int namelen; int found = 0; struct xattr_list *xattr; namelen = strlen(req_xattr_name); list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { if (!all_xattrs && !xattr->enabled) continue; if ((strlen(xattr->name) == namelen) && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) { found = 1; break; } if (strncmp(req_xattr_name, xattr->name + XATTR_SECURITY_PREFIX_LEN, strlen(req_xattr_name)) == 0) { found = 1; break; } } return found; } int evm_protected_xattr(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, false); } int evm_protected_xattr_if_enabled(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, true); } /** * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values * @dentry: dentry of the read xattrs * @buffer: buffer xattr names, lengths or values are copied to * @buffer_size: size of buffer * @type: n: names, l: lengths, v: values * @canonical_fmt: data format (true: little endian, false: native format) * * Read protected xattr names (separated by |), lengths (u32) or values for a * given dentry and return the total size of copied data. If buffer is NULL, * just return the total size. * * Returns the total size on success, a negative value on error. */ int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt) { struct xattr_list *xattr; int rc, size, total_size = 0; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, NULL, 0); if (rc < 0 && rc == -ENODATA) continue; else if (rc < 0) return rc; switch (type) { case 'n': size = strlen(xattr->name) + 1; if (buffer) { if (total_size) *(buffer + total_size - 1) = '|'; memcpy(buffer + total_size, xattr->name, size); } break; case 'l': size = sizeof(u32); if (buffer) { if (canonical_fmt) rc = (__force int)cpu_to_le32(rc); *(u32 *)(buffer + total_size) = rc; } break; case 'v': size = rc; if (buffer) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, buffer + total_size, buffer_size - total_size); if (rc < 0) return rc; } break; default: return -EINVAL; } total_size += size; } return total_size; } /** * evm_verifyxattr - verify the integrity of the requested xattr * @dentry: object of the verify xattr * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Calculate the HMAC for the given dentry and verify it against the stored * security.evm xattr. For performance, use the xattr value and length * previously retrieved to calculate the HMAC. * * Returns the xattr integrity status. * * This function requires the caller to lock the inode's i_mutex before it * is executed. */ enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, size_t xattr_value_len) { if (!evm_key_loaded() || !evm_protected_xattr(xattr_name)) return INTEGRITY_UNKNOWN; return evm_verify_hmac(dentry, xattr_name, xattr_value, xattr_value_len); } EXPORT_SYMBOL_GPL(evm_verifyxattr); /* * evm_verify_current_integrity - verify the dentry's metadata integrity * @dentry: pointer to the affected dentry * * Verify and return the dentry's metadata integrity. The exceptions are * before EVM is initialized or in 'fix' mode. */ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (!evm_key_loaded() || !S_ISREG(inode->i_mode) || evm_fixmode) return INTEGRITY_PASS; return evm_verify_hmac(dentry, NULL, NULL, 0); } /* * evm_xattr_change - check if passed xattr value differs from current value * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Check if passed xattr value differs from current value. * * Returns 1 if passed xattr value differs from current value, 0 otherwise. */ static int evm_xattr_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { char *xattr_data = NULL; int rc = 0; rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr_name, &xattr_data, 0, GFP_NOFS); if (rc < 0) { rc = 1; goto out; } if (rc == xattr_value_len) rc = !!memcmp(xattr_value, xattr_data, rc); else rc = 1; out: kfree(xattr_data); return rc; } /* * evm_protect_xattr - protect the EVM extended attribute * * Prevent security.evm from being modified or removed without the * necessary permissions or when the existing value is invalid. * * The posix xattr acls are 'system' prefixed, which normally would not * affect security.evm. An interesting side affect of writing posix xattr * acls is their modifying of the i_mode, which is included in security.evm. * For posix xattr acls only, permit security.evm, even if it currently * doesn't exist, to be updated unless the EVM signature is immutable. */ static int evm_protect_xattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { enum integrity_status evm_status; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (is_unsupported_hmac_fs(dentry)) return -EPERM; } else if (!evm_protected_xattr(xattr_name)) { if (!posix_xattr_acl(xattr_name)) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; goto out; } else if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if (evm_status == INTEGRITY_NOXATTRS) { struct evm_iint_cache *iint; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled()) return 0; iint = evm_iint_inode(d_backing_inode(dentry)); if (iint && (iint->flags & EVM_NEW_FILE)) return 0; /* exception for pseudo filesystems */ if (dentry->d_sb->s_magic == TMPFS_MAGIC || dentry->d_sb->s_magic == SYSFS_MAGIC) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, dentry->d_name.name, "update_metadata", integrity_status_msg[evm_status], -EPERM, 0); } out: /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_xattr_change(idmap, dentry, xattr_name, xattr_value, xattr_value_len)) return 0; if (evm_status != INTEGRITY_PASS && evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return evm_status == INTEGRITY_PASS ? 0 : -EPERM; } /** * evm_inode_setxattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Before allowing the 'security.evm' protected xattr to be updated, * verify the existing value is valid. As only the kernel should have * access to the EVM encrypted key needed to calculate the HMAC, prevent * userspace from writing HMAC value. Writing 'security.evm' requires * requires CAP_SYS_ADMIN privileges. */ static int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xattr_data = xattr_value; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!xattr_value_len) return -EINVAL; if (xattr_data->type != EVM_IMA_XATTR_DIGSIG && xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) return -EPERM; } return evm_protect_xattr(idmap, dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_removexattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that * the current value is valid. */ static int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; return evm_protect_xattr(idmap, dentry, xattr_name, NULL, 0); } #ifdef CONFIG_FS_POSIX_ACL static int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { int rc; umode_t mode; struct inode *inode = d_backing_inode(dentry); if (!kacl) return 1; rc = posix_acl_update_mode(idmap, inode, &mode, &kacl); if (rc || (inode->i_mode != mode)) return 1; return 0; } #else static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { return 0; } #endif /** * evm_inode_set_acl - protect the EVM extended attribute from posix acls * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Prevent modifying posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { enum integrity_status evm_status; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_inode_set_acl_change(idmap, dentry, acl_name, kacl)) return 0; if (evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_remove_acl - Protect the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Prevent removing posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return evm_inode_set_acl(idmap, dentry, acl_name, NULL); } static void evm_reset_status(struct inode *inode) { struct evm_iint_cache *iint; iint = evm_iint_inode(inode); if (iint) iint->evm_status = INTEGRITY_UNKNOWN; } /** * evm_metadata_changed: Detect changes to the metadata * @inode: a file's inode * @metadata_inode: metadata inode * * On a stacked filesystem detect whether the metadata has changed. If this is * the case reset the evm_status associated with the inode that represents the * file. */ bool evm_metadata_changed(struct inode *inode, struct inode *metadata_inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); bool ret = false; if (iint) { ret = (!IS_I_VERSION(metadata_inode) || integrity_inode_attrs_changed(&iint->metadata_inode, metadata_inode)); if (ret) iint->evm_status = INTEGRITY_UNKNOWN; } return ret; } /** * evm_revalidate_status - report whether EVM status re-validation is necessary * @xattr_name: pointer to the affected extended attribute name * * Report whether callers of evm_verifyxattr() should re-validate the * EVM status. * * Return true if re-validation is necessary, false otherwise. */ bool evm_revalidate_status(const char *xattr_name) { if (!evm_key_loaded()) return false; /* evm_inode_post_setattr() passes NULL */ if (!xattr_name) return true; if (!evm_protected_xattr(xattr_name) && !posix_xattr_acl(xattr_name) && strcmp(xattr_name, XATTR_NAME_EVM)) return false; return true; } /** * evm_inode_post_setxattr - update 'security.evm' to reflect the changes * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Update the HMAC stored in 'security.evm' to reflect the change. * * No need to take the i_mutex lock here, as this function is called from * __vfs_setxattr_noperm(). The caller of which has taken the inode's * i_mutex lock. */ static void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_post_set_acl - Update the EVM extended attribute from posix acls * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after setting * posix acls. */ static void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0); } /** * evm_inode_post_removexattr - update 'security.evm' after removing the xattr * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Update the HMAC stored in 'security.evm' to reflect removal of the xattr. * * No need to take the i_mutex lock here, as this function is called from * vfs_removexattr() which takes the i_mutex. */ static void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; evm_update_evmxattr(dentry, xattr_name, NULL, 0); } /** * evm_inode_post_remove_acl - Update the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after * removing posix acls. */ static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { evm_inode_post_removexattr(dentry, acl_name); } static int evm_attr_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = attr->ia_valid; if (!i_uid_needs_update(idmap, attr, inode) && !i_gid_needs_update(idmap, attr, inode) && (!(ia_valid & ATTR_MODE) || attr->ia_mode == inode->i_mode)) return 0; return 1; } /** * evm_inode_setattr - prevent updating an invalid EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @attr: iattr structure containing the new file attributes * * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. */ static int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; enum integrity_status evm_status; /* Policy permits modification of the protected attrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) return 0; evm_status = evm_verify_current_integrity(dentry); /* * Writing attrs is safe for portable signatures, as portable signatures * are immutable and can never be updated. */ if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS) || (evm_status == INTEGRITY_FAIL_IMMUTABLE) || (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN))) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_attr_change(idmap, dentry, attr)) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_post_setattr - update 'security.evm' after modifying metadata * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * For now, update the HMAC stored in 'security.evm' to reflect UID/GID * changes. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void evm_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (!evm_revalidate_status(NULL)) return; evm_reset_status(dentry->d_inode); if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) evm_update_evmxattr(dentry, NULL, NULL, 0); } static int evm_inode_copy_up_xattr(struct dentry *src, const char *name) { struct evm_ima_xattr_data *xattr_data = NULL; int rc; if (strcmp(name, XATTR_NAME_EVM) != 0) return -EOPNOTSUPP; /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, src, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) return -EPERM; if (rc < offsetof(struct evm_ima_xattr_data, type) + sizeof(xattr_data->type)) return -EPERM; switch (xattr_data->type) { case EVM_XATTR_PORTABLE_DIGSIG: rc = 0; /* allow copy-up */ break; case EVM_XATTR_HMAC: case EVM_IMA_XATTR_DIGSIG: default: rc = -ECANCELED; /* discard */ } kfree(xattr_data); return rc; } /* * evm_inode_init_security - initializes security.evm HMAC value */ int evm_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { struct evm_xattr *xattr_data; struct xattr *xattr, *evm_xattr; bool evm_protected_xattrs = false; int rc; if (!(evm_initialized & EVM_INIT_HMAC) || !xattrs) return 0; /* * security_inode_init_security() makes sure that the xattrs array is * contiguous, there is enough space for security.evm, and that there is * a terminator at the end of the array. */ for (xattr = xattrs; xattr->name; xattr++) { if (evm_protected_xattr(xattr->name)) evm_protected_xattrs = true; } /* EVM xattr not needed. */ if (!evm_protected_xattrs) return 0; evm_xattr = lsm_get_xattr_slot(xattrs, xattr_count); /* * Array terminator (xattr name = NULL) must be the first non-filled * xattr slot. */ WARN_ONCE(evm_xattr != xattr, "%s: xattrs terminator is not the first non-filled slot\n", __func__); xattr_data = kzalloc(sizeof(*xattr_data), GFP_NOFS); if (!xattr_data) return -ENOMEM; xattr_data->data.type = EVM_XATTR_HMAC; rc = evm_init_hmac(inode, xattrs, xattr_data->digest); if (rc < 0) goto out; evm_xattr->value = xattr_data; evm_xattr->value_len = sizeof(*xattr_data); evm_xattr->name = XATTR_EVM_SUFFIX; return 0; out: kfree(xattr_data); return rc; } EXPORT_SYMBOL_GPL(evm_inode_init_security); static int evm_inode_alloc_security(struct inode *inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); /* Called by security_inode_alloc(), it cannot be NULL. */ iint->flags = 0UL; iint->evm_status = INTEGRITY_UNKNOWN; return 0; } static void evm_file_release(struct file *file) { struct inode *inode = file_inode(file); struct evm_iint_cache *iint = evm_iint_inode(inode); fmode_t mode = file->f_mode; if (!S_ISREG(inode->i_mode) || !(mode & FMODE_WRITE)) return; if (iint && iint->flags & EVM_NEW_FILE && atomic_read(&inode->i_writecount) == 1) iint->flags &= ~EVM_NEW_FILE; } static void evm_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); if (!S_ISREG(inode->i_mode)) return; if (iint) iint->flags |= EVM_NEW_FILE; } #ifdef CONFIG_EVM_LOAD_X509 void __init evm_load_x509(void) { int rc; rc = integrity_load_x509(INTEGRITY_KEYRING_EVM, CONFIG_EVM_X509_PATH); if (!rc) evm_initialized |= EVM_INIT_X509; } #endif static int __init init_evm(void) { int error; struct list_head *pos, *q; evm_init_config(); error = integrity_init_keyring(INTEGRITY_KEYRING_EVM); if (error) goto error; error = evm_init_secfs(); if (error < 0) { pr_info("Error registering secfs\n"); goto error; } error: if (error != 0) { if (!list_empty(&evm_config_xattrnames)) { list_for_each_safe(pos, q, &evm_config_xattrnames) list_del(pos); } } return error; } static struct security_hook_list evm_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_setattr, evm_inode_setattr), LSM_HOOK_INIT(inode_post_setattr, evm_inode_post_setattr), LSM_HOOK_INIT(inode_copy_up_xattr, evm_inode_copy_up_xattr), LSM_HOOK_INIT(inode_setxattr, evm_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, evm_inode_post_setxattr), LSM_HOOK_INIT(inode_set_acl, evm_inode_set_acl), LSM_HOOK_INIT(inode_post_set_acl, evm_inode_post_set_acl), LSM_HOOK_INIT(inode_remove_acl, evm_inode_remove_acl), LSM_HOOK_INIT(inode_post_remove_acl, evm_inode_post_remove_acl), LSM_HOOK_INIT(inode_removexattr, evm_inode_removexattr), LSM_HOOK_INIT(inode_post_removexattr, evm_inode_post_removexattr), LSM_HOOK_INIT(inode_init_security, evm_inode_init_security), LSM_HOOK_INIT(inode_alloc_security, evm_inode_alloc_security), LSM_HOOK_INIT(file_release, evm_file_release), LSM_HOOK_INIT(path_post_mknod, evm_post_path_mknod), }; static const struct lsm_id evm_lsmid = { .name = "evm", .id = LSM_ID_EVM, }; static int __init init_evm_lsm(void) { security_add_hooks(evm_hooks, ARRAY_SIZE(evm_hooks), &evm_lsmid); return 0; } struct lsm_blob_sizes evm_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct evm_iint_cache), .lbs_xattr_count = 1, }; DEFINE_LSM(evm) = { .name = "evm", .init = init_evm_lsm, .order = LSM_ORDER_LAST, .blobs = &evm_blob_sizes, }; late_initcall(init_evm); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Guest PC manipulation helpers * * Copyright (C) 2012,2013 - ARM Ltd * Copyright (C) 2020 - Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ #define __ARM64_KVM_HYP_ADJUST_PC_H__ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu); } else { *vcpu_pc(vcpu) += 4; *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /* * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu); write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } /* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ static inline void kvm_skip_host_instr(void) { write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); } #endif |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <net/busy_poll.h> #include <net/net_namespace.h> #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> #include <net/sock.h> #include <net/xdp.h> #include <net/xdp_sock.h> #include "dev.h" #include "devmem.h" #include "netdev-genl-gen.h" struct netdev_nl_dump_ctx { unsigned long ifindex; unsigned int rxq_idx; unsigned int txq_idx; unsigned int napi_id; }; static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb) { NL_ASSERT_CTX_FITS(struct netdev_nl_dump_ctx); return (struct netdev_nl_dump_ctx *)cb->ctx; } static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { u64 xsk_features = 0; u64 xdp_rx_meta = 0; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; #define XDP_METADATA_KFUNC(_, flag, __, xmo) \ if (netdev->xdp_metadata_ops && netdev->xdp_metadata_ops->xmo) \ xdp_rx_meta |= flag; XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC if (netdev->xsk_tx_metadata_ops) { if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp) xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP; if (netdev->xsk_tx_metadata_ops->tmo_request_checksum) xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM; } if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, netdev->xdp_features, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, xdp_rx_meta, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, xsk_features, NETDEV_A_DEV_PAD)) goto err_cancel_msg; if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) { if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, netdev->xdp_zc_max_segs)) goto err_cancel_msg; } genlmsg_end(rsp, hdr); return 0; err_cancel_msg: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static void netdev_genl_dev_notify(struct net_device *netdev, int cmd) { struct genl_info info; struct sk_buff *ntf; if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev), NETDEV_NLGRP_MGMT)) return; genl_info_init_ntf(&info, &netdev_nl_family, cmd); ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) return; if (netdev_nl_dev_fill(netdev, ntf, &info)) { nlmsg_free(ntf); return; } genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf, 0, NETDEV_NLGRP_MGMT, GFP_KERNEL); } int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info) { struct net_device *netdev; struct sk_buff *rsp; u32 ifindex; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX)) return -EINVAL; ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; rtnl_lock(); netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (netdev) err = netdev_nl_dev_fill(netdev, rsp, info); else err = -ENODEV; rtnl_unlock(); if (err) goto err_free_msg; return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); return err; } int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; int err = 0; rtnl_lock(); for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb)); if (err < 0) break; } rtnl_unlock(); return err; } static int netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, const struct genl_info *info) { unsigned long irq_suspend_timeout; unsigned long gro_flush_timeout; u32 napi_defer_hard_irqs; void *hdr; pid_t pid; if (WARN_ON_ONCE(!napi->dev)) return -EINVAL; if (!(napi->dev->flags & IFF_UP)) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (napi->napi_id >= MIN_NAPI_ID && nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) goto nla_put_failure; if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) goto nla_put_failure; if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq)) goto nla_put_failure; if (napi->thread) { pid = task_pid_nr(napi->thread); if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid)) goto nla_put_failure; } napi_defer_hard_irqs = napi_get_defer_hard_irqs(napi); if (nla_put_s32(rsp, NETDEV_A_NAPI_DEFER_HARD_IRQS, napi_defer_hard_irqs)) goto nla_put_failure; irq_suspend_timeout = napi_get_irq_suspend_timeout(napi); if (nla_put_uint(rsp, NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, irq_suspend_timeout)) goto nla_put_failure; gro_flush_timeout = napi_get_gro_flush_timeout(napi); if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, gro_flush_timeout)) goto nla_put_failure; genlmsg_end(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) { struct napi_struct *napi; struct sk_buff *rsp; u32 napi_id; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID)) return -EINVAL; napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; rtnl_lock(); rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { err = netdev_nl_napi_fill_one(rsp, napi, info); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } rcu_read_unlock(); rtnl_unlock(); if (err) goto err_free_msg; return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); return err; } static int netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { struct napi_struct *napi; int err = 0; if (!(netdev->flags & IFF_UP)) return err; list_for_each_entry(napi, &netdev->napi_list, dev_list) { if (ctx->napi_id && napi->napi_id >= ctx->napi_id) continue; err = netdev_nl_napi_fill_one(rsp, napi, info); if (err) return err; ctx->napi_id = napi->napi_id; } return err; } int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; u32 ifindex = 0; int err = 0; if (info->attrs[NETDEV_A_NAPI_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]); rtnl_lock(); if (ifindex) { netdev = __dev_get_by_index(net, ifindex); if (netdev) err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); else err = -ENODEV; } else { for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); if (err < 0) break; ctx->napi_id = 0; } } rtnl_unlock(); return err; } static int netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info) { u64 irq_suspend_timeout = 0; u64 gro_flush_timeout = 0; u32 defer = 0; if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) { defer = nla_get_u32(info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]); napi_set_defer_hard_irqs(napi, defer); } if (info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]) { irq_suspend_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]); napi_set_irq_suspend_timeout(napi, irq_suspend_timeout); } if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) { gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]); napi_set_gro_flush_timeout(napi, gro_flush_timeout); } return 0; } int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info) { struct napi_struct *napi; unsigned int napi_id; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID)) return -EINVAL; napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); rtnl_lock(); rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { err = netdev_nl_napi_set_config(napi, info); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } rcu_read_unlock(); rtnl_unlock(); return err; } static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { struct net_devmem_dmabuf_binding *binding; struct netdev_rx_queue *rxq; struct netdev_queue *txq; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) || nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) || nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex)) goto nla_put_failure; switch (q_type) { case NETDEV_QUEUE_TYPE_RX: rxq = __netif_get_rx_queue(netdev, q_idx); if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, rxq->napi->napi_id)) goto nla_put_failure; binding = rxq->mp_params.mp_priv; if (binding && nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id)) goto nla_put_failure; break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, txq->napi->napi_id)) goto nla_put_failure; } genlmsg_end(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id, u32 q_type) { switch (q_type) { case NETDEV_QUEUE_TYPE_RX: if (q_id >= netdev->real_num_rx_queues) return -EINVAL; return 0; case NETDEV_QUEUE_TYPE_TX: if (q_id >= netdev->real_num_tx_queues) return -EINVAL; } return 0; } static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { int err = 0; if (!(netdev->flags & IFF_UP)) return err; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) return err; return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info); } int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) { u32 q_id, q_type, ifindex; struct net_device *netdev; struct sk_buff *rsp; int err; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX)) return -EINVAL; q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]); q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]); ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; rtnl_lock(); netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (netdev) err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info); else err = -ENODEV; rtnl_unlock(); if (err) goto err_free_msg; return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); return err; } static int netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { int err = 0; int i; if (!(netdev->flags & IFF_UP)) return err; for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { err = netdev_nl_queue_fill_one(rsp, netdev, i, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; ctx->rxq_idx = i++; } for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { err = netdev_nl_queue_fill_one(rsp, netdev, i, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; ctx->txq_idx = i++; } return err; } int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; u32 ifindex = 0; int err = 0; if (info->attrs[NETDEV_A_QUEUE_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); rtnl_lock(); if (ifindex) { netdev = __dev_get_by_index(net, ifindex); if (netdev) err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); else err = -ENODEV; } else { for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); if (err < 0) break; ctx->rxq_idx = 0; ctx->txq_idx = 0; } } rtnl_unlock(); return err; } #define NETDEV_STAT_NOT_SET (~0ULL) static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) { const u64 *add = _add; u64 *sum = _sum; while (size) { if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) *sum += *add; sum++; add++; size -= 8; } } static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) { if (value == NETDEV_STAT_NOT_SET) return 0; return nla_put_uint(rsp, attr_id, value); } static int netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, rx->hw_gro_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_BYTES, rx->hw_gro_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, rx->hw_gro_wire_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, rx->hw_gro_wire_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, rx->hw_drop_ratelimits)) return -EMSGSIZE; return 0; } static int netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROPS, tx->hw_drops) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, tx->hw_drop_errors) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_CSUM_NONE, tx->csum_none) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_NEEDS_CSUM, tx->needs_csum) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, tx->hw_gso_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_STOP, tx->stop) || netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_WAKE, tx->wake)) return -EMSGSIZE; return 0; } static int netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, u32 q_type, int i, const struct genl_info *info) { const struct netdev_stat_ops *ops = netdev->stat_ops; struct netdev_queue_stats_rx rx; struct netdev_queue_stats_tx tx; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) goto nla_put_failure; switch (q_type) { case NETDEV_QUEUE_TYPE_RX: memset(&rx, 0xff, sizeof(rx)); ops->get_queue_stats_rx(netdev, i, &rx); if (!memchr_inv(&rx, 0xff, sizeof(rx))) goto nla_cancel; if (netdev_nl_stats_write_rx(rsp, &rx)) goto nla_put_failure; break; case NETDEV_QUEUE_TYPE_TX: memset(&tx, 0xff, sizeof(tx)); ops->get_queue_stats_tx(netdev, i, &tx); if (!memchr_inv(&tx, 0xff, sizeof(tx))) goto nla_cancel; if (netdev_nl_stats_write_tx(rsp, &tx)) goto nla_put_failure; break; } genlmsg_end(rsp, hdr); return 0; nla_cancel: genlmsg_cancel(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static int netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { const struct netdev_stat_ops *ops = netdev->stat_ops; int i, err; if (!(netdev->flags & IFF_UP)) return 0; i = ctx->rxq_idx; while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, i, info); if (err) return err; ctx->rxq_idx = i++; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, i, info); if (err) return err; ctx->txq_idx = i++; } ctx->rxq_idx = 0; ctx->txq_idx = 0; return 0; } static int netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { struct netdev_queue_stats_rx rx_sum, rx; struct netdev_queue_stats_tx tx_sum, tx; const struct netdev_stat_ops *ops; void *hdr; int i; ops = netdev->stat_ops; /* Netdev can't guarantee any complete counters */ if (!ops->get_base_stats) return 0; memset(&rx_sum, 0xff, sizeof(rx_sum)); memset(&tx_sum, 0xff, sizeof(tx_sum)); ops->get_base_stats(netdev, &rx_sum, &tx_sum); /* The op was there, but nothing reported, don't bother */ if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) goto nla_put_failure; for (i = 0; i < netdev->real_num_rx_queues; i++) { memset(&rx, 0xff, sizeof(rx)); if (ops->get_queue_stats_rx) ops->get_queue_stats_rx(netdev, i, &rx); netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); } for (i = 0; i < netdev->real_num_tx_queues; i++) { memset(&tx, 0xff, sizeof(tx)); if (ops->get_queue_stats_tx) ops->get_queue_stats_tx(netdev, i, &tx); netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); } if (netdev_nl_stats_write_rx(rsp, &rx_sum) || netdev_nl_stats_write_tx(rsp, &tx_sum)) goto nla_put_failure; genlmsg_end(rsp, hdr); return 0; nla_put_failure: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static int netdev_nl_qstats_get_dump_one(struct net_device *netdev, unsigned int scope, struct sk_buff *skb, const struct genl_info *info, struct netdev_nl_dump_ctx *ctx) { if (!netdev->stat_ops) return 0; switch (scope) { case 0: return netdev_nl_stats_by_netdev(netdev, skb, info); case NETDEV_QSTATS_SCOPE_QUEUE: return netdev_nl_stats_by_queue(netdev, skb, info, ctx); } return -EINVAL; /* Should not happen, per netlink policy */ } int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; unsigned int ifindex; unsigned int scope; int err = 0; scope = 0; if (info->attrs[NETDEV_A_QSTATS_SCOPE]) scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); ifindex = 0; if (info->attrs[NETDEV_A_QSTATS_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_QSTATS_IFINDEX]); rtnl_lock(); if (ifindex) { netdev = __dev_get_by_index(net, ifindex); if (netdev && netdev->stat_ops) { err = netdev_nl_qstats_get_dump_one(netdev, scope, skb, info, ctx); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_QSTATS_IFINDEX]); err = netdev ? -EOPNOTSUPP : -ENODEV; } } else { for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_qstats_get_dump_one(netdev, scope, skb, info, ctx); if (err < 0) break; } } rtnl_unlock(); return err; } int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)]; struct net_devmem_dmabuf_binding *binding; struct list_head *sock_binding_list; u32 ifindex, dmabuf_fd, rxq_idx; struct net_device *netdev; struct sk_buff *rsp; struct nlattr *attr; int rem, err = 0; void *hdr; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD) || GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES)) return -EINVAL; ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); sock_binding_list = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); if (IS_ERR(sock_binding_list)) return PTR_ERR(sock_binding_list); rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) return -ENOMEM; hdr = genlmsg_iput(rsp, info); if (!hdr) { err = -EMSGSIZE; goto err_genlmsg_free; } rtnl_lock(); netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (!netdev || !netif_device_present(netdev)) { err = -ENODEV; goto err_unlock; } if (dev_xdp_prog_count(netdev)) { NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); err = -EEXIST; goto err_unlock; } binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); if (IS_ERR(binding)) { err = PTR_ERR(binding); goto err_unlock; } nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES, genlmsg_data(info->genlhdr), genlmsg_len(info->genlhdr), rem) { err = nla_parse_nested( tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr, netdev_queue_id_nl_policy, info->extack); if (err < 0) goto err_unbind; if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) || NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) { err = -EINVAL; goto err_unbind; } if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) { NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]); err = -EINVAL; goto err_unbind; } rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]); err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding, info->extack); if (err) goto err_unbind; } list_add(&binding->list, sock_binding_list); nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); genlmsg_end(rsp, hdr); err = genlmsg_reply(rsp, info); if (err) goto err_unbind; rtnl_unlock(); return 0; err_unbind: net_devmem_unbind_dmabuf(binding); err_unlock: rtnl_unlock(); err_genlmsg_free: nlmsg_free(rsp); return err; } void netdev_nl_sock_priv_init(struct list_head *priv) { INIT_LIST_HEAD(priv); } void netdev_nl_sock_priv_destroy(struct list_head *priv) { struct net_devmem_dmabuf_binding *binding; struct net_devmem_dmabuf_binding *temp; list_for_each_entry_safe(binding, temp, priv, list) { rtnl_lock(); net_devmem_unbind_dmabuf(binding); rtnl_unlock(); } } static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF); break; case NETDEV_UNREGISTER: netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF); break; case NETDEV_XDP_FEAT_CHANGE: netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF); break; } return NOTIFY_OK; } static struct notifier_block netdev_genl_nb = { .notifier_call = netdev_genl_netdevice_event, }; static int __init netdev_genl_init(void) { int err; err = register_netdevice_notifier(&netdev_genl_nb); if (err) return err; err = genl_register_family(&netdev_nl_family); if (err) goto err_unreg_ntf; return 0; err_unreg_ntf: unregister_netdevice_notifier(&netdev_genl_nb); return err; } subsys_initcall(netdev_genl_init); |
| 5 5 5 5 4 5 5 4 4 4 5 5 4 5 5 9 27 27 87 50 41 41 41 41 4 4 4 2 1 1 1 1 35 66 59 60 60 1 59 34 6 3 43 42 3 41 45 45 45 45 41 41 41 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/irqchip/arm-gic-v3.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/kstrtox.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_asm.h> #include "vgic.h" static bool group0_trap; static bool group1_trap; static bool common_trap; static bool dir_trap; static bool gicv4_enable; void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; cpuif->vgic_hcr |= ICH_HCR_UIE; } static bool lr_signals_eoi_mi(u64 lr_val) { return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) && !(lr_val & ICH_LR_HW); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; int lr; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); cpuif->vgic_hcr &= ~ICH_HCR_UIE; for (lr = 0; lr < cpuif->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; u32 intid, cpuid; struct vgic_irq *irq; bool is_v2_sgi = false; bool deactivated; cpuid = val & GICH_LR_PHYSID_CPUID; cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; if (model == KVM_DEV_TYPE_ARM_VGIC_V3) { intid = val & ICH_LR_VIRTUAL_ID_MASK; } else { intid = val & GICH_LR_VIRTUALID; is_v2_sgi = vgic_irq_is_sgi(intid); } /* Notify fds when the guest EOI'ed a level-triggered IRQ */ if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) kvm_notify_acked_irq(vcpu->kvm, 0, intid - VGIC_NR_PRIVATE_IRQS); irq = vgic_get_vcpu_irq(vcpu, intid); if (!irq) /* An LPI could have been unmapped. */ continue; raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit, note deactivation */ deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT); irq->active = !!(val & ICH_LR_ACTIVE_BIT); if (irq->active && is_v2_sgi) irq->active_source = cpuid; /* Edge is the only case where we preserve the pending bit */ if (irq->config == VGIC_CONFIG_EDGE && (val & ICH_LR_PENDING_BIT)) { irq->pending_latch = true; if (is_v2_sgi) irq->source |= (1 << cpuid); } /* * Clear soft pending state when level irqs have been acked. */ if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) irq->pending_latch = false; /* Handle resampling for mapped interrupts if required */ vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT); raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } cpuif->used_lrs = 0; } /* Requires the irq to be locked already */ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) { u32 model = vcpu->kvm->arch.vgic.vgic_model; u64 val = irq->intid; bool allow_pending = true, is_v2_sgi; is_v2_sgi = (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2); if (irq->active) { val |= ICH_LR_ACTIVE_BIT; if (is_v2_sgi) val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; if (vgic_irq_is_multi_sgi(irq)) { allow_pending = false; val |= ICH_LR_EOI; } } if (irq->hw && !vgic_irq_needs_resampling(irq)) { val |= ICH_LR_HW; val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT; /* * Never set pending+active on a HW interrupt, as the * pending state is kept at the physical distributor * level. */ if (irq->active) allow_pending = false; } else { if (irq->config == VGIC_CONFIG_LEVEL) { val |= ICH_LR_EOI; /* * Software resampling doesn't work very well * if we allow P+A, so let's not do that. */ if (irq->active) allow_pending = false; } } if (allow_pending && irq_is_pending(irq)) { val |= ICH_LR_PENDING_BIT; if (irq->config == VGIC_CONFIG_EDGE) irq->pending_latch = false; if (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2) { u32 src = ffs(irq->source); if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", irq->intid)) return; val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; irq->source &= ~(1 << (src - 1)); if (irq->source) { irq->pending_latch = true; val |= ICH_LR_EOI; } } } /* * Level-triggered mapped IRQs are special because we only observe * rising edges as input to the VGIC. We therefore lower the line * level here, so that we can take new virtual IRQs. See * vgic_v3_fold_lr_state for more info. */ if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) irq->line_level = false; if (irq->group) val |= ICH_LR_GROUP; val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT; vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val; } void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr) { vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0; } void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) & ICH_VMCR_ACK_CTL_MASK; vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) & ICH_VMCR_FIQ_EN_MASK; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcr = ICH_VMCR_FIQ_EN_MASK; } vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK; vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK; vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK; vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK; cpu_if->vgic_vmcr = vmcr; } void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; vmcr = cpu_if->vgic_vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >> ICH_VMCR_ACK_CTL_SHIFT; vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >> ICH_VMCR_FIQ_EN_SHIFT; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcrp->fiqen = 1; vmcrp->ackctl = 0; } vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT; vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; vmcrp->grpen0 = (vmcr & ICH_VMCR_ENG0_MASK) >> ICH_VMCR_ENG0_SHIFT; vmcrp->grpen1 = (vmcr & ICH_VMCR_ENG1_MASK) >> ICH_VMCR_ENG1_SHIFT; } #define INITIAL_PENDBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)) void vgic_v3_enable(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; /* * By forcing VMCR to zero, the GIC will restore the binary * points to their reset values. Anything else resets to zero * anyway. */ vgic_v3->vgic_vmcr = 0; /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; } vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_ID_BITS_MASK) >> ICH_VTR_ID_BITS_SHIFT; vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_PRI_BITS_MASK) >> ICH_VTR_PRI_BITS_SHIFT) + 1; /* Get the show on the road... */ vgic_v3->vgic_hcr = ICH_HCR_EN; } void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; /* Hide GICv3 sysreg if necessary */ if (!kvm_has_gicv3(vcpu->kvm)) { vgic_v3->vgic_hcr |= ICH_HCR_TALL0 | ICH_HCR_TALL1 | ICH_HCR_TC; return; } if (group0_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL0; if (group1_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL1; if (common_trap) vgic_v3->vgic_hcr |= ICH_HCR_TC; if (dir_trap) vgic_v3->vgic_hcr |= ICH_HCR_TDIR; } int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) { struct kvm_vcpu *vcpu; int byte_offset, bit_nr; gpa_t pendbase, ptr; bool status; u8 val; int ret; unsigned long flags; retry: vcpu = irq->target_vcpu; if (!vcpu) return 0; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; status = val & (1 << bit_nr); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu != vcpu) { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); goto retry; } irq->pending_latch = status; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } return 0; } /* * The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ static void unmap_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); } static void map_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), dist->its_vm.vpes[i]->irq)); } /* * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; gpa_t last_ptr = ~(gpa_t)0; bool vlpi_avail = false; unsigned long index; int ret = 0; u8 val; if (unlikely(!vgic_initialized(kvm))) return -ENXIO; /* * A preparation for getting any VLPI states. * The above vgic initialized check also ensures that the allocation * and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { unmap_all_vpes(kvm); vlpi_avail = true; } xa_for_each(&dist->lpi_xa, index, irq) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; bool is_pending; bool stored; vcpu = irq->target_vcpu; if (!vcpu) continue; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; last_ptr = ptr; } stored = val & (1U << bit_nr); is_pending = irq->pending_latch; if (irq->hw && vlpi_avail) vgic_v4_get_vlpi_state(irq, &is_pending); if (stored == is_pending) continue; if (is_pending) val |= 1 << bit_nr; else val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } out: if (vlpi_avail) map_all_vpes(kvm); return ret; } /** * vgic_v3_rdist_overlap - check if a region overlaps with any * existing redistributor region * * @kvm: kvm handle * @base: base of the region * @size: size of region * * Return: true if there is an overlap */ bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, &d->rd_regions, list) { if ((base + size > rdreg->base) && (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) return true; } return false; } /* * Check for overlapping regions and for regions crossing the end of memory * for base addresses which have already been set. */ bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; list_for_each_entry(rdreg, &d->rd_regions, list) { size_t sz = vgic_v3_rd_region_size(kvm, rdreg); if (vgic_check_iorange(kvm, VGIC_ADDR_UNDEF, rdreg->base, SZ_64K, sz)) return false; } if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) return true; return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, KVM_VGIC_V3_DIST_SIZE); } /** * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one * which has free space to put a new rdist region. * * @rd_regions: redistributor region list head * * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). * Stride between redistributors is 0 and regions are filled in the index order. * * Return: the redist region handle, if any, that has space to map a new rdist * region. */ struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) { struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (!vgic_v3_redist_region_full(rdreg)) return rdreg; } return NULL; } struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index) { struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (rdreg->index == index) return rdreg; } return NULL; } int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_debug("Need to set vgic distributor addresses first\n"); return -ENXIO; } if (!vgic_v3_check_base(kvm)) { kvm_debug("VGIC redist and dist frames overlap\n"); return -EINVAL; } /* * For a VGICv3 we require the userland to explicitly initialize * the VGIC before we need to use it. */ if (!vgic_initialized(kvm)) { return -EBUSY; } if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); static int __init early_group0_trap_cfg(char *buf) { return kstrtobool(buf, &group0_trap); } early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); static int __init early_group1_trap_cfg(char *buf) { return kstrtobool(buf, &group1_trap); } early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); static int __init early_common_trap_cfg(char *buf) { return kstrtobool(buf, &common_trap); } early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); static int __init early_gicv4_enable(char *buf) { return kstrtobool(buf, &gicv4_enable); } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; static bool vgic_v3_broken_seis(void) { return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && is_midr_in_range_list(read_cpuid_id(), broken_seis)); } /** * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller * @info: pointer to the GIC description * * Returns 0 if the VGICv3 has been probed successfully, returns an error code * otherwise */ int vgic_v3_probe(const struct gic_kvm_info *info) { u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config); bool has_v2; int ret; has_v2 = ich_vtr_el2 >> 63; ich_vtr_el2 = (u32)ich_vtr_el2; /* * The ListRegs field is 5 bits, but there is an architectural * maximum of 16 list registers. Just ignore bit 4... */ kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1; kvm_vgic_global_state.can_emulate_gicv2 = false; kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2; /* GICv4 support? */ if (info->has_v4) { kvm_vgic_global_state.has_gicv4 = gicv4_enable; kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; kvm_info("GICv4%s support %sabled\n", kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", gicv4_enable ? "en" : "dis"); } kvm_vgic_global_state.vcpu_base = 0; if (!info->vcpu.start) { kvm_info("GICv3: no GICV resource entry\n"); } else if (!has_v2) { pr_warn(FW_BUG "CPU interface incapable of MMIO access\n"); } else if (!PAGE_ALIGNED(info->vcpu.start)) { pr_warn("GICV physical address 0x%llx not page aligned\n", (unsigned long long)info->vcpu.start); } else if (kvm_get_mode() != KVM_MODE_PROTECTED) { kvm_vgic_global_state.vcpu_base = info->vcpu.start; kvm_vgic_global_state.can_emulate_gicv2 = true; ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); if (ret) { kvm_err("Cannot register GICv2 KVM device.\n"); return ret; } kvm_info("vgic-v2@%llx\n", info->vcpu.start); } ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) { kvm_err("Cannot register GICv3 KVM device.\n"); kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2); return ret; } if (kvm_vgic_global_state.vcpu_base == 0) kvm_info("disabling GICv2 emulation\n"); if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_30115)) { group0_trap = true; group1_trap = true; } if (vgic_v3_broken_seis()) { kvm_info("GICv3 with broken locally generated SEI\n"); kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; group0_trap = true; group1_trap = true; if (ich_vtr_el2 & ICH_VTR_TDS_MASK) dir_trap = true; else common_trap = true; } if (group0_trap || group1_trap || common_trap | dir_trap) { kvm_info("GICv3 sysreg trapping enabled ([%s%s%s%s], reduced performance)\n", group0_trap ? "G0" : "", group1_trap ? "G1" : "", common_trap ? "C" : "", dir_trap ? "D" : ""); static_branch_enable(&vgic_v3_cpuif_trap); } kvm_vgic_global_state.vctrl_base = NULL; kvm_vgic_global_state.type = VGIC_V3; kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; return 0; } void vgic_v3_load(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); if (has_vhe()) __vgic_v3_activate_traps(cpu_if); WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); WARN_ON(vgic_v4_put(vcpu)); if (has_vhe()) __vgic_v3_deactivate_traps(cpu_if); } |
| 216 25 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * 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 THE AUTHORS OR COPYRIGHT HOLDERS * 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 "ipoib.h" #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> /* For ARPHRD_xxx */ #include <linux/ip.h> #include <linux/in.h> #include <linux/jhash.h> #include <net/arp.h> #include <net/addrconf.h> #include <net/pkt_sched.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; module_param_named(send_queue_size, ipoib_sendq_size, int, 0444); MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue"); module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444); MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue"); #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG int ipoib_debug_level; module_param_named(debug_level, ipoib_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); #endif struct ipoib_path_iter { struct net_device *dev; struct ipoib_path path; }; static const u8 ipv4_bcast_addr[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0x12, 0x40, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff }; struct workqueue_struct *ipoib_workqueue; struct ib_sa_client ipoib_sa_client; static int ipoib_add_one(struct ib_device *device); static void ipoib_remove_one(struct ib_device *device, void *client_data); static void ipoib_neigh_reclaim(struct rcu_head *rp); static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); static int ipoib_set_mac(struct net_device *dev, void *addr); static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static struct ib_client ipoib_client = { .name = "ipoib", .add = ipoib_add_one, .remove = ipoib_remove_one, .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static int ipoib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *ni = ptr; struct net_device *dev = ni->dev; if (dev->netdev_ops->ndo_open != ipoib_open) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: ipoib_create_debug_files(dev); break; case NETDEV_CHANGENAME: ipoib_delete_debug_files(dev); ipoib_create_debug_files(dev); break; case NETDEV_UNREGISTER: ipoib_delete_debug_files(dev); break; } return NOTIFY_DONE; } #endif int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); netif_carrier_off(dev); set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; } ipoib_ib_dev_up(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (flags & IFF_UP) continue; dev_change_flags(cpriv->dev, flags | IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } else if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &ppriv->flags)) ipoib_dbg(priv, "parent device %s is not up, so child device may be not functioning.\n", ppriv->dev->name); } netif_start_queue(dev); return 0; err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); return -EINVAL; } static int ipoib_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); netif_stop_queue(dev); ipoib_ib_dev_down(dev); ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (!(flags & IFF_UP)) continue; dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } return 0; } static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { if (new_mtu > ipoib_cm_max_mtu(dev)) return -EINVAL; if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); WRITE_ONCE(dev->mtu, new_mtu); return 0; } if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) || new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu)) return -EINVAL; priv->admin_mtu = new_mtu; if (priv->mcast_mtu < priv->admin_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); new_mtu = min(priv->mcast_mtu, priv->admin_mtu); if (priv->rn_ops->ndo_change_mtu) { bool carrier_status = netif_carrier_ok(dev); netif_carrier_off(dev); /* notify lower level on the real mtu */ ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); if (carrier_status) netif_carrier_on(dev); } else { WRITE_ONCE(dev->mtu, new_mtu); } return ret; } static void ipoib_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->rn_ops->ndo_get_stats64) priv->rn_ops->ndo_get_stats64(dev, stats); else netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr, struct net_device *dev) { struct net *net = dev_net(dev); struct in_device *in_dev; struct sockaddr_in *addr_in = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr; __be32 ret_addr; switch (addr->sa_family) { case AF_INET: in_dev = in_dev_get(dev); if (!in_dev) return false; ret_addr = inet_confirm_addr(net, in_dev, 0, addr_in->sin_addr.s_addr, RT_SCOPE_HOST); in_dev_put(in_dev); if (ret_addr) return true; break; case AF_INET6: if (IS_ENABLED(CONFIG_IPV6) && ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1)) return true; break; } return false; } /* * Find the master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the master net_device with a reference held, or the same net_device * if no master exists. */ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); dev_hold(master); rcu_read_unlock(); if (master) return master; dev_hold(dev); return dev; } struct ipoib_walk_data { const struct sockaddr *addr; struct net_device *result; }; static int ipoib_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { dev_hold(upper); data->result = upper; ret = 1; } return ret; } /** * ipoib_get_net_dev_match_addr - Find a net_device matching * the given address, which is an upper device of the given net_device. * * @addr: IP address to look for. * @dev: base IPoIB net_device * * If found, returns the net_device with a reference held. Otherwise return * NULL. */ static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); data.result = dev; goto out; } netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; } /* returns the number of IPoIB netdevs on top a given ipoib device matching a * pkey_index and address, if one exists. * * @found_net_dev: contains a matching net_device if the return value >= 1, * with a reference held. */ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv, const union ib_gid *gid, u16 pkey_index, const struct sockaddr *addr, int nesting, struct net_device **found_net_dev) { struct ipoib_dev_priv *child_priv; struct net_device *net_dev = NULL; int matches = 0; if (priv->pkey_index == pkey_index && (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) { if (!addr) { net_dev = ipoib_get_master_net_dev(priv->dev); } else { /* Verify the net_device matches the IP address, as * IPoIB child devices currently share a GID. */ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev); } if (net_dev) { if (!*found_net_dev) *found_net_dev = net_dev; else dev_put(net_dev); ++matches; } } /* Check child interfaces */ down_read_nested(&priv->vlan_rwsem, nesting); list_for_each_entry(child_priv, &priv->child_intfs, list) { matches += ipoib_match_gid_pkey_addr(child_priv, gid, pkey_index, addr, nesting + 1, found_net_dev); if (matches > 1) break; } up_read(&priv->vlan_rwsem); return matches; } /* Returns the number of matching net_devs found (between 0 and 2). Also * return the matching net_device in the @net_dev parameter, holding a * reference to the net_device, if the number of matches >= 1 */ static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u32 port, u16 pkey_index, const union ib_gid *gid, const struct sockaddr *addr, struct net_device **net_dev) { struct ipoib_dev_priv *priv; int matches = 0; *net_dev = NULL; list_for_each_entry(priv, dev_list, list) { if (priv->port != port) continue; matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index, addr, 0, net_dev); if (matches > 1) break; } return matches; } static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data) { struct net_device *net_dev; struct list_head *dev_list = client_data; u16 pkey_index; int matches; int ret; if (!rdma_protocol_ib(dev, port)) return NULL; ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index); if (ret) return NULL; /* See if we can find a unique device matching the L2 parameters */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, NULL, &net_dev); switch (matches) { case 0: return NULL; case 1: return net_dev; } dev_put(net_dev); /* Couldn't find a unique device with L2 parameters only. Use L3 * address to uniquely match the net device */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, addr, &net_dev); switch (matches) { case 0: return NULL; default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); fallthrough; case 1: return net_dev; } } int ipoib_set_mode(struct net_device *dev, const char *buf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "datagram\n"))) { return 0; } /* flush paths if we switch modes so that connections are restarted */ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) { set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_update_features(dev); dev_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); rtnl_unlock(); priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); netdev_update_features(dev); dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); rtnl_unlock(); ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; } struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; while (n) { path = rb_entry(n, struct ipoib_path, rb_node); ret = memcmp(gid, path->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = n->rb_left; else if (ret > 0) n = n->rb_right; else return path; } return NULL; } static int __path_add(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; int ret; while (*n) { pn = *n; tpath = rb_entry(pn, struct ipoib_path, rb_node); ret = memcmp(path->pathrec.dgid.raw, tpath->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = &pn->rb_left; else if (ret > 0) n = &pn->rb_right; else return -EEXIST; } rb_link_node(&path->rb_node, pn, n); rb_insert_color(&path->rb_node, &priv->path_tree); list_add_tail(&path->list, &priv->path_list); return 0; } static void path_free(struct net_device *dev, struct ipoib_path *path) { struct sk_buff *skb; while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); ipoib_dbg(ipoib_priv(dev), "%s\n", __func__); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (path->ah) ipoib_put_ah(path->ah); kfree(path); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) { struct ipoib_path_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; iter->dev = dev; memset(iter->path.pathrec.dgid.raw, 0, 16); if (ipoib_path_iter_next(iter)) { kfree(iter); return NULL; } return iter; } int ipoib_path_iter_next(struct ipoib_path_iter *iter) { struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; spin_lock_irq(&priv->lock); n = rb_first(&priv->path_tree); while (n) { path = rb_entry(n, struct ipoib_path, rb_node); if (memcmp(iter->path.pathrec.dgid.raw, path->pathrec.dgid.raw, sizeof (union ib_gid)) < 0) { iter->path = *path; ret = 0; break; } n = rb_next(n); } spin_unlock_irq(&priv->lock); return ret; } void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path) { *path = iter->path; } #endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */ void ipoib_mark_paths_invalid(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec)), path->pathrec.dgid.raw); if (path->ah) path->ah->valid = 0; } spin_unlock_irq(&priv->lock); } static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; phdr = skb_push(skb, sizeof(*phdr)); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); } void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->path_list, &remove_list); list_for_each_entry(path, &remove_list, list) rb_erase(&path->rb_node, &priv->path_tree); list_for_each_entry_safe(path, tp, &remove_list, list) { if (path->query) ib_sa_cancel_query(path->query_id, path->query); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); wait_for_completion(&path->done); path_free(dev, path); netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); } spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); } static void path_rec_completion(int status, struct sa_path_rec *pathrec, unsigned int num_prs, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; struct sk_buff_head skqueue; struct sk_buff *skb; unsigned long flags; if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); skb_queue_head_init(&skqueue); if (!status) { struct rdma_ah_attr av; if (!ib_init_ah_attr_from_path(priv->ca, priv->port, pathrec, &av, NULL)) { ah = ipoib_create_ah(dev, priv->pd, &av); rdma_destroy_ah_attr(&av); } } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { /* * pathrec.dgid is used as the database key from the LLADDR, * it must remain unchanged even if the SA returns a different * GID to use in the AH. */ if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid))) { ipoib_dbg( priv, "%s got PathRec for gid %pI6 while asked for %pI6\n", dev->name, pathrec->dgid.raw, path->pathrec.dgid.raw); memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid)); } path->pathrec = *pathrec; old_ah = path->ah; path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", ah, be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) { if (neigh->ah) { WARN_ON(neigh->ah != old_ah); /* * Dropping the ah reference inside * priv->lock is safe here, because we * will hold one more reference from * the original value of path->ah (ie * old_ah). */ ipoib_put_ah(neigh->ah); } kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); continue; } } while ((skb = __skb_dequeue(&neigh->queue))) __skb_queue_tail(&skqueue, skb); } path->ah->valid = 1; } path->query = NULL; complete(&path->done); spin_unlock_irqrestore(&priv->lock, flags); if (IS_ERR_OR_NULL(ah)) ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (old_ah) ipoib_put_ah(old_ah); while ((skb = __skb_dequeue(&skqueue))) { int ret; skb->dev = dev; ret = dev_queue_xmit(skb); if (ret) ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n", __func__, ret); } } static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, void *gid) { path->dev = priv->dev; if (rdma_cap_opa_ah(priv->ca, priv->port)) path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; else path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; } static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) return NULL; path = kzalloc(sizeof(*path), GFP_ATOMIC); if (!path) return NULL; skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); init_path_rec(priv, path, gid); return path; } static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); init_completion(&path->done); path->query_id = ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port, &path->pathrec, IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_TRAFFIC_CLASS | IB_SA_PATH_REC_PKEY, 1000, GFP_ATOMIC, path_rec_completion, path, &path->query); if (path->query_id < 0) { ipoib_warn(priv, "ib_sa_path_rec_get failed: %d\n", path->query_id); path->query = NULL; complete(&path->done); return path->query_id; } return 0; } static void neigh_refresh_path(struct ipoib_neigh *neigh, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); path = __path_find(dev, daddr + 4); if (!path) goto out; if (!path->query) path_rec_start(dev, path); out: spin_unlock_irqrestore(&priv->lock, flags); } static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NULL; } /* To avoid race condition, make sure that the * neigh will be added only once. */ if (unlikely(!list_empty(&neigh->list))) { spin_unlock_irqrestore(&priv->lock, flags); return neigh; } path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); if (!path) goto err_path; __path_add(dev, path); } list_add_tail(&neigh->list, &path->neigh_list); if (path->ah && path->ah->valid) { kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); goto err_drop; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; } } else { spin_unlock_irqrestore(&priv->lock, flags); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return NULL; } } else { neigh->ah = NULL; if (!path->query && path_rec_start(dev, path)) goto err_path; if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { goto err_drop; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; err_path: ipoib_neigh_free(neigh); err_drop: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); /* no broadcast means that all paths are (going to be) not valid */ if (!priv->broadcast) goto drop_and_unlock; path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->ah || !path->ah->valid) { if (!path) { path = path_rec_create(dev, phdr->hwaddr + 4); if (!path) goto drop_and_unlock; __path_add(dev, path); } else { /* * make sure there are no changes in the existing * path record */ init_path_rec(priv, path, phdr->hwaddr + 4); } if (!path->query && path_rec_start(dev, path)) { goto drop_and_unlock; } if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); goto unlock; } else { goto drop_and_unlock; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_dbg(priv, "Send unicast ARP to %08x\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec))); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(phdr->hwaddr)); return; drop_and_unlock: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); unlock: spin_unlock_irqrestore(&priv->lock, flags); } static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; phdr = (struct ipoib_pseudo_header *) skb->data; skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && (header->proto != htons(ETH_P_ARP)) && (header->proto != htons(ETH_P_RARP)) && (header->proto != htons(ETH_P_TIPC))) { /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; phdr->hwaddr[9] = priv->pkey & 0xff; neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } /* unicast, arrange "switch" according to probability */ switch (header->proto) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { neigh = neigh_add_path(skb, phdr->hwaddr, dev); if (likely(!neigh)) return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } send_using_neigh: /* note we now hold a ref to neigh */ if (ipoib_cm_get(neigh)) { if (ipoib_cm_up(neigh)) { ipoib_cm_send(dev, skb, ipoib_cm_get(neigh)); goto unref; } } else if (neigh->ah && neigh->ah->valid) { neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } else if (neigh->ah) { neigh_refresh_path(neigh, phdr->hwaddr, dev); } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } unref: ipoib_neigh_put(neigh); return NETDEV_TX_OK; } static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); if (rn->tx_timeout) { rn->tx_timeout(dev, txqueue); return; } ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, priv->global_tx_head, priv->global_tx_tail); schedule_work(&priv->tx_timeout_work); } void ipoib_ib_tx_timeout_work(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, tx_timeout_work); int err; rtnl_lock(); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) goto unlock; ipoib_stop(priv->dev); err = ipoib_open(priv->dev); if (err) { ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n", err); goto unlock; } netif_tx_wake_all_queues(priv->dev); unlock: rtnl_unlock(); } static int ipoib_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ipoib_header *header; header = skb_push(skb, sizeof(*header)); header->proto = htons(type); header->reserved = 0; /* * we don't rely on dst_entry structure, always stuff the * destination address into skb hard header so we can figure out where * to send the packet later. */ push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); return; } queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return READ_ONCE(dev->ifindex); /* child/vlan interface */ return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) { /* * Use only the address parts that contributes to spreading * The subnet prefix is not used as one can not connect to * same remote port (GUID) using the same remote QPN via two * different subnets. */ /* qpn octets[1:4) & port GUID octets[12:20) */ u32 *d32 = (u32 *) daddr; u32 hv; hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0); return hv & htbl->mask; } struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; u32 hash_val; rcu_read_lock_bh(); htbl = rcu_dereference_bh(ntbl->htbl); if (!htbl) goto out_unlock; hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]); neigh != NULL; neigh = rcu_dereference_bh(neigh->hnext)) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; goto out_unlock; } if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) neigh->alive = jiffies; goto out_unlock; } } out_unlock: rcu_read_unlock_bh(); return neigh; } static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long neigh_obsolete; unsigned long dt; unsigned long flags; int i; LIST_HEAD(remove_list); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; /* neigh is obsolete if it was idle for two GC periods */ dt = 2 * arp_tbl.gc_interval; neigh_obsolete = jiffies - dt; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { ipoib_check_and_add_mcast_sendonly(priv, neigh->daddr + 4, &remove_list); rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); ipoib_mcast_remove_list(&remove_list); } static void ipoib_reap_neigh(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, neigh_reap_task.work); __ipoib_reap_neigh(priv); queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct net_device *dev) { struct ipoib_neigh *neigh; neigh = kzalloc(sizeof(*neigh), GFP_ATOMIC); if (!neigh) return NULL; neigh->dev = dev; memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr)); skb_queue_head_init(&neigh->queue); INIT_LIST_HEAD(&neigh->list); ipoib_cm_set(neigh, NULL); /* one ref on behalf of the caller */ refcount_set(&neigh->refcnt, 1); return neigh; } struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; } /* need to add a new neigh, but maybe some other thread succeeded? * recalc hash, maybe hash resize took place so we do a search */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; break; } neigh->alive = jiffies; goto out_unlock; } } neigh = ipoib_neigh_ctor(daddr, dev); if (!neigh) goto out_unlock; /* one ref on behalf of the hash table */ refcount_inc(&neigh->refcnt); neigh->alive = jiffies; /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: return neigh; } void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); while ((skb = __skb_dequeue(&neigh->queue))) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); kfree(neigh); if (atomic_dec_and_test(&priv->ntbl.entries)) { if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags)) complete(&priv->ntbl.flushed); } } static void ipoib_neigh_reclaim(struct rcu_head *rp) { /* Called as a result of removal from hash table */ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu); /* note TX context may hold another ref */ ipoib_neigh_put(neigh); } void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; struct ipoib_neigh *n; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); return; } else { np = &n->hnext; } } } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **buckets; u32 size; clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; size = roundup_pow_of_two(arp_tbl.gc_thresh3); buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL); if (!buckets) { kfree(htbl); return -ENOMEM; } htbl->size = size; htbl->mask = (size - 1); htbl->buckets = buckets; RCU_INIT_POINTER(ntbl->htbl, htbl); htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct ipoib_neigh_hash *htbl = container_of(head, struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; struct ipoib_neigh_table *ntbl = htbl->ntbl; kvfree(buckets); kfree(htbl); complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i; /* remove all neigh connected to a given path or mcast */ spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; wait_flushed = atomic_read(&priv->ntbl.entries); if (!wait_flushed) goto free_htbl; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: spin_unlock_irqrestore(&priv->lock, flags); if (wait_flushed) wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "%s\n", __func__); init_completion(&priv->ntbl.deleted); cancel_delayed_work_sync(&priv->neigh_reap_task); ipoib_flush_neighs(priv); wait_for_completion(&priv->ntbl.deleted); } static void ipoib_napi_add(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_add_weight(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); netif_napi_add_weight(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); } static void ipoib_napi_del(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_del(&priv->recv_napi); netif_napi_del(&priv->send_napi); } static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); kfree(priv->rx_ring); vfree(priv->tx_ring); priv->rx_ring = NULL; priv->tx_ring = NULL; } static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); u8 addr_mod[3]; ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kcalloc(ipoib_recvq_size, sizeof(*priv->rx_ring), GFP_KERNEL); if (!priv->rx_ring) goto out; priv->tx_ring = vzalloc(array_size(ipoib_sendq_size, sizeof(*priv->tx_ring))); if (!priv->tx_ring) { pr_warn("%s: failed to allocate TX ring (%d entries)\n", priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", priv->ca->name); goto out_tx_ring_cleanup; } /* after qp created set dev address */ addr_mod[0] = (priv->qp->qp_num >> 16) & 0xff; addr_mod[1] = (priv->qp->qp_num >> 8) & 0xff; addr_mod[2] = (priv->qp->qp_num) & 0xff; dev_addr_mod(priv->dev, 1, addr_mod, sizeof(addr_mod)); return 0; out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); out: ipoib_napi_del(dev); return -ENOMEM; } static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = -ENOMEM; priv->qp = NULL; /* * the various IPoIB tasks assume they will never race against * themselves, so always use a single thread workqueue */ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); if (!priv->wq) { pr_warn("%s: failed to allocate device WQ\n", dev->name); goto out; } /* create pd, which used both for control and datapath*/ priv->pd = ib_alloc_pd(priv->ca, 0); if (IS_ERR(priv->pd)) { pr_warn("%s: failed to allocate PD\n", priv->ca->name); goto clean_wq; } ret = priv->rn_ops->ndo_init(dev); if (ret) { pr_warn("%s failed to init HW resource\n", dev->name); goto out_free_pd; } ret = ipoib_neigh_hash_init(priv); if (ret) { pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; } if (dev->flags & IFF_UP) { if (ipoib_ib_dev_open(dev)) { pr_warn("%s failed to open device\n", dev->name); ret = -ENODEV; goto out_hash_uninit; } } return 0; out_hash_uninit: ipoib_neigh_hash_uninit(dev); out_dev_uninit: ipoib_ib_dev_cleanup(dev); out_free_pd: if (priv->pd) { ib_dealloc_pd(priv->pd); priv->pd = NULL; } clean_wq: if (priv->wq) { destroy_workqueue(priv->wq); priv->wq = NULL; } out: return ret; } /* * This must be called before doing an unregister_netdev on a parent device to * shutdown the IB event handler. */ static void ipoib_parent_unregister_pre(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); /* * ipoib_set_mac checks netif_running before pushing work, clearing * running ensures the it will not add more work. */ rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL); rtnl_unlock(); /* ipoib_event() cannot be running once this returns */ ib_unregister_event_handler(&priv->event_handler); /* * Work on the queue grabs the rtnl lock, so this cannot be done while * also holding it. */ flush_workqueue(ipoib_workqueue); } static void ipoib_set_dev_features(struct ipoib_dev_priv *priv) { priv->hca_caps = priv->ca->attrs.device_cap_flags; priv->kernel_caps = priv->ca->attrs.kernel_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->kernel_caps & IBK_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; priv->dev->features |= priv->dev->hw_features; } } static int ipoib_parent_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ib_port_attr attr; int result; result = ib_query_port(priv->ca, priv->port, &attr); if (result) { pr_warn("%s: ib_query_port %d failed\n", priv->ca->name, priv->port); return result; } priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr); result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey); if (result) { pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid); if (result) { pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } dev_addr_mod(priv->dev, 4, priv->local_gid.raw, sizeof(union ib_gid)); SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent); priv->dev->dev_port = priv->port - 1; /* Let's set this one too for backwards compatibility. */ priv->dev->dev_id = priv->port - 1; return 0; } static void ipoib_child_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) memcpy(&priv->local_gid, priv->dev->dev_addr + 4, sizeof(priv->local_gid)); else { __dev_addr_set(priv->dev, ppriv->dev->dev_addr, INFINIBAND_ALEN); memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); } } static int ipoib_ndo_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); int rc; struct rdma_netdev *rn = netdev_priv(ndev); if (priv->parent) { ipoib_child_init(ndev); } else { rc = ipoib_parent_init(ndev); if (rc) return rc; } /* MTU will be reset when mcast join happens */ ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = ndev->mtu; rn->mtu = priv->mcast_mtu; ndev->max_mtu = IPOIB_CM_MTU; ndev->neigh_priv_len = sizeof(struct ipoib_neigh); /* * Set the full membership bit, so that we join the right * broadcast group, etc. */ priv->pkey |= 0x8000; ndev->broadcast[8] = priv->pkey >> 8; ndev->broadcast[9] = priv->pkey & 0xff; set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); ipoib_set_dev_features(priv); rc = ipoib_dev_init(ndev); if (rc) { pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n", priv->ca->name, priv->dev->name, priv->port, rc); return rc; } if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); dev_hold(priv->parent); down_write(&ppriv->vlan_rwsem); list_add_tail(&priv->list, &ppriv->child_intfs); up_write(&ppriv->vlan_rwsem); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ASSERT_RTNL(); /* * ipoib_remove_one guarantees the children are removed before the * parent, and that is the only place where a parent can be removed. */ WARN_ON(!list_empty(&priv->child_intfs)); if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); down_write(&ppriv->vlan_rwsem); list_del(&priv->list); up_write(&ppriv->vlan_rwsem); } ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); /* no more works over the priv->wq */ if (priv->wq) { /* See ipoib_mcast_carrier_on_task() */ WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); destroy_workqueue(priv->wq); priv->wq = NULL; } dev_put(priv->parent); } static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } static int ipoib_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); if (err) return err; ivf->vf = vf; memcpy(ivf->mac, dev->dev_addr, dev->addr_len); return 0; } static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); } static int ipoib_get_vf_guid(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid); } static int ipoib_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_get_vf_guid = ipoib_get_vf_guid, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_init = ipoib_dev_init_default, .ndo_uninit = ipoib_dev_uninit_default, .ndo_open = ipoib_ib_dev_open_default, .ndo_stop = ipoib_ib_dev_stop_default, }; void ipoib_setup_common(struct net_device *dev) { dev->header_ops = &ipoib_header_ops; dev->netdev_ops = &ipoib_netdev_default_pf; ipoib_set_ethtool_ops(dev); dev->watchdog_timeo = 10 * HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->features = (NETIF_F_VLAN_CHALLENGED | NETIF_F_HIGHDMA); netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); /* * unregister_netdev always frees the netdev, we use this mode * consistently to unify all the various unregister paths, including * those connected to rtnl_link_ops which require it. */ dev->needs_free_netdev = true; } static void ipoib_build_priv(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); INIT_LIST_HEAD(&priv->dead_ahs); INIT_LIST_HEAD(&priv->multicast_list); INIT_DELAYED_WORK(&priv->mcast_task, ipoib_mcast_join_task); INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task); INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work); INIT_WORK(&priv->flush_light, ipoib_ib_dev_flush_light); INIT_WORK(&priv->flush_normal, ipoib_ib_dev_flush_normal); INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy); INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task); INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work); INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah); INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) return dev; dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!dev) return ERR_PTR(-ENOMEM); return dev; } int ipoib_intf_init(struct ib_device *hca, u32 port, const char *name, struct net_device *dev) { struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->ca = hca; priv->port = port; rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common, dev); if (rc) { if (rc != -EOPNOTSUPP) goto out; rn->send = ipoib_send; rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; rc = netif_set_real_num_tx_queues(dev, 1); if (rc) goto out; rc = netif_set_real_num_rx_queues(dev, 1); if (rc) goto out; } priv->rn_ops = dev->netdev_ops; if (hca->attrs.kernel_cap_flags & IBK_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; rn->clnt_priv = priv; /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it * is safe to turn on. */ priv->next_priv_destructor = dev->priv_destructor; dev->priv_destructor = NULL; ipoib_build_priv(dev); return 0; out: kfree(priv); return rc; } struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; int rc; dev = ipoib_alloc_netdev(hca, port, name); if (IS_ERR(dev)) return dev; rc = ipoib_intf_init(hca, port, name, dev); if (rc) { free_netdev(dev); return ERR_PTR(rc); } /* * Upon success the caller must ensure ipoib_intf_free is called or * register_netdevice succeed'd and priv_destructor is set to * ipoib_intf_free. */ return dev; } void ipoib_intf_free(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); dev->priv_destructor = priv->next_priv_destructor; if (dev->priv_destructor) dev->priv_destructor(dev); /* * There are some error flows around register_netdev failing that may * attempt to call priv_destructor twice, prevent that from happening. */ dev->priv_destructor = NULL; /* unregister/destroy is very complicated. Make bugs more obvious. */ rn->clnt_priv = NULL; kfree(priv); } static ssize_t pkey_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "0x%04x\n", priv->pkey); } static DEVICE_ATTR_RO(pkey); static ssize_t umcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); ipoib_warn(priv, "ignoring multicast groups joined directly " "by userspace\n"); } else clear_bit(IPOIB_FLAG_UMCAST, &priv->flags); } static ssize_t umcast_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long umcast_val = simple_strtoul(buf, NULL, 0); ipoib_set_umcast(to_net_dev(dev), umcast_val); return count; } static DEVICE_ATTR_RW(umcast); int ipoib_add_umcast_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_umcast); } static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) { struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, sizeof(gid->global.interface_id)); dev_addr_mod(netdev, 4, (u8 *)&priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { down_read(&priv->vlan_rwsem); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); up_read(&priv->vlan_rwsem); } } static int ipoib_check_lladdr(struct net_device *dev, struct sockaddr_storage *ss) { union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. */ if (memcmp(dev->dev_addr, ss->__data, 4 + sizeof(gid->global.subnet_prefix)) || gid->global.interface_id == 0) ret = -EINVAL; netif_addr_unlock_bh(dev); return ret; } static int ipoib_set_mac(struct net_device *dev, void *addr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; ret = ipoib_check_lladdr(dev, ss); if (ret) return ret; set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); queue_work(ipoib_workqueue, &priv->flush_light); return 0; } static ssize_t create_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) return -EINVAL; ret = ipoib_vlan_add(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(create_child); static ssize_t delete_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey < 0 || pkey > 0xffff) return -EINVAL; ret = ipoib_vlan_delete(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(delete_child); int ipoib_add_pkey_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_pkey); } /* * We erroneously exposed the iface's port number in the dev_id * sysfs field long after dev_port was introduced for that purpose[1], * and we need to stop everyone from relying on that. * Let's overload the shower routine for the dev_id file here * to gently bring the issue up. * * [1] https://www.spinics.net/lists/netdev/msg272123.html */ static ssize_t dev_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); /* * ndev->dev_port will be equal to 0 in old kernel prior to commit * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface * port numbers") Zero was chosen as special case for user space * applications to fallback and query dev_id to check if it has * different value or not. * * Don't print warning in such scenario. * * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358 */ if (ndev->dev_port && ndev->dev_id == ndev->dev_port) netdev_info_once(ndev, "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n", current->comm); return sysfs_emit(buf, "%#x\n", ndev->dev_id); } static DEVICE_ATTR_RO(dev_id); static int ipoib_intercept_dev_id_attr(struct net_device *dev) { device_remove_file(&dev->dev, &dev_attr_dev_id); return device_create_file(&dev->dev, &dev_attr_dev_id); } static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u32 port) { struct rtnl_link_ops *ops = ipoib_get_link_ops(); struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; ndev = ipoib_intf_alloc(hca, port, format); if (IS_ERR(ndev)) { pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, PTR_ERR(ndev)); return ndev; } priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler); /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); ndev->rtnl_link_ops = ipoib_get_link_ops(); result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", hca->name, port, result); ipoib_parent_unregister_pre(ndev); ipoib_intf_free(ndev); free_netdev(ndev); return ERR_PTR(result); } if (hca->ops.rdma_netdev_get_params) { int rc = hca->ops.rdma_netdev_get_params(hca, port, RDMA_NETDEV_IPOIB, ¶ms); if (!rc && ops->priv_size < params.sizeof_priv) ops->priv_size = params.sizeof_priv; } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute * ipoib_parent_unregister_pre(). Instead handle it manually and only * enter priv_destructor mode once we are completely registered. */ ndev->priv_destructor = ipoib_intf_free; if (ipoib_intercept_dev_id_attr(ndev)) goto sysfs_failed; if (ipoib_cm_add_mode_attr(ndev)) goto sysfs_failed; if (ipoib_add_pkey_attr(ndev)) goto sysfs_failed; if (ipoib_add_umcast_attr(ndev)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_create_child)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_delete_child)) goto sysfs_failed; return ndev; sysfs_failed: ipoib_parent_unregister_pre(ndev); unregister_netdev(ndev); return ERR_PTR(-ENOMEM); } static int ipoib_add_one(struct ib_device *device) { struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; unsigned int p; int count = 0; dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL); if (!dev_list) return -ENOMEM; INIT_LIST_HEAD(dev_list); rdma_for_each_port (device, p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } } if (!count) { kfree(dev_list); return -EOPNOTSUPP; } ib_set_client_data(device, &ipoib_client, dev_list); return 0; } static void ipoib_remove_one(struct ib_device *device, void *client_data) { struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv; struct list_head *dev_list = client_data; list_for_each_entry_safe(priv, tmp, dev_list, list) { LIST_HEAD(head); ipoib_parent_unregister_pre(priv->dev); rtnl_lock(); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); unregister_netdevice_queue(priv->dev, &head); unregister_netdevice_many(&head); rtnl_unlock(); } kfree(dev_list); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static struct notifier_block ipoib_netdev_notifier = { .notifier_call = ipoib_netdev_event, }; #endif static int __init ipoib_init_module(void) { int ret; ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size); ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE); ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* * When copying small received packets, we only copy from the * linear data part of the SKB, so we rely on this condition. */ BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE); ipoib_register_debugfs(); /* * We create a global workqueue here that is used for all flush * operations. However, if you attempt to flush a workqueue * from a task on that same workqueue, it deadlocks the system. * We want to be able to flush the tasks associated with a * specific net device, so we also create a workqueue for each * netdevice. We queue up the tasks for that device only on * its private workqueue, and we only queue up flush events * on our global flush workqueue. This avoids the deadlocks. */ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; } ib_sa_register_client(&ipoib_sa_client); ret = ib_register_client(&ipoib_client); if (ret) goto err_sa; ret = ipoib_netlink_init(); if (ret) goto err_client; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG register_netdevice_notifier(&ipoib_netdev_notifier); #endif return 0; err_client: ib_unregister_client(&ipoib_client); err_sa: ib_sa_unregister_client(&ipoib_sa_client); destroy_workqueue(ipoib_workqueue); err_fs: ipoib_unregister_debugfs(); return ret; } static void __exit ipoib_cleanup_module(void) { #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG unregister_netdevice_notifier(&ipoib_netdev_notifier); #endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); ipoib_unregister_debugfs(); destroy_workqueue(ipoib_workqueue); } module_init(ipoib_init_module); module_exit(ipoib_cleanup_module); |
| 1224 750 167 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 Huawei Ltd. * Author: Jiang Liu <liuj97@gmail.com> * * Based on arch/arm/include/asm/jump_label.h */ #ifndef __ASM_JUMP_LABEL_H #define __ASM_JUMP_LABEL_H #ifndef __ASSEMBLY__ #include <linux/types.h> #include <asm/insn.h> #define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE #define JUMP_TABLE_ENTRY(key, label) \ ".pushsection __jump_table, \"aw\"\n\t" \ ".align 3\n\t" \ ".long 1b - ., " label " - .\n\t" \ ".quad " key " - .\n\t" \ ".popsection\n\t" /* This macro is also expanded on the Rust side. */ #define ARCH_STATIC_BRANCH_ASM(key, label) \ "1: nop\n\t" \ JUMP_TABLE_ENTRY(key, label) static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { char *k = &((char *)key)[branch]; asm goto( ARCH_STATIC_BRANCH_ASM("%c0", "%l[l_yes]") : : "i"(k) : : l_yes ); return false; l_yes: return true; } static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { char *k = &((char *)key)[branch]; asm goto( "1: b %l[l_yes] \n\t" JUMP_TABLE_ENTRY("%c0", "%l[l_yes]") : : "i"(k) : : l_yes ); return false; l_yes: return true; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_JUMP_LABEL_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); for_each_process_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 29 362 24 178 1 35 371 372 372 372 129 225 167 17 75 18 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/khugepaged.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/pagewalk.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> /* Internal core VMA manipulation functions. */ #include "vma.h" struct folio_batch; /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ static inline int mmap_file(struct file *file, struct vm_area_struct *vma) { int err = call_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we most not invoke * any further hooks on it. */ vma->vm_ops = &vma_dummy_vm_ops; return err; } /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ static inline void vma_close(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &vma_dummy_vm_ops; } } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */ #define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */ #define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (flags & FPB_IGNORE_DIRTY) pte = pte_mkclean(pte); if (likely(flags & FPB_IGNORE_SOFT_DIRTY)) pte = pte_clear_soft_dirty(pte); return pte_wrprotect(pte_mkold(pte)); } /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @addr: The user virtual address the first page is mapped at. * @start_ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. * @any_dirty: Optional pointer to indicate whether any entry except the * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY). * * start_ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; if (any_dirty) *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; while (ptep < end_ptep) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); if (any_dirty) dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) break; /* * Stop immediately once we reached the end of the folio. In * corner cases the next PFN might fall into a different * folio. */ if (pte_pfn(pte) >= folio_end_pfn) break; if (any_writable) *any_writable |= writable; if (any_young) *any_young |= young; if (any_dirty) *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); ptep += nr; } return min(ptep - start_ptep, max_nr); } /** * pte_move_swp_offset - Move the swap entry offset field of a swap pte * forward or backward by delta * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * @delta: The direction and the offset we are moving; forward if delta * is positive; backward if delta is negative * * Moves the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_move_swp_offset(pte_t pte, long delta) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + delta))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { return pte_move_swp_offset(pte, 1); } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; swp_entry_t entry = pte_to_swp_entry(pte); pte_t *ptep = start_ptep + 1; unsigned short cgroup_id; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(entry)); cgroup_id = lookup_swap_cgroup_id(entry); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; if (lookup_swap_cgroup_id(pte_to_swp_entry(pte)) != cgroup_id) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { vm_fault_t ret = __vmf_anon_prepare(vmf); if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vmf->vma); return ret; } vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order, enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef CONFIG_64BIT folio->_folio_nr_pages = 1U << order; #endif } bool __folio_unqueue_deferred_split(struct folio *folio); static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) return false; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return false; return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; void free_unref_page(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end, int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* mm/util.c */ struct anon_vma *folio_anon_vma(const struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(const struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif /* * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu); void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; #define MAGIC_HWPOISON 0x48575053U /* HWPS */ void SetPageHWPoisonTakenOff(struct page *page); void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); unsigned long page_mapped_in_vma(const struct page *page, struct vm_area_struct *vma); #else static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) { } #endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); struct folio *alloc_migrate_folio(struct folio *src, unsigned long private); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller); /* * mm/gup.c */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); static inline bool alloc_zeroed(void) { return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc); } /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. */ static inline int get_order_from_str(const char *size_str, unsigned long valid_orders) { unsigned long size; char *endptr; int order; size = memparse(size_str, &endptr); if (!is_power_of_2(size)) return -EINVAL; order = get_order(size); if (BIT(order) & ~valid_orders) return -EINVAL; return order; } enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; extern bool memblock_has_mirror(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { if (flags) return -EINVAL; return 0; } #else static inline int can_do_mseal(unsigned long flags) { return -EPERM; } #endif #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks, bool for_stack); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { } #endif /* CONFIG_UNACCEPTED_MEMORY */ /* pagewalk.c */ int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); #endif /* __MM_INTERNAL_H */ |
| 1 16 16 16 15 1 16 101 10 | 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * * This driver produces cryptographically secure pseudorandom data. It is divided * into roughly six sections, each with a section header: * * - Initialization and readiness waiting. * - Fast key erasure RNG, the "crng". * - Entropy accumulation and extraction routines. * - Entropy collection routines. * - Userspace reader/writer interfaces. * - Sysctl interface. * * The high level overview is that there is one input pool, into which * various pieces of data are hashed. Prior to initialization, some of that * data is then "credited" as having a certain number of bits of entropy. * When enough bits of entropy are available, the hash is finalized and * handed as a key to a stream cipher that expands it indefinitely for * various consumers. This key is periodically refreshed as the various * entropy collectors, described below, add data to the input pool. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/utsname.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/nodemask.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/percpu.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/suspend.h> #include <linux/siphash.h> #include <linux/sched/isolation.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> #ifdef CONFIG_VDSO_GETRANDOM #include <vdso/getrandom.h> #include <vdso/datapage.h> #include <vdso/vsyscall.h> #endif #include <asm/archrandom.h> #include <asm/processor.h> #include <asm/irq.h> #include <asm/irq_regs.h> #include <asm/io.h> /********************************************************************* * * Initialization and readiness waiting. * * Much of the RNG infrastructure is devoted to various dependencies * being able to wait until the RNG has collected enough entropy and * is ready for safe consumption. * *********************************************************************/ /* * crng_init is protected by base_crng->lock, and only increases * its value (from empty->early->ready). */ static enum { CRNG_EMPTY = 0, /* Little to no entropy collected */ CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */ CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */ } crng_init __read_mostly = CRNG_EMPTY; static DEFINE_STATIC_KEY_FALSE(crng_is_ready); #define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY) /* Various types of waiters for crng_init->CRNG_READY transition. */ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); static struct fasync_struct *fasync; static ATOMIC_NOTIFIER_HEAD(random_ready_notifier); /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); /* * Returns whether or not the input pool has been seeded and thus guaranteed * to supply cryptographically secure random numbers. This applies to: the * /dev/urandom device, the get_random_bytes function, and the get_random_{u8, * u16,u32,u64,long} family of functions. * * Returns: true if the input pool has been seeded. * false if the input pool has not been seeded. */ bool rng_is_initialized(void) { return crng_ready(); } EXPORT_SYMBOL(rng_is_initialized); static void __cold crng_set_ready(struct work_struct *work) { static_branch_enable(&crng_is_ready); } /* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ static void try_to_generate_entropy(void); /* * Wait for the input pool to be seeded and thus guaranteed to supply * cryptographically secure random numbers. This applies to: the /dev/urandom * device, the get_random_bytes function, and the get_random_{u8,u16,u32,u64, * long} family of functions. Using any of these functions without first * calling this function forfeits the guarantee of security. * * Returns: 0 if the input pool has been seeded. * -ERESTARTSYS if the function was interrupted by a signal. */ int wait_for_random_bytes(void) { while (!crng_ready()) { int ret; try_to_generate_entropy(); ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ); if (ret) return ret > 0 ? 0 : ret; } return 0; } EXPORT_SYMBOL(wait_for_random_bytes); /* * Add a callback function that will be invoked when the crng is initialised, * or immediately if it already has been. Only use this is you are absolutely * sure it is required. Most users should instead be able to test * `rng_is_initialized()` on demand, or make use of `get_random_bytes_wait()`. */ int __cold execute_with_initialized_rng(struct notifier_block *nb) { unsigned long flags; int ret = 0; spin_lock_irqsave(&random_ready_notifier.lock, flags); if (crng_ready()) nb->notifier_call(nb, 0, NULL); else ret = raw_notifier_chain_register((struct raw_notifier_head *)&random_ready_notifier.head, nb); spin_unlock_irqrestore(&random_ready_notifier.lock, flags); return ret; } #define warn_unseeded_randomness() \ if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \ printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \ __func__, (void *)_RET_IP_, crng_init) /********************************************************************* * * Fast key erasure RNG, the "crng". * * These functions expand entropy from the entropy extractor into * long streams for external consumption using the "fast key erasure" * RNG described at <https://blog.cr.yp.to/20170723-random.html>. * * There are a few exported interfaces for use by other drivers: * * void get_random_bytes(void *buf, size_t len) * u8 get_random_u8() * u16 get_random_u16() * u32 get_random_u32() * u32 get_random_u32_below(u32 ceil) * u32 get_random_u32_above(u32 floor) * u32 get_random_u32_inclusive(u32 floor, u32 ceil) * u64 get_random_u64() * unsigned long get_random_long() * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to * a read from /dev/urandom. The u8, u16, u32, u64, long family of * functions may be higher performance for one-off random integers, * because they do a bit of buffering and do not invoke reseeding * until the buffer is emptied. * *********************************************************************/ enum { CRNG_RESEED_START_INTERVAL = HZ, CRNG_RESEED_INTERVAL = 60 * HZ }; static struct { u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long)); unsigned long generation; spinlock_t lock; } base_crng = { .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock) }; struct crng { u8 key[CHACHA_KEY_SIZE]; unsigned long generation; local_lock_t lock; }; static DEFINE_PER_CPU(struct crng, crngs) = { .generation = ULONG_MAX, .lock = INIT_LOCAL_LOCK(crngs.lock), }; /* * Return the interval until the next reseeding, which is normally * CRNG_RESEED_INTERVAL, but during early boot, it is at an interval * proportional to the uptime. */ static unsigned int crng_reseed_interval(void) { static bool early_boot = true; if (unlikely(READ_ONCE(early_boot))) { time64_t uptime = ktime_get_seconds(); if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2) WRITE_ONCE(early_boot, false); else return max_t(unsigned int, CRNG_RESEED_START_INTERVAL, (unsigned int)uptime / 2 * HZ); } return CRNG_RESEED_INTERVAL; } /* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */ static void extract_entropy(void *buf, size_t len); /* This extracts a new crng key from the input pool. */ static void crng_reseed(struct work_struct *work) { static DECLARE_DELAYED_WORK(next_reseed, crng_reseed); unsigned long flags; unsigned long next_gen; u8 key[CHACHA_KEY_SIZE]; /* Immediately schedule the next reseeding, so that it fires sooner rather than later. */ if (likely(system_unbound_wq)) queue_delayed_work(system_unbound_wq, &next_reseed, crng_reseed_interval()); extract_entropy(key, sizeof(key)); /* * We copy the new key into the base_crng, overwriting the old one, * and update the generation counter. We avoid hitting ULONG_MAX, * because the per-cpu crngs are initialized to ULONG_MAX, so this * forces new CPUs that come online to always initialize. */ spin_lock_irqsave(&base_crng.lock, flags); memcpy(base_crng.key, key, sizeof(base_crng.key)); next_gen = base_crng.generation + 1; if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); #ifdef CONFIG_VDSO_GETRANDOM /* base_crng.generation's invalid value is ULONG_MAX, while * _vdso_rng_data.generation's invalid value is 0, so add one to the * former to arrive at the latter. Use smp_store_release so that this * is ordered with the write above to base_crng.generation. Pairs with * the smp_rmb() before the syscall in the vDSO code. * * Cast to unsigned long for 32-bit architectures, since atomic 64-bit * operations are not supported on those architectures. This is safe * because base_crng.generation is a 32-bit value. On big-endian * architectures it will be stored in the upper 32 bits, but that's okay * because the vDSO side only checks whether the value changed, without * actually using or interpreting the value. */ smp_store_release((unsigned long *)&__arch_get_k_vdso_rng_data()->generation, next_gen + 1); #endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); memzero_explicit(key, sizeof(key)); } /* * This generates a ChaCha block using the provided key, and then * immediately overwrites that key with half the block. It returns * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. * * The returned ChaCha state contains within it a copy of the old * key value, at index 4, so the state should always be zeroed out * immediately after using in order to maintain forward secrecy. * If the state cannot be erased in a timely manner, then it is * safer to set the random_data parameter to &chacha_state[4] so * that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], u32 chacha_state[CHACHA_STATE_WORDS], u8 *random_data, size_t random_data_len) { u8 first_block[CHACHA_BLOCK_SIZE]; BUG_ON(random_data_len > 32); chacha_init_consts(chacha_state); memcpy(&chacha_state[4], key, CHACHA_KEY_SIZE); memset(&chacha_state[12], 0, sizeof(u32) * 4); chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } /* * This function returns a ChaCha state that you may use for generating * random data. It also returns up to 32 bytes on its own of random data * that may be used; random_data_len may not be greater than 32. */ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], u8 *random_data, size_t random_data_len) { unsigned long flags; struct crng *crng; BUG_ON(random_data_len > 32); /* * For the fast path, we check whether we're ready, unlocked first, and * then re-check once locked later. In the case where we're really not * ready, we do fast key erasure with the base_crng directly, extracting * when crng_init is CRNG_EMPTY. */ if (!crng_ready()) { bool ready; spin_lock_irqsave(&base_crng.lock, flags); ready = crng_ready(); if (!ready) { if (crng_init == CRNG_EMPTY) extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_fast_key_erasure(base_crng.key, chacha_state, random_data, random_data_len); } spin_unlock_irqrestore(&base_crng.lock, flags); if (!ready) return; } local_lock_irqsave(&crngs.lock, flags); crng = raw_cpu_ptr(&crngs); /* * If our per-cpu crng is older than the base_crng, then it means * somebody reseeded the base_crng. In that case, we do fast key * erasure on the base_crng, and use its output as the new key * for our per-cpu crng. This brings us up to date with base_crng. */ if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) { spin_lock(&base_crng.lock); crng_fast_key_erasure(base_crng.key, chacha_state, crng->key, sizeof(crng->key)); crng->generation = base_crng.generation; spin_unlock(&base_crng.lock); } /* * Finally, when we've made it this far, our per-cpu crng has an up * to date key, and we can do fast key erasure with it to produce * some random data and a ChaCha state for the caller. All other * branches of this function are "unlikely", so most of the time we * should wind up here immediately. */ crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len); local_unlock_irqrestore(&crngs.lock, flags); } static void _get_random_bytes(void *buf, size_t len) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 tmp[CHACHA_BLOCK_SIZE]; size_t first_block_len; if (!len) return; first_block_len = min_t(size_t, 32, len); crng_make_state(chacha_state, buf, first_block_len); len -= first_block_len; buf += first_block_len; while (len) { if (len < CHACHA_BLOCK_SIZE) { chacha20_block(chacha_state, tmp); memcpy(buf, tmp, len); memzero_explicit(tmp, sizeof(tmp)); break; } chacha20_block(chacha_state, buf); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; len -= CHACHA_BLOCK_SIZE; buf += CHACHA_BLOCK_SIZE; } memzero_explicit(chacha_state, sizeof(chacha_state)); } /* * This returns random bytes in arbitrary quantities. The quality of the * random bytes is good as /dev/urandom. In order to ensure that the * randomness provided by this function is okay, the function * wait_for_random_bytes() should be called and return 0 at least once * at any point prior. */ void get_random_bytes(void *buf, size_t len) { warn_unseeded_randomness(); _get_random_bytes(buf, len); } EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(struct iov_iter *iter) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 block[CHACHA_BLOCK_SIZE]; size_t ret = 0, copied; if (unlikely(!iov_iter_count(iter))) return 0; /* * Immediately overwrite the ChaCha key at index 4 with random * bytes, in case userspace causes copy_to_iter() below to sleep * forever, so that we still retain forward secrecy in that case. */ crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); /* * However, if we're doing a read of len <= 32, we don't need to * use chacha_state after, so we can simply return those bytes to * the user directly. */ if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) { ret = copy_to_iter(&chacha_state[4], CHACHA_KEY_SIZE, iter); goto out_zero_chacha; } for (;;) { chacha20_block(chacha_state, block); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; copied = copy_to_iter(block, sizeof(block), iter); ret += copied; if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); out_zero_chacha: memzero_explicit(chacha_state, sizeof(chacha_state)); return ret ? ret : -EFAULT; } /* * Batched entropy returns random integers. The quality of the random * number is good as /dev/urandom. In order to ensure that the randomness * provided by this function is okay, the function wait_for_random_bytes() * should be called and return 0 at least once at any point prior. */ #define DEFINE_BATCHED_ENTROPY(type) \ struct batch_ ##type { \ /* \ * We make this 1.5x a ChaCha block, so that we get the \ * remaining 32 bytes from fast key erasure, plus one full \ * block from the detached ChaCha state. We can increase \ * the size of this later if needed so long as we keep the \ * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \ */ \ type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \ local_lock_t lock; \ unsigned long generation; \ unsigned int position; \ }; \ \ static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \ .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \ .position = UINT_MAX \ }; \ \ type get_random_ ##type(void) \ { \ type ret; \ unsigned long flags; \ struct batch_ ##type *batch; \ unsigned long next_gen; \ \ warn_unseeded_randomness(); \ \ if (!crng_ready()) { \ _get_random_bytes(&ret, sizeof(ret)); \ return ret; \ } \ \ local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \ batch = raw_cpu_ptr(&batched_entropy_##type); \ \ next_gen = READ_ONCE(base_crng.generation); \ if (batch->position >= ARRAY_SIZE(batch->entropy) || \ next_gen != batch->generation) { \ _get_random_bytes(batch->entropy, sizeof(batch->entropy)); \ batch->position = 0; \ batch->generation = next_gen; \ } \ \ ret = batch->entropy[batch->position]; \ batch->entropy[batch->position] = 0; \ ++batch->position; \ local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \ return ret; \ } \ EXPORT_SYMBOL(get_random_ ##type); DEFINE_BATCHED_ENTROPY(u8) DEFINE_BATCHED_ENTROPY(u16) DEFINE_BATCHED_ENTROPY(u32) DEFINE_BATCHED_ENTROPY(u64) u32 __get_random_u32_below(u32 ceil) { /* * This is the slow path for variable ceil. It is still fast, most of * the time, by doing traditional reciprocal multiplication and * opportunistically comparing the lower half to ceil itself, before * falling back to computing a larger bound, and then rejecting samples * whose lower half would indicate a range indivisible by ceil. The use * of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable * in 32-bits. */ u32 rand = get_random_u32(); u64 mult; /* * This function is technically undefined for ceil == 0, and in fact * for the non-underscored constant version in the header, we build bug * on that. But for the non-constant case, it's convenient to have that * evaluate to being a straight call to get_random_u32(), so that * get_random_u32_inclusive() can work over its whole range without * undefined behavior. */ if (unlikely(!ceil)) return rand; mult = (u64)ceil * rand; if (unlikely((u32)mult < ceil)) { u32 bound = -ceil % ceil; while (unlikely((u32)mult < bound)) mult = (u64)ceil * get_random_u32(); } return mult >> 32; } EXPORT_SYMBOL(__get_random_u32_below); #ifdef CONFIG_SMP /* * This function is called when the CPU is coming up, with entry * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP. */ int __cold random_prepare_cpu(unsigned int cpu) { /* * When the cpu comes back online, immediately invalidate both * the per-cpu crng and all batches, so that we serve fresh * randomness. */ per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX; per_cpu_ptr(&batched_entropy_u8, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX; return 0; } #endif /********************************************************************** * * Entropy accumulation and extraction routines. * * Callers may add entropy via: * * static void mix_pool_bytes(const void *buf, size_t len) * * After which, if added entropy should be credited: * * static void credit_init_bits(size_t bits) * * Finally, extract entropy via: * * static void extract_entropy(void *buf, size_t len) * **********************************************************************/ enum { POOL_BITS = BLAKE2S_HASH_SIZE * 8, POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */ POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */ }; static struct { struct blake2s_state hash; spinlock_t lock; unsigned int init_bits; } input_pool = { .hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE), BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4, BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 }, .hash.outlen = BLAKE2S_HASH_SIZE, .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), }; static void _mix_pool_bytes(const void *buf, size_t len) { blake2s_update(&input_pool.hash, buf, len); } /* * This function adds bytes into the input pool. It does not * update the initialization bit counter; the caller should call * credit_init_bits if this is appropriate. */ static void mix_pool_bytes(const void *buf, size_t len) { unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } /* * This is an HKDF-like construction for using the hashed collected entropy * as a PRF key, that's then expanded block-by-block. */ static void extract_entropy(void *buf, size_t len) { unsigned long flags; u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE]; struct { unsigned long rdseed[32 / sizeof(long)]; size_t counter; } block; size_t i, longs; for (i = 0; i < ARRAY_SIZE(block.rdseed);) { longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } block.rdseed[i++] = random_get_entropy(); } spin_lock_irqsave(&input_pool.lock, flags); /* seed = HASHPRF(last_key, entropy_input) */ blake2s_final(&input_pool.hash, seed); /* next_key = HASHPRF(seed, RDSEED || 0) */ block.counter = 0; blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed)); blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key)); spin_unlock_irqrestore(&input_pool.lock, flags); memzero_explicit(next_key, sizeof(next_key)); while (len) { i = min_t(size_t, len, BLAKE2S_HASH_SIZE); /* output = HASHPRF(seed, RDSEED || ++counter) */ ++block.counter; blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed)); len -= i; buf += i; } memzero_explicit(seed, sizeof(seed)); memzero_explicit(&block, sizeof(block)); } #define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) static void __cold _credit_init_bits(size_t bits) { static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; if (!bits) return; add = min_t(size_t, bits, POOL_BITS); orig = READ_ONCE(input_pool.init_bits); do { new = min_t(unsigned int, POOL_BITS, orig + add); } while (!try_cmpxchg(&input_pool.init_bits, &orig, new)); if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); #ifdef CONFIG_VDSO_GETRANDOM WRITE_ONCE(__arch_get_k_vdso_rng_data()->is_ready, true); #endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); if (urandom_warning.missed) pr_notice("%d urandom warning(s) missed due to ratelimiting\n", urandom_warning.missed); } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) { spin_lock_irqsave(&base_crng.lock, flags); /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */ if (crng_init == CRNG_EMPTY) { extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_init = CRNG_EARLY; } spin_unlock_irqrestore(&base_crng.lock, flags); } } /********************************************************************** * * Entropy collection routines. * * The following exported functions are used for pushing entropy into * the above entropy accumulation routines: * * void add_device_randomness(const void *buf, size_t len); * void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after); * void add_bootloader_randomness(const void *buf, size_t len); * void add_vmfork_randomness(const void *unique_vm_id, size_t len); * void add_interrupt_randomness(int irq); * void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); * void add_disk_randomness(struct gendisk *disk); * * add_device_randomness() adds data to the input pool that * is likely to differ between two devices (or possibly even per boot). * This would be things like MAC addresses or serial numbers, or the * read-out of the RTC. This does *not* credit any actual entropy to * the pool, but it initializes the pool to different values for devices * that might otherwise be identical and have very little entropy * available to them (particularly common in the embedded world). * * add_hwgenerator_randomness() is for true hardware RNGs, and will credit * entropy as specified by the caller. If the entropy pool is full it will * block until more entropy is needed. * * add_bootloader_randomness() is called by bootloader drivers, such as EFI * and device tree, and credits its input depending on whether or not the * command line option 'random.trust_bootloader'. * * add_vmfork_randomness() adds a unique (but not necessarily secret) ID * representing the current instance of a VM to the pool, without crediting, * and then force-reseeds the crng so that it takes effect immediately. * * add_interrupt_randomness() uses the interrupt timing as random * inputs to the entropy pool. Using the cycle counters and the irq source * as inputs, it feeds the input pool roughly once a second or after 64 * interrupts, crediting 1 bit of entropy for whichever comes first. * * add_input_randomness() uses the input layer interrupt timing, as well * as the event type information from the hardware. * * add_disk_randomness() uses what amounts to the seek time of block * layer request events, on a per-disk_devt basis, as input to the * entropy pool. Note that high-speed solid state drives with very low * seek times do not make for good sources of entropy, as their seek * times are usually fairly consistent. * * The last two routines try to estimate how many bits of entropy * to credit. They do this by keeping track of the first and second * order deltas of the event timings. * **********************************************************************/ static bool trust_cpu __initdata = true; static bool trust_bootloader __initdata = true; static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); } static int __init parse_trust_bootloader(char *arg) { return kstrtobool(arg, &trust_bootloader); } early_param("random.trust_cpu", parse_trust_cpu); early_param("random.trust_bootloader", parse_trust_bootloader); static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { unsigned long flags, entropy = random_get_entropy(); /* * Encode a representation of how long the system has been suspended, * in a way that is distinct from prior system suspends. */ ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&action, sizeof(action)); _mix_pool_bytes(stamps, sizeof(stamps)); _mix_pool_bytes(&entropy, sizeof(entropy)); spin_unlock_irqrestore(&input_pool.lock, flags); if (crng_ready() && (action == PM_RESTORE_PREPARE || (action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && !IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) { crng_reseed(NULL); pr_notice("crng reseeded on system resumption\n"); } return 0; } static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; /* * This is called extremely early, before time keeping functionality is * available, but arch randomness is. Interrupts are not yet enabled. */ void __init random_init_early(const char *command_line) { unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)]; size_t i, longs, arch_bits; #if defined(LATENT_ENTROPY_PLUGIN) static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) { longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } arch_bits -= sizeof(*entropy) * 8; ++i; } _mix_pool_bytes(init_utsname(), sizeof(*(init_utsname()))); _mix_pool_bytes(command_line, strlen(command_line)); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); else if (trust_cpu) _credit_init_bits(arch_bits); } /* * This is called a little bit after the prior function, and now there is * access to timestamps counters. Interrupts are not yet enabled. */ void __init random_init(void) { unsigned long entropy = random_get_entropy(); ktime_t now = ktime_get_real(); _mix_pool_bytes(&now, sizeof(now)); _mix_pool_bytes(&entropy, sizeof(entropy)); add_latent_entropy(); /* * If we were initialized by the cpu or bootloader before jump labels * or workqueues are initialized, then we should enable the static * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); WARN_ON(register_pm_notifier(&pm_notifier)); WARN(!entropy, "Missing cycle counter and fallback timer; RNG " "entropy collection will consequently suffer."); } /* * Add device- or boot-specific data to the input pool to help * initialize it. * * None of this adds any entropy; it is meant to avoid the problem of * the entropy pool having similar initial state across largely * identical devices. */ void add_device_randomness(const void *buf, size_t len) { unsigned long entropy = random_get_entropy(); unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); /* * Interface for in-kernel drivers of true hardware RNGs. Those devices * may produce endless random bits, so this function will sleep for * some amount of time after, if the sleep_after parameter is true. */ void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after) { mix_pool_bytes(buf, len); credit_init_bits(entropy); /* * Throttle writing to once every reseed interval, unless we're not yet * initialized or no entropy is credited. */ if (sleep_after && !kthread_should_stop() && (crng_ready() || !entropy)) schedule_timeout_interruptible(crng_reseed_interval()); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); /* * Handle random seed passed by bootloader, and credit it depending * on the command line option 'random.trust_bootloader'. */ void __init add_bootloader_randomness(const void *buf, size_t len) { mix_pool_bytes(buf, len); if (trust_bootloader) credit_init_bits(len * 8); } #if IS_ENABLED(CONFIG_VMGENID) static BLOCKING_NOTIFIER_HEAD(vmfork_chain); /* * Handle a new unique VM ID, which is unique, not secret, so we * don't credit it, but we do immediately force a reseed after so * that it's used by the crng posthaste. */ void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) { add_device_randomness(unique_vm_id, len); if (crng_ready()) { crng_reseed(NULL); pr_notice("crng reseeded due to virtual machine fork\n"); } blocking_notifier_call_chain(&vmfork_chain, 0, NULL); } #if IS_MODULE(CONFIG_VMGENID) EXPORT_SYMBOL_GPL(add_vmfork_randomness); #endif int __cold register_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier); #endif struct fast_pool { unsigned long pool[4]; unsigned long last; unsigned int count; struct timer_list mix; }; static void mix_interrupt_randomness(struct timer_list *work); static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { #ifdef CONFIG_64BIT #define FASTMIX_PERM SIPHASH_PERMUTATION .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }, #else #define FASTMIX_PERM HSIPHASH_PERMUTATION .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }, #endif .mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0) }; /* * This is [Half]SipHash-1-x, starting from an empty key. Because * the key is fixed, it assumes that its inputs are non-malicious, * and therefore this has no security on its own. s represents the * four-word SipHash state, while v represents a two-word input. */ static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { s[3] ^= v1; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v1; s[3] ^= v2; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v2; } #ifdef CONFIG_SMP /* * This function is called when the CPU has just come online, with * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ int __cold random_online_cpu(unsigned int cpu) { /* * During CPU shutdown and before CPU onlining, add_interrupt_ * randomness() may schedule mix_interrupt_randomness(), and * set the MIX_INFLIGHT flag. However, because the worker can * be scheduled on a different CPU during this period, that * flag will never be cleared. For that reason, we zero out * the flag here, which runs just after workqueues are onlined * for the CPU again. This also has the effect of setting the * irq randomness count to zero so that new accumulated irqs * are fresh. */ per_cpu_ptr(&irq_randomness, cpu)->count = 0; return 0; } #endif static void mix_interrupt_randomness(struct timer_list *work) { struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix); /* * The size of the copied stack pool is explicitly 2 longs so that we * only ever ingest half of the siphash output each time, retaining * the other half as the next "key" that carries over. The entropy is * supposed to be sufficiently dispersed between bits so on average * we don't wind up "losing" some. */ unsigned long pool[2]; unsigned int count; /* Check to see if we're running on the wrong CPU due to hotplug. */ local_irq_disable(); if (fast_pool != this_cpu_ptr(&irq_randomness)) { local_irq_enable(); return; } /* * Copy the pool to the stack so that the mixer always has a * consistent view, before we reenable irqs again. */ memcpy(pool, fast_pool->pool, sizeof(pool)); count = fast_pool->count; fast_pool->count = 0; fast_pool->last = jiffies; local_irq_enable(); mix_pool_bytes(pool, sizeof(pool)); credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8)); memzero_explicit(pool, sizeof(pool)); } void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; unsigned long entropy = random_get_entropy(); struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; fast_mix(fast_pool->pool, entropy, (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq)); new_count = ++fast_pool->count; if (new_count & MIX_INFLIGHT) return; if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ)) return; fast_pool->count |= MIX_INFLIGHT; if (!timer_pending(&fast_pool->mix)) { fast_pool->mix.expires = jiffies; add_timer_on(&fast_pool->mix, raw_smp_processor_id()); } } EXPORT_SYMBOL_GPL(add_interrupt_randomness); /* There is one of these per entropy source */ struct timer_rand_state { unsigned long last_time; long last_delta, last_delta2; }; /* * This function adds entropy to the entropy "pool" by using timing * delays. It uses the timer_rand_state structure to make an estimate * of how many bits of entropy this call has added to the pool. The * value "num" is also added to the pool; it should somehow describe * the type of event that just happened. */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { unsigned long entropy = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; unsigned int bits; /* * If we're in a hard IRQ, add_interrupt_randomness() will be called * sometime after, so mix into the fast pool. */ if (in_hardirq()) { fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num); } else { spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(&num, sizeof(num)); spin_unlock_irqrestore(&input_pool.lock, flags); } if (crng_ready()) return; /* * Calculate number of bits of randomness we probably added. * We take into account the first, second and third-order deltas * in order to make our estimate. */ delta = now - READ_ONCE(state->last_time); WRITE_ONCE(state->last_time, now); delta2 = delta - READ_ONCE(state->last_delta); WRITE_ONCE(state->last_delta, delta); delta3 = delta2 - READ_ONCE(state->last_delta2); WRITE_ONCE(state->last_delta2, delta2); if (delta < 0) delta = -delta; if (delta2 < 0) delta2 = -delta2; if (delta3 < 0) delta3 = -delta3; if (delta > delta2) delta = delta2; if (delta > delta3) delta = delta3; /* * delta is now minimum absolute delta. Round down by 1 bit * on general principles, and limit entropy estimate to 11 bits. */ bits = min(fls(delta >> 1), 11); /* * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness() * will run after this, which uses a different crediting scheme of 1 bit * per every 64 interrupts. In order to let that function do accounting * close to the one in this function, we credit a full 64/64 bit per bit, * and then subtract one to account for the extra one added. */ if (in_hardirq()) this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1; else _credit_init_bits(bits); } void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) { static unsigned char last_value; static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; /* Ignore autorepeat and the like. */ if (value == last_value) return; last_value = value; add_timer_randomness(&input_timer_state, (type << 4) ^ code ^ (code >> 4) ^ value); } EXPORT_SYMBOL_GPL(add_input_randomness); #ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) return; /* First major is 1, so we get >= 0x200 here. */ add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); } EXPORT_SYMBOL_GPL(add_disk_randomness); void __cold rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; /* * If kzalloc returns null, we just won't use that entropy * source. */ state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); if (state) { state->last_time = INITIAL_JIFFIES; disk->random = state; } } #endif struct entropy_timer_state { unsigned long entropy; struct timer_list timer; atomic_t samples; unsigned int samples_per_bit; }; /* * Each time the timer fires, we expect that we got an unpredictable jump in * the cycle counter. Even if the timer is running on another CPU, the timer * activity will be touching the stack of the CPU that is generating entropy. * * Note that we don't re-arm the timer in the timer itself - we are happy to be * scheduled away, since that just makes the load more complex, but we do not * want the timer to keep ticking unless the entropy loop is running. * * So the re-arming always happens in the entropy loop itself. */ static void __cold entropy_timer(struct timer_list *timer) { struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); unsigned long entropy = random_get_entropy(); mix_pool_bytes(&entropy, sizeof(entropy)); if (atomic_inc_return(&state->samples) % state->samples_per_bit == 0) credit_init_bits(1); } /* * If we have an actual cycle counter, see if we can generate enough entropy * with timing noise. */ static void __cold try_to_generate_entropy(void) { enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 }; u8 stack_bytes[sizeof(struct entropy_timer_state) + SMP_CACHE_BYTES - 1]; struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES); unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); int cpu = -1; for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { stack->entropy = random_get_entropy(); if (stack->entropy != last) ++num_different; last = stack->entropy; } stack->samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); if (stack->samples_per_bit > MAX_SAMPLES_PER_BIT) return; atomic_set(&stack->samples, 0); timer_setup_on_stack(&stack->timer, entropy_timer, 0); while (!crng_ready() && !signal_pending(current)) { /* * Check !timer_pending() and then ensure that any previous callback has finished * executing by checking try_to_del_timer_sync(), before queueing the next one. */ if (!timer_pending(&stack->timer) && try_to_del_timer_sync(&stack->timer) >= 0) { struct cpumask timer_cpus; unsigned int num_cpus; /* * Preemption must be disabled here, both to read the current CPU number * and to avoid scheduling a timer on a dead CPU. */ preempt_disable(); /* Only schedule callbacks on timer CPUs that are online. */ cpumask_and(&timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); num_cpus = cpumask_weight(&timer_cpus); /* In very bizarre case of misconfiguration, fallback to all online. */ if (unlikely(num_cpus == 0)) { timer_cpus = *cpu_online_mask; num_cpus = cpumask_weight(&timer_cpus); } /* Basic CPU round-robin, which avoids the current CPU. */ do { cpu = cpumask_next(cpu, &timer_cpus); if (cpu >= nr_cpu_ids) cpu = cpumask_first(&timer_cpus); } while (cpu == smp_processor_id() && num_cpus > 1); /* Expiring the timer at `jiffies` means it's the next tick. */ stack->timer.expires = jiffies; add_timer_on(&stack->timer, cpu); preempt_enable(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); schedule(); stack->entropy = random_get_entropy(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); del_timer_sync(&stack->timer); destroy_timer_on_stack(&stack->timer); } /********************************************************************** * * Userspace reader/writer interfaces. * * getrandom(2) is the primary modern interface into the RNG and should * be used in preference to anything else. * * Reading from /dev/random has the same functionality as calling * getrandom(2) with flags=0. In earlier versions, however, it had * vastly different semantics and should therefore be avoided, to * prevent backwards compatibility issues. * * Reading from /dev/urandom has the same functionality as calling * getrandom(2) with flags=GRND_INSECURE. Because it does not block * waiting for the RNG to be ready, it should not be used. * * Writing to either /dev/random or /dev/urandom adds entropy to * the input pool but does not credit it. * * Polling on /dev/random indicates when the RNG is initialized, on * the read side, and when it wants new entropy, on the write side. * * Both /dev/random and /dev/urandom have the same set of ioctls for * adding entropy, getting the entropy count, zeroing the count, and * reseeding the crng. * **********************************************************************/ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { struct iov_iter iter; int ret; if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; /* * Requesting insecure and blocking randomness at the same time makes * no sense. */ if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; if (!crng_ready() && !(flags & GRND_INSECURE)) { if (flags & GRND_NONBLOCK) return -EAGAIN; ret = wait_for_random_bytes(); if (unlikely(ret)) return ret; } ret = import_ubuf(ITER_DEST, ubuf, len, &iter); if (unlikely(ret)) return ret; return get_random_bytes_user(&iter); } static __poll_t random_poll(struct file *file, poll_table *wait) { poll_wait(file, &crng_init_wait, wait); return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } static ssize_t write_pool_user(struct iov_iter *iter) { u8 block[BLAKE2S_BLOCK_SIZE]; ssize_t ret = 0; size_t copied; if (unlikely(!iov_iter_count(iter))) return 0; for (;;) { copied = copy_from_iter(block, sizeof(block), iter); ret += copied; mix_pool_bytes(block, copied); if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); return ret ? ret : -EFAULT; } static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { return write_pool_user(iter); } static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { static int maxwarn = 10; /* * Opportunistically attempt to initialize the RNG on platforms that * have fast cycle counters, but don't (for now) require it to succeed. */ if (!crng_ready()) try_to_generate_entropy(); if (!crng_ready()) { if (!ratelimit_disable && maxwarn <= 0) ++urandom_warning.missed; else if (ratelimit_disable || __ratelimit(&urandom_warning)) { --maxwarn; pr_notice("%s: uninitialized urandom read (%zu bytes read)\n", current->comm, iov_iter_count(iter)); } } return get_random_bytes_user(iter); } static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { int ret; if (!crng_ready() && ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) || (kiocb->ki_filp->f_flags & O_NONBLOCK))) return -EAGAIN; ret = wait_for_random_bytes(); if (ret != 0) return ret; return get_random_bytes_user(iter); } static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { int __user *p = (int __user *)arg; int ent_count; switch (cmd) { case RNDGETENTCNT: /* Inherently racy, no point locking. */ if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; if (ent_count < 0) return -EINVAL; credit_init_bits(ent_count); return 0; case RNDADDENTROPY: { struct iov_iter iter; ssize_t ret; int len; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p++)) return -EFAULT; if (ent_count < 0) return -EINVAL; if (get_user(len, p++)) return -EFAULT; ret = import_ubuf(ITER_SOURCE, p, len, &iter); if (unlikely(ret)) return ret; ret = write_pool_user(&iter); if (unlikely(ret < 0)) return ret; /* Since we're crediting, enforce that it was all written into the pool. */ if (unlikely(ret != len)) return -EFAULT; credit_init_bits(ent_count); return 0; } case RNDZAPENTCNT: case RNDCLEARPOOL: /* No longer has any effect. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!crng_ready()) return -ENODATA; crng_reseed(NULL); return 0; default: return -EINVAL; } } static int random_fasync(int fd, struct file *filp, int on) { return fasync_helper(fd, filp, on, &fasync); } const struct file_operations random_fops = { .read_iter = random_read_iter, .write_iter = random_write_iter, .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { .read_iter = urandom_read_iter, .write_iter = random_write_iter, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /******************************************************************** * * Sysctl interface. * * These are partly unused legacy knobs with dummy values to not break * userspace and partly still useful things. They are usually accessible * in /proc/sys/kernel/random/ and are as follows: * * - boot_id - a UUID representing the current boot. * * - uuid - a random UUID, different each time the file is read. * * - poolsize - the number of bits of entropy that the input pool can * hold, tied to the POOL_BITS constant. * * - entropy_avail - the number of bits of entropy currently in the * input pool. Always <= poolsize. * * - write_wakeup_threshold - the amount of entropy in the input pool * below which write polls to /dev/random will unblock, requesting * more entropy, tied to the POOL_READY_BITS constant. It is writable * to avoid breaking old userspaces, but writing to it does not * change any behavior of the RNG. * * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL. * It is writable to avoid breaking old userspaces, but writing * to it does not change any behavior of the RNG. * ********************************************************************/ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ; static int sysctl_random_write_wakeup_bits = POOL_READY_BITS; static int sysctl_poolsize = POOL_BITS; static u8 sysctl_bootid[UUID_SIZE]; /* * This function is used to return both the bootid UUID, and random * UUID. The difference is in whether table->data is NULL; if it is, * then a new UUID is generated and returned to the user. */ static int proc_do_uuid(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { u8 tmp_uuid[UUID_SIZE], *uuid; char uuid_string[UUID_STRING_LEN + 1]; struct ctl_table fake_table = { .data = uuid_string, .maxlen = UUID_STRING_LEN }; if (write) return -EPERM; uuid = table->data; if (!uuid) { uuid = tmp_uuid; generate_random_uuid(uuid); } else { static DEFINE_SPINLOCK(bootid_spinlock); spin_lock(&bootid_spinlock); if (!uuid[8]) generate_random_uuid(uuid); spin_unlock(&bootid_spinlock); } snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); return proc_dostring(&fake_table, 0, buf, lenp, ppos); } /* The same as proc_dointvec, but writes don't change anything. */ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } static struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "entropy_avail", .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "write_wakeup_threshold", .data = &sysctl_random_write_wakeup_bits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "urandom_min_reseed_secs", .data = &sysctl_random_min_urandom_seed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "boot_id", .data = &sysctl_bootid, .mode = 0444, .proc_handler = proc_do_uuid, }, { .procname = "uuid", .mode = 0444, .proc_handler = proc_do_uuid, }, }; /* * random_init() is called before sysctl_init(), * so we cannot call register_sysctl_init() in random_init() */ static int __init random_sysctls_init(void) { register_sysctl_init("kernel/random", random_table); return 0; } device_initcall(random_sysctls_init); #endif |
| 179 178 179 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Fixmap manipulation code */ #include <linux/bug.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/libfdt.h> #include <linux/memory.h> #include <linux/mm.h> #include <linux/sizes.h> #include <asm/fixmap.h> #include <asm/kernel-pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> /* ensure that the fixmap region does not grow down into the PCI I/O region */ static_assert(FIXADDR_TOT_START > PCI_IO_END); #define NR_BM_PTE_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT) #define NR_BM_PMD_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT) static_assert(NR_BM_PMD_TABLES == 1); #define __BM_TABLE_IDX(addr, shift) \ (((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift))) #define BM_PTE_TABLE_IDX(addr) __BM_TABLE_IDX(addr, PMD_SHIFT) static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss; static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; static inline pte_t *fixmap_pte(unsigned long addr) { return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)]; } static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr) { pmd_t pmd = READ_ONCE(*pmdp); pte_t *ptep; if (pmd_none(pmd)) { ptep = bm_pte[BM_PTE_TABLE_IDX(addr)]; __pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE | PMD_TABLE_AF); } } static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr, unsigned long end) { unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; if (pud_none(pud)) __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE | PUD_TABLE_AF); pmdp = pmd_offset_kimg(pudp, addr); do { next = pmd_addr_end(addr, end); early_fixmap_init_pte(pmdp, addr); } while (pmdp++, addr = next, addr != end); } static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end) { p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) && p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); } if (p4d_none(p4d)) __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE | P4D_TABLE_AF); pudp = pud_offset_kimg(p4dp, addr); early_fixmap_init_pmd(pudp, addr, end); } /* * The p*d_populate functions call virt_to_phys implicitly so they can't be used * directly on kernel symbols (bm_p*d). This function is called too early to use * lm_alias so __p*d_populate functions must be used to populate with the * physical address from __pa_symbol. */ void __init early_fixmap_init(void) { unsigned long addr = FIXADDR_TOT_START; unsigned long end = FIXADDR_TOP; pgd_t *pgdp = pgd_offset_k(addr); p4d_t *p4dp = p4d_offset_kimg(pgdp, addr); early_fixmap_init_pud(p4dp, addr, end); } /* * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we * ever need to use IPIs for TLB broadcasting, then we're in trouble here. */ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); ptep = fixmap_pte(addr); if (pgprot_val(flags)) { __set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { __pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); phys_addr_t dt_phys_base; int offset; void *dt_virt; /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be * at least 8 bytes so that we can always access the magic and size * fields of the FDT header after mapping the first chunk, double check * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) return NULL; dt_phys_base = round_down(dt_phys, PAGE_SIZE); offset = dt_phys % PAGE_SIZE; dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot); if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; *size = fdt_totalsize(dt_virt); if (*size > MAX_FDT_SIZE) return NULL; if (offset + *size > PAGE_SIZE) { create_mapping_noalloc(dt_phys_base, dt_virt_base, offset + *size, prot); } return dt_virt; } |
| 641 175 441 1028 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for atomic bit * operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #include <linux/instrumented.h> /** * set_bit - Atomically set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); } /** * clear_bit - Clears a bit in memory * @nr: Bit to clear * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). */ static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); } /** * change_bit - Toggle a bit in memory * @nr: Bit to change * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); } /** * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } /** * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } /** * test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 736 684 295 738 8 278 483 479 10 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/preempt.h> #include <linux/seqlock_types.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockbase: prefix for associated lock/unlock */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline const seqcount_t * \ __seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = smp_load_acquire(&s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lockbase##_lock(s->lock)); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = smp_load_acquire(&s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(s->lock)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return smp_load_acquire(&s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) #undef SEQCOUNT_LOCKNAME /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop, \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr)(s) #define seqprop_const_ptr(s) __seqprop(s, const_ptr)(s) #define seqprop_sequence(s) __seqprop(s, sequence)(s) #define seqprop_preemptible(s) __seqprop(s, preemptible)(s) #define seqprop_assert(s) __seqprop(s, assert)(s) /** * __read_seqcount_begin() - begin a seqcount_t read section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ while ((__seq = seqprop_sequence(s)) & 1) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) __read_seqcount_begin(s) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(seqprop_const_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned __seq = seqprop_sequence(s); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ do___read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ do_read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return do___read_seqcount_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_begin() */ #define raw_write_seqcount_begin(s) \ do { \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_raw_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_end() */ #define raw_write_seqcount_end(s) \ do { \ do_raw_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst * Context: check write_seqcount_begin() */ #define write_seqcount_begin_nested(s, subclass) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \ } while (0) static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); do_raw_write_seqcount_begin(s); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: sequence counter write side sections must be serialized and * non-preemptible. Preemption will be automatically disabled if and * only if the seqcount write serialization lock is associated, and * preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_write_seqcount_begin(seqcount_t *s) { do_write_seqcount_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: Preemption will be automatically re-enabled if and only if * the seqcount write serialization lock is associated, and preemptible. */ #define write_seqcount_end(s) \ do { \ do_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); do_raw_write_seqcount_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before nor after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ do_raw_write_seqcount_barrier(seqprop_ptr(s)) static inline void do_raw_write_seqcount_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ do_write_seqcount_invalidate(seqprop_ptr(s)) static inline void do_write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with raw_read_seqcount_latch_retry(). */ static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See write_seqcount_latch() for details and a full reader/writer usage * example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s) { kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return raw_read_seqcount_latch(s); } /** * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { smp_rmb(); return unlikely(READ_ONCE(s->seqcount.sequence) != start); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { kcsan_atomic_next(0); return raw_read_seqcount_latch_retry(s, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t */ static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /** * write_seqcount_latch_begin() - redirect latch readers to odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * write_seqcount_latch_begin(&latch->seq); * modify(latch->data[0], ...); * write_seqcount_latch(&latch->seq); * modify(latch->data[1], ...); * write_seqcount_latch_end(&latch->seq); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s) { kcsan_nestable_atomic_begin(); raw_write_seqcount_latch(s); } /** * write_seqcount_latch() - redirect latch readers to even copy * @s: Pointer to seqcount_latch_t */ static __always_inline void write_seqcount_latch(seqcount_latch_t *s) { raw_write_seqcount_latch(s); } /** * write_seqcount_latch_end() - end a seqcount_latch_t write section * @s: Pointer to seqcount_latch_t * * Marks the end of a seqcount_latch_t writer section, after all copies of the * latch-protected data have been updated. */ static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s) { kcsan_nestable_atomic_end(); } #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); do_write_seqcount_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } #endif /* __LINUX_SEQLOCK_H */ |
| 363 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/mmu_context.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_CONTEXT_H #define __ASM_MMU_CONTEXT_H #ifndef __ASSEMBLY__ #include <linux/compiler.h> #include <linux/sched.h> #include <linux/sched/hotplug.h> #include <linux/mm_types.h> #include <linux/pgtable.h> #include <linux/pkeys.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/gcs.h> #include <asm/proc-fns.h> #include <asm/cputype.h> #include <asm/sysreg.h> #include <asm/tlbflush.h> extern bool rodata_full; static inline void contextidr_thread_switch(struct task_struct *next) { if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) return; write_sysreg(task_pid_nr(next), contextidr_el1); isb(); } /* * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0. */ static inline void cpu_set_reserved_ttbr0_nosync(void) { unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); write_sysreg(ttbr, ttbr0_el1); } static inline void cpu_set_reserved_ttbr0(void) { cpu_set_reserved_ttbr0_nosync(); isb(); } void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm); static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) { BUG_ON(pgd == swapper_pg_dir); cpu_do_switch_mm(virt_to_phys(pgd),mm); } /* * TCR.T0SZ value to use when the ID map is active. */ #define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. */ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) { unsigned long tcr = read_sysreg(tcr_el1); if ((tcr & TCR_T0SZ_MASK) == t0sz) return; tcr &= ~TCR_T0SZ_MASK; tcr |= t0sz; write_sysreg(tcr, tcr_el1); isb(); } #define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual)) #define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) /* * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm. * * The idmap lives in the same VA range as userspace, but uses global entries * and may use a different TCR_EL1.T0SZ. To avoid issues resulting from * speculative TLB fetches, we must temporarily install the reserved page * tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ. * * If current is a not a user task, the mm covers the TTBR1_EL1 page tables, * which should not be installed in TTBR0_EL1. In this case we can leave the * reserved page tables in place. */ static inline void cpu_uninstall_idmap(void) { struct mm_struct *mm = current->active_mm; cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); if (mm != &init_mm && !system_uses_ttbr0_pan()) cpu_switch_mm(mm->pgd, mm); } static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* * Load our new page tables. A strict BBM approach requires that we ensure that * TLBs are free of any entries that may overlap with the global mappings we are * about to install. * * For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime * services), while for a userspace-driven test_resume cycle it points to * userspace page tables (and we must point it at a zero page ourselves). * * We change T0SZ as part of installing the idmap. This is undone by * cpu_uninstall_idmap() in __cpu_suspend_exit(). */ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); __cpu_set_tcr_t0sz(t0sz); /* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */ write_sysreg(ttbr0, ttbr0_el1); isb(); } void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); __cpu_replace_ttbr1(pgdp, false); } /* * It would be nice to return ASIDs back to the allocator, but unfortunately * that introduces a race with a generation rollover where we could erroneously * free an ASID allocated in a future generation. We could workaround this by * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap), * but we'd then need to make sure that we didn't dirty any TLBs afterwards. * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you * take CPU migration into account. */ void check_and_switch_context(struct mm_struct *mm); #define init_new_context(tsk, mm) init_new_context(tsk, mm) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { atomic64_set(&mm->context.id, 0); refcount_set(&mm->context.pinned, 0); /* pkey 0 is the default, so always reserve it. */ mm->context.pkey_allocation_map = BIT(0); return 0; } static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) { } static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { u64 ttbr; if (!system_uses_ttbr0_pan()) return; if (mm == &init_mm) ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); else ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48; WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr); } #else static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { } #endif #define enter_lazy_tlb enter_lazy_tlb static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { /* * We don't actually care about the ttbr0 mapping, so point it at the * zero page. */ update_saved_ttbr0(tsk, &init_mm); } static inline void __switch_mm(struct mm_struct *next) { /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. */ if (next == &init_mm) { cpu_set_reserved_ttbr0(); return; } check_and_switch_context(next); } static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { if (prev != next) __switch_mm(next); /* * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch * of another thread of the same process). */ update_saved_ttbr0(tsk, next); } static inline const struct cpumask * task_cpu_possible_mask(struct task_struct *p) { if (!static_branch_unlikely(&arm64_mismatched_32bit_el0)) return cpu_possible_mask; if (!is_compat_thread(task_thread_info(p))) return cpu_possible_mask; return system_32bit_el0_cpumask(); } #define task_cpu_possible_mask task_cpu_possible_mask void verify_cpu_asid_bits(void); void post_ttbr_update_workaround(void); unsigned long arm64_mm_context_get(struct mm_struct *mm); void arm64_mm_context_put(struct mm_struct *mm); #define mm_untag_mask mm_untag_mask static inline unsigned long mm_untag_mask(struct mm_struct *mm) { return -1UL >> 8; } /* * Only enforce protection keys on the current process, because there is no * user context to access POR_EL0 for another address space. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { if (!system_supports_poe()) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return por_el0_allows_pkey(vma_pkey(vma), write, execute); } #define deactivate_mm deactivate_mm static inline void deactivate_mm(struct task_struct *tsk, struct mm_struct *mm) { gcs_free(tsk); } #include <asm-generic/mmu_context.h> #endif /* !__ASSEMBLY__ */ #endif /* !__ASM_MMU_CONTEXT_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux IPv6 multicast routing support for BSD pim6sd * Based on net/ipv4/ipmr.c. * * (c) 2004 Mickael Hoerdt, <hoerdt@clarinet.u-strasbg.fr> * LSIIT Laboratory, Strasbourg, France * (c) 2004 Jean-Philippe Andriot, <jean-philippe.andriot@6WIND.com> * 6WIND, Paris, France * Copyright (C)2007,2008 USAGI/WIDE Project * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/rhashtable.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <linux/mroute6.h> #include <linux/pim.h> #include <net/addrconf.h> #include <linux/netfilter_ipv6.h> #include <linux/export.h> #include <net/ip6_checksum.h> #include <linux/netconf.h> #include <net/ip_tunnels.h> #include <linux/nospec.h> struct ip6mr_rule { struct fib_rule common; }; struct ip6mr_result { struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ static DEFINE_SPINLOCK(mrt_lock); static struct net_device *vif_dev_read(const struct vif_device *vif) { return rcu_dereference(vif->dev); } /* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved entries is changed only in process context and protected with weak lock mrt_lock. Queue of unresolved entries is protected with strong spinlock mfc_unres_lock. In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ip6mr_new_table(struct net *net, u32 id); static void ip6mr_free_table(struct mr_table *mrt); static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd); static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \ lockdep_rtnl_is_held() || \ list_empty(&net->ipv6.mr6_tables)) static bool ip6mr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { struct mr_table *ret; if (!mrt) ret = list_entry_rcu(net->ipv6.mr6_tables.next, struct mr_table, list); else ret = list_entry_rcu(mrt->list.next, struct mr_table, list); if (&ret->list == &net->ipv6.mr6_tables) return NULL; return ret; } static struct mr_table *__ip6mr_get_table(struct net *net, u32 id) { struct mr_table *mrt; ip6mr_for_each_table(mrt, net) { if (mrt->id == id) return mrt; } return NULL; } static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { struct mr_table *mrt; rcu_read_lock(); mrt = __ip6mr_get_table(net, id); rcu_read_unlock(); return mrt; } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr_table **mrt) { int err; struct ip6mr_result res; struct fib_lookup_arg arg = { .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi6_to_flowi(flp6)); err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flowi6_to_flowi(flp6), 0, &arg); if (err < 0) return err; *mrt = res.mrt; return 0; } static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ip6mr_result *res = arg->result; struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } arg->table = fib_rule_get_table(rule, arg); mrt = __ip6mr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; } static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) { return 1; } static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { return 0; } static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { return 1; } static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { frh->dst_len = 0; frh->src_len = 0; frh->tos = 0; return 0; } static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { .family = RTNL_FAMILY_IP6MR, .rule_size = sizeof(struct ip6mr_rule), .addr_size = sizeof(struct in6_addr), .action = ip6mr_rule_action, .match = ip6mr_rule_match, .configure = ip6mr_rule_configure, .compare = ip6mr_rule_compare, .fill = ip6mr_rule_fill, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, }; static int __net_init ip6mr_rules_init(struct net *net) { struct fib_rules_ops *ops; struct mr_table *mrt; int err; ops = fib_rules_register(&ip6mr_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); INIT_LIST_HEAD(&net->ipv6.mr6_tables); mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); if (IS_ERR(mrt)) { err = PTR_ERR(mrt); goto err1; } err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT); if (err < 0) goto err2; net->ipv6.mr6_rules_ops = ops; return 0; err2: rtnl_lock(); ip6mr_free_table(mrt); rtnl_unlock(); err1: fib_rules_unregister(ops); return err; } static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr_table *mrt, *next; ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } fib_rules_unregister(net->ipv6.mr6_rules_ops); } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack); } static unsigned int ip6mr_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR); } bool ip6mr_rule_default(const struct fib_rule *rule) { return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL && rule->table == RT6_TABLE_DFLT && !rule->l3mdev; } EXPORT_SYMBOL(ip6mr_rule_default); #else #define ip6mr_for_each_table(mrt, net) \ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) static bool ip6mr_can_free_table(struct net *net) { return !check_net(net); } static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) return net->ipv6.mrt6; return NULL; } static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { return net->ipv6.mrt6; } #define __ip6mr_get_table ip6mr_get_table static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr_table **mrt) { *mrt = net->ipv6.mrt6; return 0; } static int __net_init ip6mr_rules_init(struct net *net) { struct mr_table *mrt; mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); if (IS_ERR(mrt)) return PTR_ERR(mrt); net->ipv6.mrt6 = mrt; return 0; } static void __net_exit ip6mr_rules_exit(struct net *net) { ASSERT_RTNL(); ip6mr_free_table(net->ipv6.mrt6); net->ipv6.mrt6 = NULL; } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static unsigned int ip6mr_rules_seq_read(const struct net *net) { return 0; } #endif static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct mfc6_cache_cmp_arg *cmparg = arg->key; struct mfc6_cache *c = (struct mfc6_cache *)ptr; return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) || !ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin); } static const struct rhashtable_params ip6mr_rht_params = { .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc6_cache, cmparg), .key_len = sizeof(struct mfc6_cache_cmp_arg), .nelem_hint = 3, .obj_cmpfn = ip6mr_hash_cmp, .automatic_shrinking = true, }; static void ip6mr_new_table_set(struct mr_table *mrt, struct net *net) { #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); #endif } static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = { .mf6c_origin = IN6ADDR_ANY_INIT, .mf6c_mcastgrp = IN6ADDR_ANY_INIT, }; static struct mr_table_ops ip6mr_mr_table_ops = { .rht_params = &ip6mr_rht_params, .cmparg_any = &ip6mr_mr_table_ops_cmparg_any, }; static struct mr_table *ip6mr_new_table(struct net *net, u32 id) { struct mr_table *mrt; mrt = __ip6mr_get_table(net, id); if (mrt) return mrt; return mr_table_alloc(net, id, &ip6mr_mr_table_ops, ipmr_expire_process, ip6mr_new_table_set); } static void ip6mr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); WARN_ON_ONCE(!ip6mr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC | MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing * /proc/ip6_mr_cache /proc/ip6_mr_vif */ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; rcu_read_lock(); mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) { rcu_read_unlock(); return ERR_PTR(-ENOENT); } iter->mrt = mrt; return mr_vif_seq_start(seq, pos); } static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); } else { const struct vif_device *vif = v; const struct net_device *vif_dev; const char *name; vif_dev = vif_dev_read(vif); name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); } return 0; } static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, .next = mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, .show = ip6mr_vif_seq_show, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) return ERR_PTR(-ENOENT); return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Group " "Origin " "Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc6_cache *mfc = v; const struct mr_mfc_iter *it = seq->private; struct mr_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->_c.mfc_un.res.pkt, mfc->_c.mfc_un.res.bytes, mfc->_c.mfc_un.res.wrong_if); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain * pkt, bytes and wrong_if values */ seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = mr_mfc_seq_next, .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; #endif #ifdef CONFIG_IPV6_PIMSM_V2 static int pim6_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; int reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) || (pim->flags & PIM_NULL_REGISTER) || (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, sizeof(*pim), IPPROTO_PIM, csum_partial((void *)pim, sizeof(*pim), 0)) && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; /* check if the inner packet is destined to mcast group */ encap = (struct ipv6hdr *)(skb_transport_header(skb) + sizeof(*pim)); if (!ipv6_addr_is_multicast(&encap->daddr) || encap->payload_len == 0 || ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto drop; /* Pairs with WRITE_ONCE() in mif6_add()/mif6_delete() */ reg_vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (reg_vif_num >= 0) reg_dev = vif_dev_read(&mrt->vif_table[reg_vif_num]); if (!reg_dev) goto drop; skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_NONE; skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); return 0; drop: kfree_skb(skb); return 0; } static const struct inet6_protocol pim6_protocol = { .handler = pim6_rcv, }; /* Service routines creating virtual interfaces: PIMREG */ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; if (!pskb_inet_may_pull(skb)) goto tx_err; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto tx_err; DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), MRT6MSG_WHOLEPKT); rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) { return 0; } static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8; dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; dev->netns_local = true; } static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; if (mrt->id == RT6_TABLE_DFLT) sprintf(name, "pim6reg"); else sprintf(name, "pim6reg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (!dev) return NULL; dev_net_set(dev, net); if (register_netdevice(dev)) { free_netdev(dev); return NULL; } if (dev_open(dev, NULL)) goto failure; dev_hold(dev); return dev; failure: unregister_netdevice(dev); return NULL; } #endif static int call_ip6mr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, mifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type, vif, vif_dev, vif_index, tb_id, &net->ipv6.ipmr_seq); } static int call_ip6mr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc6_cache *mfc, u32 tb_id) { return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type, &mfc->_c, tb_id, &net->ipv6.ipmr_seq); } /* Delete a VIF entry */ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct vif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; v = &mrt->vif_table[vifi]; dev = rtnl_dereference(v->dev); if (!dev) return -EADDRNOTAVAIL; call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_VIF_DEL, v, dev, vifi, mrt->id); spin_lock(&mrt_lock); RCU_INIT_POINTER(v->dev, NULL); #ifdef CONFIG_IPV6_PIMSM_V2 if (vifi == mrt->mroute_reg_vif_num) { /* Pairs with READ_ONCE() in ip6mr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, -1); } #endif if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } WRITE_ONCE(mrt->maxvif, tmp + 1); } spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); in6_dev = __in6_dev_get(dev); if (in6_dev) { atomic_dec(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); netdev_put(dev, &v->dev_tracker); return 0; } static inline void ip6mr_cache_free_rcu(struct rcu_head *head) { struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c); } static inline void ip6mr_cache_free(struct mfc6_cache *c) { call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs and reporting error to netlink readers. */ static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT; rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else kfree_skb(skb); } ip6mr_cache_free(c); } /* Timer process for all the unresolved queue. */ static void ipmr_do_expire_process(struct mr_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; struct mr_mfc *c, *next; list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; continue; } list_del(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } if (!list_empty(&mrt->mfc_unres_queue)) ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under locked mrt_lock. */ static void ip6mr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; cache->mfc_un.res.minvif = MAXMIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; if (cache->mfc_un.res.maxvif <= vifi) cache->mfc_un.res.maxvif = vifi + 1; } } cache->mfc_un.res.lastuse = jiffies; } static int mif6_add(struct net *net, struct mr_table *mrt, struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { #ifdef CONFIG_IPV6_PIMSM_V2 case MIFF_REGISTER: /* * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ip6mr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); if (err) { unregister_netdevice(dev); dev_put(dev); return err; } break; #endif case 0: dev = dev_get_by_index(net, vifc->mif6c_pifi); if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); if (err) { dev_put(dev); return err; } break; default: return -EINVAL; } in6_dev = __in6_dev_get(dev); if (in6_dev) { atomic_inc(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } /* Fill in the VIF structures */ vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0), MIFF_REGISTER); /* And finish update writing critical data */ spin_lock(&mrt_lock); rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); #endif if (vifi + 1 > mrt->maxvif) WRITE_ONCE(mrt->maxvif, vifi + 1); spin_unlock(&mrt_lock); call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, dev, vifi, mrt->id); return 0; } static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = *origin, .mf6c_mcastgrp = *mcastgrp, }; return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt, struct in6_addr *mcastgrp, mifi_t mifi) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = in6addr_any, .mf6c_mcastgrp = *mcastgrp, }; if (ipv6_addr_any(mcastgrp)) return mr_mfc_find_any_parent(mrt, mifi); return mr_mfc_find_any(mrt, mifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ static struct mfc6_cache * ip6mr_cache_find_parent(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp, int parent) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = *origin, .mf6c_mcastgrp = *mcastgrp, }; return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (!c) return NULL; c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXMIFS; c->_c.free = ip6mr_cache_free_rcu; refcount_set(&c->_c.mfc_un.res.refcount, 1); return c; } static struct mfc6_cache *ip6mr_cache_alloc_unres(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (!c) return NULL; skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; return c; } /* * A cache entry has gone into a resolved state from queued */ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; /* * Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); if (mr_fill_mroute(mrt, skb, &c->_c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE; } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { rcu_read_lock(); ip6_mr_forward(net, mrt, skb->dev, skb, c); rcu_read_unlock(); } } } /* * Bounce a cache query up to pim6sd and netlink. * * Called under rcu_read_lock() */ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert) { struct sock *mroute6_sk; struct sk_buff *skb; struct mrt6msg *msg; int ret; #ifdef CONFIG_IPV6_PIMSM_V2 if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt) +sizeof(*msg)); else #endif skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC); if (!skb) return -ENOBUFS; /* I suppose that internal messages * do not require checksums */ skb->ip_summed = CHECKSUM_UNNECESSARY; #ifdef CONFIG_IPV6_PIMSM_V2 if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) { /* Ugly, but we have no choice with this interface. Duplicate old header, fix length etc. And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = assert; if (assert == MRT6MSG_WRMIFWHOLE) msg->im6_mif = mifi; else msg->im6_mif = READ_ONCE(mrt->mroute_reg_vif_num); msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; skb->ip_summed = CHECKSUM_UNNECESSARY; } else #endif { /* * Copy the IP header */ skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr)); /* * Add our header */ skb_put(skb, sizeof(*msg)); skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = assert; msg->im6_mif = mifi; msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; } mroute6_sk = rcu_dereference(mrt->mroute_sk); if (!mroute6_sk) { kfree_skb(skb); return -EINVAL; } mrt6msg_netlink_event(mrt, skb); /* Deliver to user space multicast routing algorithms */ ret = sock_queue_rcv_skb(mroute6_sk, skb); if (ret < 0) { net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); } return ret; } /* Queue a packet for resolution. It gets locked cache entry! */ static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi, struct sk_buff *skb, struct net_device *dev) { struct mfc6_cache *c; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { found = true; break; } } if (!found) { /* * Create a new entry if allowable */ c = ip6mr_cache_alloc_unres(); if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); return -ENOBUFS; } /* Fill in the new cache entry */ c->_c.mfc_parent = -1; c->mf6c_origin = ipv6_hdr(skb)->saddr; c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; /* * Reflect first query at pim6sd */ err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); ip6mr_cache_free(c); kfree_skb(skb); return err; } atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { if (dev) { skb->dev = dev; skb->skb_iif = dev->ifindex; } skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } spin_unlock_bh(&mfc_unres_lock); return err; } /* * MFC6 cache manipulation by user space */ static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc, int parent) { struct mfc6_cache *c; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (!c) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params); list_del_rcu(&c->_c.list); call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_ENTRY_DEL, c, mrt->id); mr6_netlink_event(mrt, c, RTM_DELROUTE); mr_cache_put(&c->_c); return 0; } static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ip6mr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (rcu_access_pointer(v->dev) == dev) mif6_delete(mrt, ct, 1, NULL); } } return NOTIFY_DONE; } static unsigned int ip6mr_seq_read(const struct net *net) { return READ_ONCE(net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net); } static int ip6mr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, ip6mr_mr_table_iter, extack); } static struct notifier_block ip6_mr_notifier = { .notifier_call = ip6mr_device_event }; static const struct fib_notifier_ops ip6mr_notifier_ops_template = { .family = RTNL_FAMILY_IP6MR, .fib_seq_read = ip6mr_seq_read, .fib_dump = ip6mr_dump, .owner = THIS_MODULE, }; static int __net_init ip6mr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv6.ipmr_seq = 0; ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv6.ip6mr_notifier_ops = ops; return 0; } static void __net_exit ip6mr_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops); net->ipv6.ip6mr_notifier_ops = NULL; } /* Setup for IP multicast routing */ static int __net_init ip6mr_net_init(struct net *net) { int err; err = ip6mr_notifier_init(net); if (err) return err; err = ip6mr_rules_init(net); if (err < 0) goto ip6mr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; if (!proc_create_net("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_seq_ops, sizeof(struct mr_vif_iter))) goto proc_vif_fail; if (!proc_create_net("ip6_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: remove_proc_entry("ip6_mr_vif", net->proc_net); proc_vif_fail: rtnl_lock(); ip6mr_rules_exit(net); rtnl_unlock(); #endif ip6mr_rules_fail: ip6mr_notifier_exit(net); return err; } static void __net_exit ip6mr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ip6_mr_cache", net->proc_net); remove_proc_entry("ip6_mr_vif", net->proc_net); #endif ip6mr_notifier_exit(net); } static void __net_exit ip6mr_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ip6mr_rules_exit(net); rtnl_unlock(); } static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, .exit_batch = ip6mr_net_exit_batch, }; static const struct rtnl_msg_handler ip6mr_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = RTNL_FAMILY_IP6MR, .msgtype = RTM_GETROUTE, .doit = ip6mr_rtm_getroute, .dumpit = ip6mr_rtm_dumproute}, }; int __init ip6_mr_init(void) { int err; mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); if (!mrt_cachep) return -ENOMEM; err = register_pernet_subsys(&ip6mr_net_ops); if (err) goto reg_pernet_fail; err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; #ifdef CONFIG_IPV6_PIMSM_V2 if (inet6_add_protocol(&pim6_protocol, IPPROTO_PIM) < 0) { pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } #endif err = rtnl_register_many(ip6mr_rtnl_msg_handlers); if (!err) return 0; #ifdef CONFIG_IPV6_PIMSM_V2 inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); add_proto_fail: unregister_netdevice_notifier(&ip6_mr_notifier); #endif reg_notif_fail: unregister_pernet_subsys(&ip6mr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } void __init ip6_mr_cleanup(void) { rtnl_unregister_many(ip6mr_rtnl_msg_handlers); #ifdef CONFIG_IPV6_PIMSM_V2 inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); #endif unregister_netdevice_notifier(&ip6_mr_notifier); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, struct mf6cctl *mfc, int mrtsock, int parent) { unsigned char ttls[MAXMIFS]; struct mfc6_cache *uc, *c; struct mr_mfc *_uc; bool found; int i, err; if (mfc->mf6cc_parent >= MAXMIFS) return -ENFILE; memset(ttls, 255, MAXMIFS); for (i = 0; i < MAXMIFS; i++) { if (IF_ISSET(i, &mfc->mf6cc_ifset)) ttls[i] = 1; } /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (c) { spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; spin_unlock(&mrt_lock); call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; c = ip6mr_cache_alloc(); if (!c) return -ENOMEM; c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ip6mr_rht_params); if (err) { pr_err("ip6mr: rhtable insert error %d\n", err); ip6mr_cache_free(c); return err; } list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { uc = (struct mfc6_cache *)_uc; if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } /* * Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, int flags) { struct mr_mfc *c, *tmp; LIST_HEAD(list); int i; /* Shut down all active vif entries */ if (flags & (MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC)) { for (i = 0; i < mrt->maxvif; i++) { if (((mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS_STATIC)) || (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS))) continue; mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); } /* Wipe the cache */ if (flags & (MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC)) { list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC_STATIC)) || (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC))) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_ENTRY_DEL, (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } } if (flags & MRT6_FLUSH_MFC) { if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } spin_unlock_bh(&mfc_unres_lock); } } } static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); spin_lock(&mrt_lock); if (rtnl_dereference(mrt->mroute_sk)) { err = -EADDRINUSE; } else { rcu_assign_pointer(mrt->mroute_sk, sk); sock_set_flag(sk, SOCK_RCU_FREE); atomic_inc(&net->ipv6.devconf_all->mc_forwarding); } spin_unlock(&mrt_lock); if (!err) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); rtnl_unlock(); return err; } int ip6mr_sk_done(struct sock *sk) { struct net *net = sock_net(sk); struct ipv6_devconf *devconf; struct mr_table *mrt; int err = -EACCES; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return err; devconf = net->ipv6.devconf_all; if (!devconf || !atomic_read(&devconf->mc_forwarding)) return err; rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { spin_lock(&mrt_lock); RCU_INIT_POINTER(mrt->mroute_sk, NULL); /* Note that mroute_sk had SOCK_RCU_FREE set, * so the RCU grace period before sk freeing * is guaranteed by sk_destruct() */ atomic_dec(&devconf->mc_forwarding); spin_unlock(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MFC); err = 0; break; } } rtnl_unlock(); return err; } bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) return NULL; return rcu_access_pointer(mrt->mroute_sk); } EXPORT_SYMBOL(mroute6_is_socket); /* * Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately * that's how BSD mrouted happens to think. Maybe one day with a proper * MOSPF/PIM router set up we can clean this up. */ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { int ret, parent = 0; struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; if (optname != MRT6_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } switch (optname) { case MRT6_INIT: if (optlen < sizeof(int)) return -EINVAL; return ip6mr_sk_init(mrt, sk); case MRT6_DONE: return ip6mr_sk_done(sk); case MRT6_ADD_MIF: if (optlen < sizeof(vif)) return -EINVAL; if (copy_from_sockptr(&vif, optval, sizeof(vif))) return -EFAULT; if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); ret = mif6_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; case MRT6_DEL_MIF: if (optlen < sizeof(mifi_t)) return -EINVAL; if (copy_from_sockptr(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; /* * Manipulate the forwarding caches. These live * in a sort of kernel/user symbiosis. */ case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; fallthrough; case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) return -EFAULT; if (parent == 0) parent = mfc.mf6cc_parent; rtnl_lock(); if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) ret = ip6mr_mfc_delete(mrt, &mfc, parent); else ret = ip6mr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); rtnl_unlock(); return ret; case MRT6_FLUSH: { int flags; if (optlen != sizeof(flags)) return -EINVAL; if (copy_from_sockptr(&flags, optval, sizeof(flags))) return -EFAULT; rtnl_lock(); mroute_clean_tables(mrt, flags); rtnl_unlock(); return 0; } /* * Control PIM assert (to activate pim will activate assert) */ case MRT6_ASSERT: { int v; if (optlen != sizeof(v)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; mrt->mroute_do_assert = v; return 0; } #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { bool do_wrmifwhole; int v; if (optlen != sizeof(v)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; do_wrmifwhole = (v == MRT6MSG_WRMIFWHOLE); v = !!v; rtnl_lock(); ret = 0; if (v != mrt->mroute_do_pim) { mrt->mroute_do_pim = v; mrt->mroute_do_assert = v; mrt->mroute_do_wrvifwhole = do_wrmifwhole; } rtnl_unlock(); return ret; } #endif #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES case MRT6_TABLE: { u32 v; if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (v != RT_TABLE_DEFAULT && v >= 100000000) return -EINVAL; if (sk == rcu_access_pointer(mrt->mroute_sk)) return -EBUSY; rtnl_lock(); ret = 0; mrt = ip6mr_new_table(net, v); if (IS_ERR(mrt)) ret = PTR_ERR(mrt); else raw6_sk(sk)->ip6mr_table = v; rtnl_unlock(); return ret; } #endif /* * Spurious command, or MRT6_VERSION which you cannot * set. */ default: return -ENOPROTOOPT; } } /* * Getsock opt support for the multicast routing system. */ int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) { int olr; int val; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (optname) { case MRT6_VERSION: val = 0x0305; break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: val = mrt->mroute_do_pim; break; #endif case MRT6_ASSERT: val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; } if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; olr = min_t(int, olr, sizeof(int)); if (olr < 0) return -EINVAL; if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } /* * The IP multicast ioctl support routines. */ int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) { struct sioc_sg_req6 *sr; struct sioc_mif_req6 *vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: vr = (struct sioc_mif_req6 *)arg; if (vr->mifi >= mrt->maxvif) return -EINVAL; vr->mifi = array_index_nospec(vr->mifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr->mifi]; if (VIF_EXISTS(mrt, vr->mifi)) { vr->icount = READ_ONCE(vif->pkt_in); vr->ocount = READ_ONCE(vif->pkt_out); vr->ibytes = READ_ONCE(vif->bytes_in); vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: sr = (struct sioc_sg_req6 *)arg; rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr->src.sin6_addr, &sr->grp.sin6_addr); if (c) { sr->pktcnt = c->_c.mfc_un.res.pkt; sr->bytecnt = c->_c.mfc_un.res.bytes; sr->wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT struct compat_sioc_sg_req6 { struct sockaddr_in6 src; struct sockaddr_in6 grp; compat_ulong_t pktcnt; compat_ulong_t bytecnt; compat_ulong_t wrong_if; }; struct compat_sioc_mif_req6 { mifi_t mifi; compat_ulong_t icount; compat_ulong_t ocount; compat_ulong_t ibytes; compat_ulong_t obytes; }; int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req6 sr; struct compat_sioc_mif_req6 vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = READ_ONCE(vif->pkt_in); vr.ocount = READ_ONCE(vif->pkt_out); vr.ibytes = READ_ONCE(vif->bytes_in); vr.obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = c->_c.mfc_un.res.pkt; sr.bytecnt = c->_c.mfc_un.res.bytes; sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #endif static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); return dst_output(net, sk, skb); } /* * Processing handlers for ip6mr_forward */ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; struct ipv6hdr *ipv6h; struct dst_entry *dst; struct flowi6 fl6; vif_dev = vif_dev_read(vif); if (!vif_dev) goto out_free; #ifdef CONFIG_IPV6_PIMSM_V2 if (vif->flags & MIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } #endif ipv6h = ipv6_hdr(skb); fl6 = (struct flowi6) { .flowi6_oif = vif->link, .daddr = ipv6h->daddr, }; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); goto out_free; } skb_dst_drop(skb); skb_dst_set(skb, dst); /* * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface * program is joined. * If we will not make it, the program will have to join on all * interfaces. On the other hand, multihoming host (or router, but * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ skb->dev = vif_dev; WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); /* We are about to write */ /* XXX: extension headers? */ if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(vif_dev))) goto out_free; ipv6h = ipv6_hdr(skb); ipv6h->hop_limit--; IP6CB(skb)->flags |= IP6SKB_FORWARDED; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, vif_dev, ip6mr_forward2_finish); out_free: kfree_skb(skb); return 0; } /* Called with rcu_read_lock() */ static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev) { int ct; /* Pairs with WRITE_ONCE() in mif6_delete()/mif6_add() */ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } /* Called under rcu_read_lock() */ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *c) { int psend = -1; int vif, ct; int true_vifi = ip6mr_find_vif(mrt, dev); vif = c->_c.mfc_parent; c->_c.mfc_un.res.pkt++; c->_c.mfc_un.res.bytes += skb->len; c->_c.mfc_un.res.lastuse = jiffies; if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, c->_c.mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); if (mrt->mroute_do_wrvifwhole) ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRMIFWHOLE); } goto dont_forward; } forward: WRITE_ONCE(mrt->vif_table[vif].pkt_in, mrt->vif_table[vif].pkt_in + 1); WRITE_ONCE(mrt->vif_table[vif].bytes_in, mrt->vif_table[vif].bytes_in + skb->len); /* * Forward the frame */ if (ipv6_addr_any(&c->mf6c_origin) && ipv6_addr_any(&c->mf6c_mcastgrp)) { if (true_vifi >= 0 && true_vifi != c->_c.mfc_parent && ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ if ((!ipv6_addr_any(&c->mf6c_origin) || ct != true_vifi) && ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ip6mr_forward2(net, mrt, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, psend); return; } dont_forward: kfree_skb(skb); } /* * Multicast packets for forwarding arrive here */ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; int err; struct net_device *dev; /* skb->dev passed in is the master dev for vrfs. * Get the proper interface that does have a vif associated with it. */ dev = skb->dev; if (netif_is_l3_master(skb->dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); return -ENODEV; } } err = ip6mr_fib_lookup(net, &fl6, &mrt); if (err < 0) { kfree_skb(skb); return err; } cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); if (!cache) { int vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &ipv6_hdr(skb)->daddr, vif); } /* * No usable cache entry */ if (!cache) { int vif; vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) { int err = ip6mr_cache_unresolved(mrt, vif, skb, dev); return err; } kfree_skb(skb); return -ENODEV; } ip6_mr_forward(net, mrt, dev, skb, cache); return 0; } int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid) { int err; struct mr_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); rcu_read_lock(); mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) { rcu_read_unlock(); return -ENOENT; } cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache && skb->dev) { int vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, vif); } if (!cache) { struct sk_buff *skb2; struct ipv6hdr *iph; struct net_device *dev; int vif; dev = skb->dev; if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) { rcu_read_unlock(); return -ENODEV; } /* really correct? */ skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb2) { rcu_read_unlock(); return -ENOMEM; } NETLINK_CB(skb2).portid = portid; skb_reset_transport_header(skb2); skb_put(skb2, sizeof(struct ipv6hdr)); skb_reset_network_header(skb2); iph = ipv6_hdr(skb2); iph->version = 0; iph->priority = 0; iph->flow_lbl[0] = 0; iph->flow_lbl[1] = 0; iph->flow_lbl[2] = 0; iph->payload_len = 0; iph->nexthdr = IPPROTO_NONE; iph->hop_limit = 0; iph->saddr = rt->rt6i_src.addr; iph->daddr = rt->rt6i_dst.addr; err = ip6mr_cache_unresolved(mrt, vif, skb2, dev); rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); rcu_read_unlock(); return err; } static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc6_cache *c, int cmd, int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = RTNL_FAMILY_IP6MR; rtm->rtm_dst_len = 128; rtm->rtm_src_len = 128; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) || nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp)) goto nla_put_failure; err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int _ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags) { return ip6mr_fill_mroute(mrt, skb, portid, seq, (struct mfc6_cache *)c, cmd, flags); } static int mr6_msgsize(bool unresolved, int maxvif) { size_t len = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */ + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */ ; if (!unresolved) len = len + nla_total_size(4) /* RTA_IIF */ + nla_total_size(0) /* RTA_MULTIPATH */ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) /* RTA_MFC_STATS */ + nla_total_size_64bit(sizeof(struct rta_mfc_stats)) ; return len; } static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mr6_msgsize(mfc->_c.mfc_parent >= MAXMIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC); return; errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } static size_t mrt6msg_netlink_msgsize(size_t payloadlen) { size_t len = NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(1) /* IP6MRA_CREPORT_MSGTYPE */ + nla_total_size(4) /* IP6MRA_CREPORT_MIF_ID */ /* IP6MRA_CREPORT_SRC_ADDR */ + nla_total_size(sizeof(struct in6_addr)) /* IP6MRA_CREPORT_DST_ADDR */ + nla_total_size(sizeof(struct in6_addr)) /* IP6MRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; return len; } static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; struct rtgenmsg *rtgenm; struct mrt6msg *msg; struct sk_buff *skb; struct nlattr *nla; int payloadlen; payloadlen = pkt->len - sizeof(struct mrt6msg); msg = (struct mrt6msg *)skb_transport_header(pkt); skb = nlmsg_new(mrt6msg_netlink_msgsize(payloadlen), GFP_ATOMIC); if (!skb) goto errout; nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, sizeof(struct rtgenmsg), 0); if (!nlh) goto errout; rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IP6MR; if (nla_put_u8(skb, IP6MRA_CREPORT_MSGTYPE, msg->im6_msgtype) || nla_put_u32(skb, IP6MRA_CREPORT_MIF_ID, msg->im6_mif) || nla_put_in6_addr(skb, IP6MRA_CREPORT_SRC_ADDR, &msg->im6_src) || nla_put_in6_addr(skb, IP6MRA_CREPORT_DST_ADDR, &msg->im6_dst)) goto nla_put_failure; nla = nla_reserve(skb, IP6MRA_CREPORT_PKT, payloadlen); if (!nla || skb_copy_bits(pkt, sizeof(struct mrt6msg), nla_data(nla), payloadlen)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE_R, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_cancel(skb, nlh); errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS); } static const struct nla_policy ip6mr_getroute_policy[RTA_MAX + 1] = { [RTA_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [RTA_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [RTA_TABLE] = { .type = NLA_U32 }, }; static int ip6mr_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int err; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, ip6mr_getroute_policy, extack); if (err) return err; rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for multicast route get request"); return -EINVAL; } if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } return 0; } static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct in6_addr src = {}, grp = {}; struct nlattr *tb[RTA_MAX + 1]; struct mfc6_cache *cache; struct mr_table *mrt; struct sk_buff *skb; u32 tableid; int err; err = ip6mr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (tb[RTA_SRC]) src = nla_get_in6_addr(tb[RTA_SRC]); if (tb[RTA_DST]) grp = nla_get_in6_addr(tb[RTA_DST]); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = __ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT); if (!mrt) { NL_SET_ERR_MSG_MOD(extack, "MR table does not exist"); return -ENOENT; } /* entries are added/deleted only under RTNL */ rcu_read_lock(); cache = ip6mr_cache_find(mrt, &src, &grp); rcu_read_unlock(); if (!cache) { NL_SET_ERR_MSG_MOD(extack, "MR cache entry not found"); return -ENOENT; } skb = nlmsg_new(mr6_msgsize(false, mrt->maxvif), GFP_KERNEL); if (!skb) return -ENOBUFS; err = ip6mr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); if (err < 0) { kfree_skb(skb); return err; } return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct fib_dump_filter filter = { .rtnl_held = true, }; int err; if (cb->strict_check) { err = ip_valid_fib_dump_req(sock_net(skb->sk), nlh, &filter, cb); if (err < 0) return err; } if (filter.table_id) { struct mr_table *mrt; mrt = __ip6mr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR) return skb->len; NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist"); return -ENOENT; } err = mr_table_dump(mrt, skb, cb, _ip6mr_fill_mroute, &mfc_unres_lock, &filter); return skb->len ? : err; } return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter, _ip6mr_fill_mroute, &mfc_unres_lock, &filter); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct user_namespace; struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { refcount_t a_refcount; unsigned int a_count; struct rcu_head a_rcu; struct posix_acl_entry a_entries[] __counted_by(a_count); }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(unsigned int count, gfp_t flags); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); int set_posix_acl(struct mnt_idmap *, struct dentry *, int, struct posix_acl *); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); struct posix_acl *posix_acl_clone(const struct posix_acl *acl, gfp_t flags); #ifdef CONFIG_FS_POSIX_ACL int posix_acl_chmod(struct mnt_idmap *, struct dentry *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); int posix_acl_update_mode(struct mnt_idmap *, struct inode *, umode_t *, struct posix_acl **); int simple_set_acl(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); int posix_acl_valid(struct user_namespace *, const struct posix_acl *); int posix_acl_permission(struct mnt_idmap *, struct inode *, const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl); struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size); #else static inline int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } static inline int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *acl) { return -EOPNOTSUPP; } static inline struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ERR_PTR(-EOPNOTSUPP); } static inline int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return -EOPNOTSUPP; } static inline int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { return 0; } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_inode_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_CHECKSUM_H #define __ASM_CHECKSUM_H #include <linux/in6.h> #define _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum sum); static inline __sum16 csum_fold(__wsum csum) { u32 sum = (__force u32)csum; sum += (sum >> 16) | (sum << 16); return ~(__force __sum16)(sum >> 16); } #define csum_fold csum_fold static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force __wsum)(sum >> 32)); } #define ip_fast_csum ip_fast_csum extern unsigned int do_csum(const unsigned char *buff, int len); #define do_csum do_csum #include <asm-generic/checksum.h> #endif /* __ASM_CHECKSUM_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netprio_cgroup.c Priority Control Group * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/atomic.h> #include <linux/sched/task.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/netprio_cgroup.h> #include <linux/fdtable.h> /* * netprio allocates per-net_device priomap array which is indexed by * css->id. Limiting css ID to 16bits doesn't lose anything. */ #define NETPRIO_ID_MAX USHRT_MAX #define PRIOMAP_MIN_SZ 128 /* * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ static int extend_netdev_table(struct net_device *dev, u32 target_idx) { struct netprio_map *old, *new; size_t new_sz, new_len; /* is the existing priomap large enough? */ old = rtnl_dereference(dev->priomap); if (old && old->priomap_len > target_idx) return 0; /* * Determine the new size. Let's keep it power-of-two. We start * from PRIOMAP_MIN_SZ and double it until it's large enough to * accommodate @target_idx. */ new_sz = PRIOMAP_MIN_SZ; while (true) { new_len = (new_sz - offsetof(struct netprio_map, priomap)) / sizeof(new->priomap[0]); if (new_len > target_idx) break; new_sz *= 2; /* overflowed? */ if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) return -ENOSPC; } /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); if (!new) return -ENOMEM; if (old) memcpy(new->priomap, old->priomap, old->priomap_len * sizeof(old->priomap[0])); new->priomap_len = new_len; /* install the new priomap */ rcu_assign_pointer(dev->priomap, new); if (old) kfree_rcu(old, rcu); return 0; } /** * netprio_prio - return the effective netprio of a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * * Should be called under RCU read or rtnl lock. */ static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; return 0; } /** * netprio_set_prio - set netprio on a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * @prio: prio to set * * Set netprio to @prio on @css-@dev pair. Should be called under rtnl * lock and may fail under memory pressure for non-zero @prio. */ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; int id = css->id; int ret; /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); if (!prio && (!map || map->priomap_len <= id)) return 0; ret = extend_netdev_table(dev, id); if (ret) return ret; map = rtnl_dereference(dev->priomap); map->priomap[id] = prio; return 0; } static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *parent_css = css->parent; struct net_device *dev; int ret = 0; if (css->id > NETPRIO_ID_MAX) return -ENOSPC; if (!parent_css) return 0; rtnl_lock(); /* * Inherit prios from the parent. As all prios are set during * onlining, there is no need to clear them on offline. */ for_each_netdev(&init_net, dev) { u32 prio = netprio_prio(parent_css, dev); ret = netprio_set_prio(css, dev, prio); if (ret) break; } rtnl_unlock(); return ret; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css); } static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { return css->id; } static int read_priomap(struct seq_file *sf, void *v) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) seq_printf(sf, "%s %u\n", dev->name, netprio_prio(seq_css(sf), dev)); rcu_read_unlock(); return 0; } static ssize_t write_priomap(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; int ret; if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) return -ENODEV; rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); rtnl_unlock(); dev_put(dev); return ret ?: nbytes; } static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); return 0; } static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); } } static struct cftype ss_files[] = { { .name = "prioidx", .read_u64 = read_prioidx, }, { .name = "ifpriomap", .seq_show = read_priomap, .write = write_priomap, }, { } /* terminate */ }; struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, .legacy_cftypes = ss_files, }; static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* * Note this is called with rtnl_lock held so we have update side * protection on our rcu assignments */ switch (event) { case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); if (old) kfree_rcu(old, rcu); break; } return NOTIFY_DONE; } static struct notifier_block netprio_device_notifier = { .notifier_call = netprio_device_event }; static int __init init_cgroup_netprio(void) { register_netdevice_notifier(&netprio_device_notifier); return 0; } subsys_initcall(init_cgroup_netprio); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/workqueue_internal.h * * Workqueue internal header file. Only to be included by workqueue and * core kernel subsystems. */ #ifndef _KERNEL_WORKQUEUE_INTERNAL_H #define _KERNEL_WORKQUEUE_INTERNAL_H #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/preempt.h> struct worker_pool; /* * The poor guys doing the actual heavy lifting. All on-duty workers are * either serving the manager role, on idle list or on busy hash. For * details on the locking annotation (L, I, X...), refer to workqueue.c. * * Only to be used in workqueue and async. */ struct worker { /* on idle list while idle, on busy hash table while busy */ union { struct list_head entry; /* L: while idle */ struct hlist_node hentry; /* L: while busy */ }; struct work_struct *current_work; /* K: work being processed and its */ work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ /* used by the scheduler to determine a worker's last known identity */ work_func_t last_func; /* K: last work's fn */ struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* A: the associated pool */ /* L: for rescuers */ struct list_head node; /* A: anchored at pool->workers */ /* A: runs through worker->node */ unsigned long last_active; /* K: last active timestamp */ unsigned int flags; /* L: flags */ int id; /* I: worker id */ /* * Opaque string set with work_set_desc(). Printed out with task * dump for debugging - WARN, BUG, panic or sysrq. */ char desc[WORKER_DESC_LEN]; /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; /** * current_wq_worker - return struct worker if %current is a workqueue worker */ static inline struct worker *current_wq_worker(void) { if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } /* * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/ and workqueue.c. */ void wq_worker_running(struct task_struct *task); void wq_worker_sleeping(struct task_struct *task); void wq_worker_tick(struct task_struct *task); work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |
| 14 4 14 27 14 27 27 27 27 26 8 84 362 84 362 83 84 84 14 84 84 355 55 55 6 55 55 363 362 363 363 362 363 363 363 363 362 362 363 | 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 | #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/swap.h> #include <linux/rmap.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #ifndef CONFIG_MMU_GATHER_NO_GATHER static bool tlb_next_batch(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; /* Limit batching if we have delayed rmaps pending */ if (tlb->delayed_rmap && tlb->active != &tlb->local) return false; batch = tlb->active; if (batch->next) { tlb->active = batch->next; return true; } if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) return false; batch = (void *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (!batch) return false; tlb->batch_count++; batch->next = NULL; batch->nr = 0; batch->max = MAX_GATHER_BATCH; tlb->active->next = batch; tlb->active = batch; return true; } #ifdef CONFIG_SMP static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_struct *vma) { struct encoded_page **pages = batch->encoded_pages; for (int i = 0; i < batch->nr; i++) { struct encoded_page *enc = pages[i]; if (encoded_page_flags(enc) & ENCODED_PAGE_BIT_DELAY_RMAP) { struct page *page = encoded_page_ptr(enc); unsigned int nr_pages = 1; if (unlikely(encoded_page_flags(enc) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) nr_pages = encoded_nr_pages(pages[++i]); folio_remove_rmap_ptes(page_folio(page), page, nr_pages, vma); } } } /** * tlb_flush_rmaps - do pending rmap removals after we have flushed the TLB * @tlb: the current mmu_gather * @vma: The memory area from which the pages are being removed. * * Note that because of how tlb_next_batch() above works, we will * never start multiple new batches with pending delayed rmaps, so * we only need to walk through the current active batch and the * original local one. */ void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (!tlb->delayed_rmap) return; tlb_flush_rmap_batch(&tlb->local, vma); if (tlb->active != &tlb->local) tlb_flush_rmap_batch(tlb->active, vma); tlb->delayed_rmap = 0; } #endif /* * We might end up freeing a lot of pages. Reschedule on a regular * basis to avoid soft lockups in configurations without full * preemption enabled. The magic number of 512 folios seems to work. */ #define MAX_NR_FOLIOS_PER_FREE 512 static void __tlb_batch_free_encoded_pages(struct mmu_gather_batch *batch) { struct encoded_page **pages = batch->encoded_pages; unsigned int nr, nr_pages; while (batch->nr) { if (!page_poisoning_enabled_static() && !want_init_on_free()) { nr = min(MAX_NR_FOLIOS_PER_FREE, batch->nr); /* * Make sure we cover page + nr_pages, and don't leave * nr_pages behind when capping the number of entries. */ if (unlikely(encoded_page_flags(pages[nr - 1]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) nr++; } else { /* * With page poisoning and init_on_free, the time it * takes to free memory grows proportionally with the * actual memory size. Therefore, limit based on the * actual memory size and not the number of involved * folios. */ for (nr = 0, nr_pages = 0; nr < batch->nr && nr_pages < MAX_NR_FOLIOS_PER_FREE; nr++) { if (unlikely(encoded_page_flags(pages[nr]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) nr_pages += encoded_nr_pages(pages[++nr]); else nr_pages++; } } free_pages_and_swap_cache(pages, nr); pages += nr; batch->nr -= nr; cond_resched(); } } static void tlb_batch_pages_flush(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; for (batch = &tlb->local; batch && batch->nr; batch = batch->next) __tlb_batch_free_encoded_pages(batch); tlb->active = &tlb->local; } static void tlb_batch_list_free(struct mmu_gather *tlb) { struct mmu_gather_batch *batch, *next; for (batch = tlb->local.next; batch; batch = next) { next = batch->next; free_pages((unsigned long)batch, 0); } tlb->local.next = NULL; } static bool __tlb_remove_folio_pages_size(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap, int page_size) { int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0; struct mmu_gather_batch *batch; VM_BUG_ON(!tlb->end); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE VM_WARN_ON(tlb->page_size != page_size); VM_WARN_ON_ONCE(nr_pages != 1 && page_size != PAGE_SIZE); VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1)); #endif batch = tlb->active; /* * Add the page and check if we are full. If so * force a flush. */ if (likely(nr_pages == 1)) { batch->encoded_pages[batch->nr++] = encode_page(page, flags); } else { flags |= ENCODED_PAGE_BIT_NR_PAGES_NEXT; batch->encoded_pages[batch->nr++] = encode_page(page, flags); batch->encoded_pages[batch->nr++] = encode_nr_pages(nr_pages); } /* * Make sure that we can always add another "page" + "nr_pages", * requiring two entries instead of only a single one. */ if (batch->nr >= batch->max - 1) { if (!tlb_next_batch(tlb)) return true; batch = tlb->active; } VM_BUG_ON_PAGE(batch->nr > batch->max - 1, page); return false; } bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap) { return __tlb_remove_folio_pages_size(tlb, page, nr_pages, delay_rmap, PAGE_SIZE); } bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, bool delay_rmap, int page_size) { return __tlb_remove_folio_pages_size(tlb, page, 1, delay_rmap, page_size); } #endif /* MMU_GATHER_NO_GATHER */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE static void __tlb_remove_table_free(struct mmu_table_batch *batch) { int i; for (i = 0; i < batch->nr; i++) __tlb_remove_table(batch->tables[i]); free_page((unsigned long)batch); } #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * Semi RCU freeing of the page directories. * * This is needed by some architectures to implement software pagetable walkers. * * gup_fast() and other software pagetable walkers do a lockless page-table * walk and therefore needs some synchronization with the freeing of the page * directories. The chosen means to accomplish that is by disabling IRQs over * the walk. * * Architectures that use IPIs to flush TLBs will then automagically DTRT, * since we unlink the page, flush TLBs, free the page. Since the disabling of * IRQs delays the completion of the TLB flush we can never observe an already * freed page. * * Architectures that do not have this (PPC) need to delay the freeing by some * other means, this is that means. * * What we do is batch the freed directory pages (tables) and RCU free them. * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling * holds off grace periods. * * However, in order to batch these pages we need to allocate storage, this * allocation is deep inside the MM code and can thus easily fail on memory * pressure. To guarantee progress we fall back to single table freeing, see * the implementation of tlb_remove_table_one(). * */ static void tlb_remove_table_smp_sync(void *arg) { /* Simply deliver the interrupt */ } void tlb_remove_table_sync_one(void) { /* * This isn't an RCU grace period and hence the page-tables cannot be * assumed to be actually RCU-freed. * * It is however sufficient for software page-table walkers that rely on * IRQ disabling. */ smp_call_function(tlb_remove_table_smp_sync, NULL, 1); } static void tlb_remove_table_rcu(struct rcu_head *head) { __tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu)); } static void tlb_remove_table_free(struct mmu_table_batch *batch) { call_rcu(&batch->rcu, tlb_remove_table_rcu); } #else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */ static void tlb_remove_table_free(struct mmu_table_batch *batch) { __tlb_remove_table_free(batch); } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ /* * If we want tlb_remove_table() to imply TLB invalidates. */ static inline void tlb_table_invalidate(struct mmu_gather *tlb) { if (tlb_needs_table_invalidate()) { /* * Invalidate page-table caches used by hardware walkers. Then * we still need to RCU-sched wait while freeing the pages * because software walkers can still be in-flight. */ tlb_flush_mmu_tlbonly(tlb); } } static void tlb_remove_table_one(void *table) { tlb_remove_table_sync_one(); __tlb_remove_table(table); } static void tlb_table_flush(struct mmu_gather *tlb) { struct mmu_table_batch **batch = &tlb->batch; if (*batch) { tlb_table_invalidate(tlb); tlb_remove_table_free(*batch); *batch = NULL; } } void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct mmu_table_batch **batch = &tlb->batch; if (*batch == NULL) { *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { tlb_table_invalidate(tlb); tlb_remove_table_one(table); return; } (*batch)->nr = 0; } (*batch)->tables[(*batch)->nr++] = table; if ((*batch)->nr == MAX_TABLE_BATCH) tlb_table_flush(tlb); } static inline void tlb_table_init(struct mmu_gather *tlb) { tlb->batch = NULL; } #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_table_flush(struct mmu_gather *tlb) { } static inline void tlb_table_init(struct mmu_gather *tlb) { } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ static void tlb_flush_mmu_free(struct mmu_gather *tlb) { tlb_table_flush(tlb); #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_pages_flush(tlb); #endif } void tlb_flush_mmu(struct mmu_gather *tlb) { tlb_flush_mmu_tlbonly(tlb); tlb_flush_mmu_free(tlb); } static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { tlb->mm = mm; tlb->fullmm = fullmm; #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb->need_flush_all = 0; tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); tlb->active = &tlb->local; tlb->batch_count = 0; #endif tlb->delayed_rmap = 0; tlb_table_init(tlb); #ifdef CONFIG_MMU_GATHER_PAGE_SIZE tlb->page_size = 0; #endif __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } /** * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize * @mm: the mm_struct of the target address space * * Called to initialize an (on-stack) mmu_gather structure for page-table * tear-down from @mm. */ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, false); } /** * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down * @tlb: the mmu_gather structure to initialize * @mm: the mm_struct of the target address space * * In this case, @mm is without users and we're going to destroy the * full address space (exit/execve). * * Called to initialize an (on-stack) mmu_gather structure for page-table * tear-down from @mm. */ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, true); } /** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish * * Called at the end of the shootdown operation to free up any resources that * were required. */ void tlb_finish_mmu(struct mmu_gather *tlb) { /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB * flush by batching, one thread may end up seeing inconsistent PTEs * and result in having stale TLB entries. So flush TLB forcefully * if we detect parallel PTE batching threads. * * However, some syscalls, e.g. munmap(), may free page tables, this * needs force flush everything in the given range. Otherwise this * may result in having stale TLB entries for some architectures, * e.g. aarch64, that could specify flush what level TLB. */ if (mm_tlb_flush_nested(tlb->mm)) { /* * The aarch64 yields better performance with fullmm by * avoiding multiple CPUs spamming TLBI messages at the * same time. * * On x86 non-fullmm doesn't yield significant difference * against fullmm. */ tlb->fullmm = 1; __tlb_reset_range(tlb); tlb->freed_tables = 1; } tlb_flush_mmu(tlb); #ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_list_free(tlb); #endif dec_tlb_flush_pending(tlb->mm); } |
| 41 41 1016 1018 1017 1018 1016 1021 1014 41 41 41 24 36 36 41 41 41 41 92 92 1017 1016 1018 1017 1017 1017 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * FP/SIMD context switching and fault handling * * Copyright (C) 2012 ARM Ltd. * Author: Catalin Marinas <catalin.marinas@arm.com> */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bottom_half.h> #include <linux/bug.h> #include <linux/cache.h> #include <linux/compat.h> #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/linkage.h> #include <linux/irqflags.h> #include <linux/init.h> #include <linux/percpu.h> #include <linux/prctl.h> #include <linux/preempt.h> #include <linux/ptrace.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/signal.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/sysctl.h> #include <linux/swab.h> #include <asm/esr.h> #include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/neon.h> #include <asm/processor.h> #include <asm/simd.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> #include <asm/traps.h> #include <asm/virt.h> #define FPEXC_IOF (1 << 0) #define FPEXC_DZF (1 << 1) #define FPEXC_OFF (1 << 2) #define FPEXC_UFF (1 << 3) #define FPEXC_IXF (1 << 4) #define FPEXC_IDF (1 << 7) /* * (Note: in this discussion, statements about FPSIMD apply equally to SVE.) * * In order to reduce the number of times the FPSIMD state is needlessly saved * and restored, we need to keep track of two things: * (a) for each task, we need to remember which CPU was the last one to have * the task's FPSIMD state loaded into its FPSIMD registers; * (b) for each CPU, we need to remember which task's userland FPSIMD state has * been loaded into its FPSIMD registers most recently, or whether it has * been used to perform kernel mode NEON in the meantime. * * For (a), we add a fpsimd_cpu field to thread_struct, which gets updated to * the id of the current CPU every time the state is loaded onto a CPU. For (b), * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the * address of the userland FPSIMD state of the task that was loaded onto the CPU * the most recently, or NULL if kernel mode NEON has been performed after that. * * With this in place, we no longer have to restore the next FPSIMD state right * when switching between tasks. Instead, we can defer this check to userland * resume, at which time we verify whether the CPU's fpsimd_last_state and the * task's fpsimd_cpu are still mutually in sync. If this is the case, we * can omit the FPSIMD restore. * * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to * indicate whether or not the userland FPSIMD state of the current task is * present in the registers. The flag is set unless the FPSIMD registers of this * CPU currently contain the most recent userland FPSIMD state of the current * task. If the task is behaving as a VMM, then this is will be managed by * KVM which will clear it to indicate that the vcpu FPSIMD state is currently * loaded on the CPU, allowing the state to be saved if a FPSIMD-aware * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and * flag the register state as invalid. * * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be * called from softirq context, which will save the task's FPSIMD context back * to task_struct. To prevent this from racing with the manipulation of the * task's FPSIMD state from task context and thereby corrupting the state, it * is necessary to protect any manipulation of a task's fpsimd_state or * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend * softirq servicing entirely until put_cpu_fpsimd_context() is called. * * For a certain task, the sequence may look something like this: * - the task gets scheduled in; if both the task's fpsimd_cpu field * contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu * variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is * cleared, otherwise it is set; * * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's * userland FPSIMD state is copied from memory to the registers, the task's * fpsimd_cpu field is set to the id of the current CPU, the current * CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the * TIF_FOREIGN_FPSTATE flag is cleared; * * - the task executes an ordinary syscall; upon return to userland, the * TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is * restored; * * - the task executes a syscall which executes some NEON instructions; this is * preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD * register contents to memory, clears the fpsimd_last_state per-cpu variable * and sets the TIF_FOREIGN_FPSTATE flag; * * - the task gets preempted after kernel_neon_end() is called; as we have not * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so * whatever is in the FPSIMD registers is not saved to memory, but discarded. */ static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state); __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = { #ifdef CONFIG_ARM64_SVE [ARM64_VEC_SVE] = { .type = ARM64_VEC_SVE, .name = "SVE", .min_vl = SVE_VL_MIN, .max_vl = SVE_VL_MIN, .max_virtualisable_vl = SVE_VL_MIN, }, #endif #ifdef CONFIG_ARM64_SME [ARM64_VEC_SME] = { .type = ARM64_VEC_SME, .name = "SME", }, #endif }; static unsigned int vec_vl_inherit_flag(enum vec_type type) { switch (type) { case ARM64_VEC_SVE: return TIF_SVE_VL_INHERIT; case ARM64_VEC_SME: return TIF_SME_VL_INHERIT; default: WARN_ON_ONCE(1); return 0; } } struct vl_config { int __default_vl; /* Default VL for tasks */ }; static struct vl_config vl_config[ARM64_VEC_MAX]; static inline int get_default_vl(enum vec_type type) { return READ_ONCE(vl_config[type].__default_vl); } #ifdef CONFIG_ARM64_SVE static inline int get_sve_default_vl(void) { return get_default_vl(ARM64_VEC_SVE); } static inline void set_default_vl(enum vec_type type, int val) { WRITE_ONCE(vl_config[type].__default_vl, val); } static inline void set_sve_default_vl(int val) { set_default_vl(ARM64_VEC_SVE, val); } static void __percpu *efi_sve_state; #else /* ! CONFIG_ARM64_SVE */ /* Dummy declaration for code that will be optimised out: */ extern void __percpu *efi_sve_state; #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int get_sme_default_vl(void) { return get_default_vl(ARM64_VEC_SME); } static void set_sme_default_vl(int val) { set_default_vl(ARM64_VEC_SME, val); } static void sme_free(struct task_struct *); #else static inline void sme_free(struct task_struct *t) { } #endif static void fpsimd_bind_task_to_cpu(void); /* * Claim ownership of the CPU FPSIMD context for use by the calling context. * * The caller may freely manipulate the FPSIMD context metadata until * put_cpu_fpsimd_context() is called. * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom * half processing is always in thread context on RT kernels so it * implicitly prevents bottom half processing as well. */ static void get_cpu_fpsimd_context(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_disable(); else preempt_disable(); } /* * Release the CPU FPSIMD context. * * Must be called from a context in which get_cpu_fpsimd_context() was * previously called, with no call to put_cpu_fpsimd_context() in the * meantime. */ static void put_cpu_fpsimd_context(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } unsigned int task_get_vl(const struct task_struct *task, enum vec_type type) { return task->thread.vl[type]; } void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl) { task->thread.vl[type] = vl; } unsigned int task_get_vl_onexec(const struct task_struct *task, enum vec_type type) { return task->thread.vl_onexec[type]; } void task_set_vl_onexec(struct task_struct *task, enum vec_type type, unsigned long vl) { task->thread.vl_onexec[type] = vl; } /* * TIF_SME controls whether a task can use SME without trapping while * in userspace, when TIF_SME is set then we must have storage * allocated in sve_state and sme_state to store the contents of both ZA * and the SVE registers for both streaming and non-streaming modes. * * If both SVCR.ZA and SVCR.SM are disabled then at any point we * may disable TIF_SME and reenable traps. */ /* * TIF_SVE controls whether a task can use SVE without trapping while * in userspace, and also (together with TIF_SME) the way a task's * FPSIMD/SVE state is stored in thread_struct. * * The kernel uses this flag to track whether a user task is actively * using SVE, and therefore whether full SVE register state needs to * be tracked. If not, the cheaper FPSIMD context handling code can * be used instead of the more costly SVE equivalents. * * * TIF_SVE or SVCR.SM set: * * The task can execute SVE instructions while in userspace without * trapping to the kernel. * * During any syscall, the kernel may optionally clear TIF_SVE and * discard the vector state except for the FPSIMD subset. * * * TIF_SVE clear: * * An attempt by the user task to execute an SVE instruction causes * do_sve_acc() to be called, which does some preparation and then * sets TIF_SVE. * * During any syscall, the kernel may optionally clear TIF_SVE and * discard the vector state except for the FPSIMD subset. * * The data will be stored in one of two formats: * * * FPSIMD only - FP_STATE_FPSIMD: * * When the FPSIMD only state stored task->thread.fp_type is set to * FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in * task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are * logically zero but not stored anywhere; P0-P15 and FFR are not * stored and have unspecified values from userspace's point of * view. For hygiene purposes, the kernel zeroes them on next use, * but userspace is discouraged from relying on this. * * task->thread.sve_state does not need to be non-NULL, valid or any * particular size: it must not be dereferenced and any data stored * there should be considered stale and not referenced. * * * SVE state - FP_STATE_SVE: * * When the full SVE state is stored task->thread.fp_type is set to * FP_STATE_SVE and Z0-Z31 (incorporating Vn in bits[127:0] or the * corresponding Zn), P0-P15 and FFR are encoded in in * task->thread.sve_state, formatted appropriately for vector * length task->thread.sve_vl or, if SVCR.SM is set, * task->thread.sme_vl. The storage for the vector registers in * task->thread.uw.fpsimd_state should be ignored. * * task->thread.sve_state must point to a valid buffer at least * sve_state_size(task) bytes in size. The data stored in * task->thread.uw.fpsimd_state.vregs should be considered stale * and not referenced. * * * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state * irrespective of whether TIF_SVE is clear or set, since these are * not vector length dependent. */ /* * Update current's FPSIMD/SVE registers from thread_struct. * * This function should be called only when the FPSIMD/SVE state in * thread_struct is known to be up to date, when preparing to enter * userspace. */ static void task_fpsimd_load(void) { bool restore_sve_regs = false; bool restore_ffr; WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); if (system_supports_fpmr()) write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: /* Stop tracking SVE for this task until next use. */ if (test_and_clear_thread_flag(TIF_SVE)) sve_user_disable(); break; case FP_STATE_SVE: if (!thread_sm_enabled(¤t->thread) && !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE))) sve_user_enable(); if (test_thread_flag(TIF_SVE)) sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); restore_sve_regs = true; restore_ffr = true; break; default: /* * This indicates either a bug in * fpsimd_save_user_state() or memory corruption, we * should always record an explicit format * when we save. We always at least have the * memory allocated for FPSIMD registers so * try that and hope for the best. */ WARN_ON_ONCE(1); clear_thread_flag(TIF_SVE); break; } } /* Restore SME, override SVE register configuration if needed */ if (system_supports_sme()) { unsigned long sme_vl = task_get_sme_vl(current); /* Ensure VL is set up for restoring data */ if (test_thread_flag(TIF_SME)) sme_set_vq(sve_vq_from_vl(sme_vl) - 1); write_sysreg_s(current->thread.svcr, SYS_SVCR); if (thread_za_enabled(¤t->thread)) sme_load_state(current->thread.sme_state, system_supports_sme2()); if (thread_sm_enabled(¤t->thread)) restore_ffr = system_supports_fa64(); } if (restore_sve_regs) { WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE); sve_load_state(sve_pffr(¤t->thread), ¤t->thread.uw.fpsimd_state.fpsr, restore_ffr); } else { WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD); fpsimd_load_state(¤t->thread.uw.fpsimd_state); } } /* * Ensure FPSIMD/SVE storage in memory for the loaded context is up to * date with respect to the CPU registers. Note carefully that the * current context is the context last bound to the CPU stored in * last, if KVM is involved this may be the guest VM context rather * than the host thread for the VM pointed to by current. This means * that we must always reference the state storage via last rather * than via current, if we are saving KVM state then it will have * ensured that the type of registers to save is set in last->to_save. */ static void fpsimd_save_user_state(void) { struct cpu_fp_state const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ bool save_sve_regs = false; bool save_ffr; unsigned int vl; WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; if (system_supports_fpmr()) *(last->fpmr) = read_sysreg_s(SYS_FPMR); /* * If a task is in a syscall the ABI allows us to only * preserve the state shared with FPSIMD so don't bother * saving the full SVE state in that case. */ if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) && !in_syscall(current_pt_regs())) || last->to_save == FP_STATE_SVE) { save_sve_regs = true; save_ffr = true; vl = last->sve_vl; } if (system_supports_sme()) { u64 *svcr = last->svcr; *svcr = read_sysreg_s(SYS_SVCR); if (*svcr & SVCR_ZA_MASK) sme_save_state(last->sme_state, system_supports_sme2()); /* If we are in streaming mode override regular SVE. */ if (*svcr & SVCR_SM_MASK) { save_sve_regs = true; save_ffr = system_supports_fa64(); vl = last->sme_vl; } } if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) { /* Get the configured VL from RDVL, will account for SM */ if (WARN_ON(sve_get_vl() != vl)) { /* * Can't save the user regs, so current would * re-enter user with corrupt state. * There's no way to recover, so kill it: */ force_signal_inject(SIGKILL, SI_KERNEL, 0, 0); return; } sve_save_state((char *)last->sve_state + sve_ffr_offset(vl), &last->st->fpsr, save_ffr); *last->fp_type = FP_STATE_SVE; } else { fpsimd_save_state(last->st); *last->fp_type = FP_STATE_FPSIMD; } } /* * All vector length selection from userspace comes through here. * We're on a slow path, so some sanity-checks are included. * If things go wrong there's a bug somewhere, but try to fall back to a * safe choice. */ static unsigned int find_supported_vector_length(enum vec_type type, unsigned int vl) { struct vl_info *info = &vl_info[type]; int bit; int max_vl = info->max_vl; if (WARN_ON(!sve_vl_valid(vl))) vl = info->min_vl; if (WARN_ON(!sve_vl_valid(max_vl))) max_vl = info->min_vl; if (vl > max_vl) vl = max_vl; if (vl < info->min_vl) vl = info->min_vl; bit = find_next_bit(info->vq_map, SVE_VQ_MAX, __vq_to_bit(sve_vq_from_vl(vl))); return sve_vl_from_vq(__bit_to_vq(bit)); } #if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL) static int vec_proc_do_default_vl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct vl_info *info = table->extra1; enum vec_type type = info->type; int ret; int vl = get_default_vl(type); struct ctl_table tmp_table = { .data = &vl, .maxlen = sizeof(vl), }; ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); if (ret || !write) return ret; /* Writing -1 has the special meaning "set to max": */ if (vl == -1) vl = info->max_vl; if (!sve_vl_valid(vl)) return -EINVAL; set_default_vl(type, find_supported_vector_length(type, vl)); return 0; } static struct ctl_table sve_default_vl_table[] = { { .procname = "sve_default_vector_length", .mode = 0644, .proc_handler = vec_proc_do_default_vl, .extra1 = &vl_info[ARM64_VEC_SVE], }, }; static int __init sve_sysctl_init(void) { if (system_supports_sve()) if (!register_sysctl("abi", sve_default_vl_table)) return -EINVAL; return 0; } #else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) static struct ctl_table sme_default_vl_table[] = { { .procname = "sme_default_vector_length", .mode = 0644, .proc_handler = vec_proc_do_default_vl, .extra1 = &vl_info[ARM64_VEC_SME], }, }; static int __init sme_sysctl_init(void) { if (system_supports_sme()) if (!register_sysctl("abi", sme_default_vl_table)) return -EINVAL; return 0; } #else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ static int __init sme_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) #ifdef CONFIG_CPU_BIG_ENDIAN static __uint128_t arm64_cpu_to_le128(__uint128_t x) { u64 a = swab64(x); u64 b = swab64(x >> 64); return ((__uint128_t)a << 64) | b; } #else static __uint128_t arm64_cpu_to_le128(__uint128_t x) { return x; } #endif #define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, unsigned int vq) { unsigned int i; __uint128_t *p; for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t *)ZREG(sst, vq, i); *p = arm64_cpu_to_le128(fst->vregs[i]); } } /* * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to * task->thread.sve_state. * * Task can be a non-runnable task, or current. In the latter case, * the caller must have ownership of the cpu FPSIMD context before calling * this function. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.uw.fpsimd_state must be up to date before calling this * function. */ static void fpsimd_to_sve(struct task_struct *task) { unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; if (!system_supports_sve() && !system_supports_sme()) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); __fpsimd_to_sve(sst, fst, vq); } /* * Transfer the SVE state in task->thread.sve_state to * task->thread.uw.fpsimd_state. * * Task can be a non-runnable task, or current. In the latter case, * the caller must have ownership of the cpu FPSIMD context before calling * this function. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.sve_state must be up to date before calling this function. */ static void sve_to_fpsimd(struct task_struct *task) { unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; __uint128_t const *p; if (!system_supports_sve() && !system_supports_sme()) return; vl = thread_get_cur_vl(&task->thread); vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); } } void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK, SYS_SCTLR_EL1); } #ifdef CONFIG_ARM64_SVE /* * Call __sve_free() directly only if you know task can't be scheduled * or preempted. */ static void __sve_free(struct task_struct *task) { kfree(task->thread.sve_state); task->thread.sve_state = NULL; } static void sve_free(struct task_struct *task) { WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); __sve_free(task); } /* * Return how many bytes of memory are required to store the full SVE * state for task, given task's currently configured vector length. */ size_t sve_state_size(struct task_struct const *task) { unsigned int vl = 0; if (system_supports_sve()) vl = task_get_sve_vl(task); if (system_supports_sme()) vl = max(vl, task_get_sme_vl(task)); return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); } /* * Ensure that task->thread.sve_state is allocated and sufficiently large. * * This function should be used only in preparation for replacing * task->thread.sve_state with new data. The memory is always zeroed * here to prevent stale data from showing through: this is done in * the interest of testability and predictability: except in the * do_sve_acc() case, there is no ABI requirement to hide stale data * written previously be task. */ void sve_alloc(struct task_struct *task, bool flush) { if (task->thread.sve_state) { if (flush) memset(task->thread.sve_state, 0, sve_state_size(task)); return; } /* This is a small allocation (maximum ~8KB) and Should Not Fail. */ task->thread.sve_state = kzalloc(sve_state_size(task), GFP_KERNEL); } /* * Force the FPSIMD state shared with SVE to be updated in the SVE state * even if the SVE state is the current active state. * * This should only be called by ptrace. task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. */ void fpsimd_force_sync_to_sve(struct task_struct *task) { fpsimd_to_sve(task); } /* * Ensure that task->thread.sve_state is up to date with respect to * the user task, irrespective of when SVE is in use or not. * * This should only be called by ptrace. task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. */ void fpsimd_sync_to_sve(struct task_struct *task) { if (!test_tsk_thread_flag(task, TIF_SVE) && !thread_sm_enabled(&task->thread)) fpsimd_to_sve(task); } /* * Ensure that task->thread.uw.fpsimd_state is up to date with respect to * the user task, irrespective of whether SVE is in use or not. * * This should only be called by ptrace. task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. */ void sve_sync_to_fpsimd(struct task_struct *task) { if (task->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(task); } /* * Ensure that task->thread.sve_state is up to date with respect to * the task->thread.uw.fpsimd_state. * * This should only be called by ptrace to merge new FPSIMD register * values into a task for which SVE is currently active. * task must be non-runnable. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.uw.fpsimd_state must already have been initialised with * the new FPSIMD register values to be merged in. */ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; if (!test_tsk_thread_flag(task, TIF_SVE) && !thread_sm_enabled(&task->thread)) return; vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); __fpsimd_to_sve(sst, fst, vq); } int vec_set_vector_length(struct task_struct *task, enum vec_type type, unsigned long vl, unsigned long flags) { bool free_sme = false; if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT | PR_SVE_SET_VL_ONEXEC)) return -EINVAL; if (!sve_vl_valid(vl)) return -EINVAL; /* * Clamp to the maximum vector length that VL-agnostic code * can work with. A flag may be assigned in the future to * allow setting of larger vector lengths without confusing * older software. */ if (vl > VL_ARCH_MAX) vl = VL_ARCH_MAX; vl = find_supported_vector_length(type, vl); if (flags & (PR_SVE_VL_INHERIT | PR_SVE_SET_VL_ONEXEC)) task_set_vl_onexec(task, type, vl); else /* Reset VL to system default on next exec: */ task_set_vl_onexec(task, type, 0); /* Only actually set the VL if not deferred: */ if (flags & PR_SVE_SET_VL_ONEXEC) goto out; if (vl == task_get_vl(task, type)) goto out; /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); fpsimd_save_user_state(); } fpsimd_flush_task_state(task); if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || thread_sm_enabled(&task->thread)) { sve_to_fpsimd(task); task->thread.fp_type = FP_STATE_FPSIMD; } if (system_supports_sme()) { if (type == ARM64_VEC_SME || !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) { /* * We are changing the SME VL or weren't using * SME anyway, discard the state and force a * reallocation. */ task->thread.svcr &= ~(SVCR_SM_MASK | SVCR_ZA_MASK); clear_tsk_thread_flag(task, TIF_SME); free_sme = true; } } if (task == current) put_cpu_fpsimd_context(); task_set_vl(task, type, vl); /* * Free the changed states if they are not in use, SME will be * reallocated to the correct size on next use and we just * allocate SVE now in case it is needed for use in streaming * mode. */ sve_free(task); sve_alloc(task, true); if (free_sme) sme_free(task); out: update_tsk_thread_flag(task, vec_vl_inherit_flag(type), flags & PR_SVE_VL_INHERIT); return 0; } /* * Encode the current vector length and flags for return. * This is only required for prctl(): ptrace has separate fields. * SVE and SME use the same bits for _ONEXEC and _INHERIT. * * flags are as for vec_set_vector_length(). */ static int vec_prctl_status(enum vec_type type, unsigned long flags) { int ret; if (flags & PR_SVE_SET_VL_ONEXEC) ret = task_get_vl_onexec(current, type); else ret = task_get_vl(current, type); if (test_thread_flag(vec_vl_inherit_flag(type))) ret |= PR_SVE_VL_INHERIT; return ret; } /* PR_SVE_SET_VL */ int sve_set_current_vl(unsigned long arg) { unsigned long vl, flags; int ret; vl = arg & PR_SVE_VL_LEN_MASK; flags = arg & ~vl; if (!system_supports_sve() || is_compat_task()) return -EINVAL; ret = vec_set_vector_length(current, ARM64_VEC_SVE, vl, flags); if (ret) return ret; return vec_prctl_status(ARM64_VEC_SVE, flags); } /* PR_SVE_GET_VL */ int sve_get_current_vl(void) { if (!system_supports_sve() || is_compat_task()) return -EINVAL; return vec_prctl_status(ARM64_VEC_SVE, 0); } #ifdef CONFIG_ARM64_SME /* PR_SME_SET_VL */ int sme_set_current_vl(unsigned long arg) { unsigned long vl, flags; int ret; vl = arg & PR_SME_VL_LEN_MASK; flags = arg & ~vl; if (!system_supports_sme() || is_compat_task()) return -EINVAL; ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags); if (ret) return ret; return vec_prctl_status(ARM64_VEC_SME, flags); } /* PR_SME_GET_VL */ int sme_get_current_vl(void) { if (!system_supports_sme() || is_compat_task()) return -EINVAL; return vec_prctl_status(ARM64_VEC_SME, 0); } #endif /* CONFIG_ARM64_SME */ static void vec_probe_vqs(struct vl_info *info, DECLARE_BITMAP(map, SVE_VQ_MAX)) { unsigned int vq, vl; bitmap_zero(map, SVE_VQ_MAX); for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) { write_vl(info->type, vq - 1); /* self-syncing */ switch (info->type) { case ARM64_VEC_SVE: vl = sve_get_vl(); break; case ARM64_VEC_SME: vl = sme_get_vl(); break; default: vl = 0; break; } /* Minimum VL identified? */ if (sve_vq_from_vl(vl) > vq) break; vq = sve_vq_from_vl(vl); /* skip intervening lengths */ set_bit(__vq_to_bit(vq), map); } } /* * Initialise the set of known supported VQs for the boot CPU. * This is called during kernel boot, before secondary CPUs are brought up. */ void __init vec_init_vq_map(enum vec_type type) { struct vl_info *info = &vl_info[type]; vec_probe_vqs(info, info->vq_map); bitmap_copy(info->vq_partial_map, info->vq_map, SVE_VQ_MAX); } /* * If we haven't committed to the set of supported VQs yet, filter out * those not supported by the current CPU. * This function is called during the bring-up of early secondary CPUs only. */ void vec_update_vq_map(enum vec_type type) { struct vl_info *info = &vl_info[type]; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); vec_probe_vqs(info, tmp_map); bitmap_and(info->vq_map, info->vq_map, tmp_map, SVE_VQ_MAX); bitmap_or(info->vq_partial_map, info->vq_partial_map, tmp_map, SVE_VQ_MAX); } /* * Check whether the current CPU supports all VQs in the committed set. * This function is called during the bring-up of late secondary CPUs only. */ int vec_verify_vq_map(enum vec_type type) { struct vl_info *info = &vl_info[type]; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); unsigned long b; vec_probe_vqs(info, tmp_map); bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX); if (bitmap_intersects(tmp_map, info->vq_map, SVE_VQ_MAX)) { pr_warn("%s: cpu%d: Required vector length(s) missing\n", info->name, smp_processor_id()); return -EINVAL; } if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available()) return 0; /* * For KVM, it is necessary to ensure that this CPU doesn't * support any vector length that guests may have probed as * unsupported. */ /* Recover the set of supported VQs: */ bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX); /* Find VQs supported that are not globally supported: */ bitmap_andnot(tmp_map, tmp_map, info->vq_map, SVE_VQ_MAX); /* Find the lowest such VQ, if any: */ b = find_last_bit(tmp_map, SVE_VQ_MAX); if (b >= SVE_VQ_MAX) return 0; /* no mismatches */ /* * Mismatches above sve_max_virtualisable_vl are fine, since * no guest is allowed to configure ZCR_EL2.LEN to exceed this: */ if (sve_vl_from_vq(__bit_to_vq(b)) <= info->max_virtualisable_vl) { pr_warn("%s: cpu%d: Unsupported vector length(s) present\n", info->name, smp_processor_id()); return -EINVAL; } return 0; } static void __init sve_efi_setup(void) { int max_vl = 0; int i; if (!IS_ENABLED(CONFIG_EFI)) return; for (i = 0; i < ARRAY_SIZE(vl_info); i++) max_vl = max(vl_info[i].max_vl, max_vl); /* * alloc_percpu() warns and prints a backtrace if this goes wrong. * This is evidence of a crippled system and we are returning void, * so no attempt is made to handle this situation here. */ if (!sve_vl_valid(max_vl)) goto fail; efi_sve_state = __alloc_percpu( SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES); if (!efi_sve_state) goto fail; return; fail: panic("Cannot allocate percpu memory for EFI SVE save/restore"); } void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1); isb(); write_sysreg_s(0, SYS_ZCR_EL1); } void __init sve_setup(void) { struct vl_info *info = &vl_info[ARM64_VEC_SVE]; DECLARE_BITMAP(tmp_map, SVE_VQ_MAX); unsigned long b; int max_bit; if (!system_supports_sve()) return; /* * The SVE architecture mandates support for 128-bit vectors, * so sve_vq_map must have at least SVE_VQ_MIN set. * If something went wrong, at least try to patch it up: */ if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map))) set_bit(__vq_to_bit(SVE_VQ_MIN), info->vq_map); max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX); info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit)); /* * For the default VL, pick the maximum supported value <= 64. * VL == 64 is guaranteed not to grow the signal frame. */ set_sve_default_vl(find_supported_vector_length(ARM64_VEC_SVE, 64)); bitmap_andnot(tmp_map, info->vq_partial_map, info->vq_map, SVE_VQ_MAX); b = find_last_bit(tmp_map, SVE_VQ_MAX); if (b >= SVE_VQ_MAX) /* No non-virtualisable VLs found */ info->max_virtualisable_vl = SVE_VQ_MAX; else if (WARN_ON(b == SVE_VQ_MAX - 1)) /* No virtualisable VLs? This is architecturally forbidden. */ info->max_virtualisable_vl = SVE_VQ_MIN; else /* b + 1 < SVE_VQ_MAX */ info->max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1)); if (info->max_virtualisable_vl > info->max_vl) info->max_virtualisable_vl = info->max_vl; pr_info("%s: maximum available vector length %u bytes per vector\n", info->name, info->max_vl); pr_info("%s: default vector length %u bytes per vector\n", info->name, get_sve_default_vl()); /* KVM decides whether to support mismatched systems. Just warn here: */ if (sve_max_virtualisable_vl() < sve_max_vl()) pr_warn("%s: unvirtualisable vector lengths present\n", info->name); sve_efi_setup(); } /* * Called from the put_task_struct() path, which cannot get here * unless dead_task is really dead and not schedulable. */ void fpsimd_release_task(struct task_struct *dead_task) { __sve_free(dead_task); sme_free(dead_task); } #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME /* * Ensure that task->thread.sme_state is allocated and sufficiently large. * * This function should be used only in preparation for replacing * task->thread.sme_state with new data. The memory is always zeroed * here to prevent stale data from showing through: this is done in * the interest of testability and predictability, the architecture * guarantees that when ZA is enabled it will be zeroed. */ void sme_alloc(struct task_struct *task, bool flush) { if (task->thread.sme_state) { if (flush) memset(task->thread.sme_state, 0, sme_state_size(task)); return; } /* This could potentially be up to 64K. */ task->thread.sme_state = kzalloc(sme_state_size(task), GFP_KERNEL); } static void sme_free(struct task_struct *task) { kfree(task->thread.sme_state); task->thread.sme_state = NULL; } void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p) { /* Set priority for all PEs to architecturally defined minimum */ write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK, SYS_SMPRI_EL1); /* Allow SME in kernel */ write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); isb(); /* Ensure all bits in SMCR are set to known values */ write_sysreg_s(0, SYS_SMCR_EL1); /* Allow EL0 to access TPIDR2 */ write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); isb(); } void cpu_enable_sme2(const struct arm64_cpu_capabilities *__always_unused p) { /* This must be enabled after SME */ BUILD_BUG_ON(ARM64_SME2 <= ARM64_SME); /* Allow use of ZT0 */ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK, SYS_SMCR_EL1); } void cpu_enable_fa64(const struct arm64_cpu_capabilities *__always_unused p) { /* This must be enabled after SME */ BUILD_BUG_ON(ARM64_SME_FA64 <= ARM64_SME); /* Allow use of FA64 */ write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK, SYS_SMCR_EL1); } void __init sme_setup(void) { struct vl_info *info = &vl_info[ARM64_VEC_SME]; int min_bit, max_bit; if (!system_supports_sme()) return; /* * SME doesn't require any particular vector length be * supported but it does require at least one. We should have * disabled the feature entirely while bringing up CPUs but * let's double check here. The bitmap is SVE_VQ_MAP sized for * sharing with SVE. */ WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX)); min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX); info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit)); max_bit = find_first_bit(info->vq_map, SVE_VQ_MAX); info->max_vl = sve_vl_from_vq(__bit_to_vq(max_bit)); WARN_ON(info->min_vl > info->max_vl); /* * For the default VL, pick the maximum supported value <= 32 * (256 bits) if there is one since this is guaranteed not to * grow the signal frame when in streaming mode, otherwise the * minimum available VL will be used. */ set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32)); pr_info("SME: minimum available vector length %u bytes per vector\n", info->min_vl); pr_info("SME: maximum available vector length %u bytes per vector\n", info->max_vl); pr_info("SME: default vector length %u bytes per vector\n", get_sme_default_vl()); } void sme_suspend_exit(void) { u64 smcr = 0; if (!system_supports_sme()) return; if (system_supports_fa64()) smcr |= SMCR_ELx_FA64; if (system_supports_sme2()) smcr |= SMCR_ELx_EZT0; write_sysreg_s(smcr, SYS_SMCR_EL1); write_sysreg_s(0, SYS_SMPRI_EL1); } #endif /* CONFIG_ARM64_SME */ static void sve_init_regs(void) { /* * Convert the FPSIMD state to SVE, zeroing all the state that * is not shared with FPSIMD. If (as is likely) the current * state is live in the registers then do this there and * update our metadata for the current task including * disabling the trap, otherwise update our in-memory copy. * We are guaranteed to not be in streaming mode, we can only * take a SVE trap when not in streaming mode and we can't be * in streaming mode when taking a SME trap. */ if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; sve_set_vq(vq_minus_one); sve_flush_live(true, vq_minus_one); fpsimd_bind_task_to_cpu(); } else { fpsimd_to_sve(current); current->thread.fp_type = FP_STATE_SVE; fpsimd_flush_task_state(current); } } /* * Trapped SVE access * * Storage is allocated for the full SVE state, the current FPSIMD * register contents are migrated across, and the access trap is * disabled. * * TIF_SVE should be clear on entry: otherwise, fpsimd_restore_current_state() * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ void do_sve_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } sve_alloc(current, true); if (!current->thread.sve_state) { force_sig(SIGKILL); return; } get_cpu_fpsimd_context(); if (test_and_set_thread_flag(TIF_SVE)) WARN_ON(1); /* SVE access shouldn't have trapped */ /* * Even if the task can have used streaming mode we can only * generate SVE access traps in normal SVE mode and * transitioning out of streaming mode may discard any * streaming mode state. Always clear the high bits to avoid * any potential errors tracking what is properly initialised. */ sve_init_regs(); put_cpu_fpsimd_context(); } /* * Trapped SME access * * Storage is allocated for the full SVE and SME state, the current * FPSIMD register contents are migrated to SVE if SVE is not already * active, and the access trap is disabled. * * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state() * would have disabled the SME access trap for userspace during * ret_to_user, making an SME access trap impossible in that case. */ void do_sme_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use SME, the hardware could still trap: */ if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } /* * If this not a trap due to SME being disabled then something * is being used in the wrong mode, report as SIGILL. */ if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } sve_alloc(current, false); sme_alloc(current, true); if (!current->thread.sve_state || !current->thread.sme_state) { force_sig(SIGKILL); return; } get_cpu_fpsimd_context(); /* With TIF_SME userspace shouldn't generate any traps */ if (test_and_set_thread_flag(TIF_SME)) WARN_ON(1); if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = sve_vq_from_vl(task_get_sme_vl(current)) - 1; sme_set_vq(vq_minus_one); fpsimd_bind_task_to_cpu(); } put_cpu_fpsimd_context(); } /* * Trapped FP/ASIMD access. */ void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs) { /* Even if we chose not to use FPSIMD, the hardware could still trap: */ if (!system_supports_fpsimd()) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } /* * When FPSIMD is enabled, we should never take a trap unless something * has gone very wrong. */ BUG(); } /* * Raise a SIGFPE for the current process. */ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; if (esr & ESR_ELx_FP_EXC_TFV) { if (esr & FPEXC_IOF) si_code = FPE_FLTINV; else if (esr & FPEXC_DZF) si_code = FPE_FLTDIV; else if (esr & FPEXC_OFF) si_code = FPE_FLTOVF; else if (esr & FPEXC_UFF) si_code = FPE_FLTUND; else if (esr & FPEXC_IXF) si_code = FPE_FLTRES; } send_sig_fault(SIGFPE, si_code, (void __user *)instruction_pointer(regs), current); } static void fpsimd_load_kernel_state(struct task_struct *task) { struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); /* * Elide the load if this CPU holds the most recent kernel mode * FPSIMD context of the current task. */ if (last->st == &task->thread.kernel_fpsimd_state && task->thread.kernel_fpsimd_cpu == smp_processor_id()) return; fpsimd_load_state(&task->thread.kernel_fpsimd_state); } static void fpsimd_save_kernel_state(struct task_struct *task) { struct cpu_fp_state cpu_fp_state = { .st = &task->thread.kernel_fpsimd_state, .to_save = FP_STATE_FPSIMD, }; fpsimd_save_state(&task->thread.kernel_fpsimd_state); fpsimd_bind_state_to_cpu(&cpu_fp_state); task->thread.kernel_fpsimd_cpu = smp_processor_id(); } /* * Invalidate any task's FPSIMD state that is present on this cpu. * The FPSIMD context should be acquired with get_cpu_fpsimd_context() * before calling this function. */ static void fpsimd_flush_cpu_state(void) { WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); /* * Leaving streaming mode enabled will cause issues for any kernel * NEON and leaving streaming mode or ZA enabled may increase power * consumption. */ if (system_supports_sme()) sme_smstop(); set_thread_flag(TIF_FOREIGN_FPSTATE); } void fpsimd_thread_switch(struct task_struct *next) { bool wrong_task, wrong_cpu; if (!system_supports_fpsimd()) return; WARN_ON_ONCE(!irqs_disabled()); /* Save unsaved fpsimd state, if any: */ if (test_thread_flag(TIF_KERNEL_FPSTATE)) fpsimd_save_kernel_state(current); else fpsimd_save_user_state(); if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) { fpsimd_load_kernel_state(next); fpsimd_flush_cpu_state(); } else { /* * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's * state. For kernel threads, FPSIMD registers are never * loaded with user mode FPSIMD state and so wrong_task and * wrong_cpu will always be true. */ wrong_task = __this_cpu_read(fpsimd_last_state.st) != &next->thread.uw.fpsimd_state; wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, wrong_task || wrong_cpu); } } static void fpsimd_flush_thread_vl(enum vec_type type) { int vl, supported_vl; /* * Reset the task vector length as required. This is where we * ensure that all user tasks have a valid vector length * configured: no kernel task can become a user task without * an exec and hence a call to this function. By the time the * first call to this function is made, all early hardware * probing is complete, so __sve_default_vl should be valid. * If a bug causes this to go wrong, we make some noise and * try to fudge thread.sve_vl to a safe value here. */ vl = task_get_vl_onexec(current, type); if (!vl) vl = get_default_vl(type); if (WARN_ON(!sve_vl_valid(vl))) vl = vl_info[type].min_vl; supported_vl = find_supported_vector_length(type, vl); if (WARN_ON(supported_vl != vl)) vl = supported_vl; task_set_vl(current, type, vl); /* * If the task is not set to inherit, ensure that the vector * length will be reset by a subsequent exec: */ if (!test_thread_flag(vec_vl_inherit_flag(type))) task_set_vl_onexec(current, type, 0); } void fpsimd_flush_thread(void) { void *sve_state = NULL; void *sme_state = NULL; if (!system_supports_fpsimd()) return; get_cpu_fpsimd_context(); fpsimd_flush_task_state(current); memset(¤t->thread.uw.fpsimd_state, 0, sizeof(current->thread.uw.fpsimd_state)); if (system_supports_sve()) { clear_thread_flag(TIF_SVE); /* Defer kfree() while in atomic context */ sve_state = current->thread.sve_state; current->thread.sve_state = NULL; fpsimd_flush_thread_vl(ARM64_VEC_SVE); } if (system_supports_sme()) { clear_thread_flag(TIF_SME); /* Defer kfree() while in atomic context */ sme_state = current->thread.sme_state; current->thread.sme_state = NULL; fpsimd_flush_thread_vl(ARM64_VEC_SME); current->thread.svcr = 0; } current->thread.fp_type = FP_STATE_FPSIMD; put_cpu_fpsimd_context(); kfree(sve_state); kfree(sme_state); } /* * Save the userland FPSIMD state of 'current' to memory, but only if the state * currently held in the registers does in fact belong to 'current' */ void fpsimd_preserve_current_state(void) { if (!system_supports_fpsimd()) return; get_cpu_fpsimd_context(); fpsimd_save_user_state(); put_cpu_fpsimd_context(); } /* * Like fpsimd_preserve_current_state(), but ensure that * current->thread.uw.fpsimd_state is updated so that it can be copied to * the signal frame. */ void fpsimd_signal_preserve_current_state(void) { fpsimd_preserve_current_state(); if (current->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(current); } /* * Called by KVM when entering the guest. */ void fpsimd_kvm_prepare(void) { if (!system_supports_sve()) return; /* * KVM does not save host SVE state since we can only enter * the guest from a syscall so the ABI means that only the * non-saved SVE state needs to be saved. If we have left * SVE enabled for performance reasons then update the task * state to be FPSIMD only. */ get_cpu_fpsimd_context(); if (test_and_clear_thread_flag(TIF_SVE)) { sve_to_fpsimd(current); current->thread.fp_type = FP_STATE_FPSIMD; } put_cpu_fpsimd_context(); } /* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling * this function. */ static void fpsimd_bind_task_to_cpu(void) { struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sme_state = current->thread.sme_state; last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; last->fpmr = ¤t->thread.uw.fpmr; last->fp_type = ¤t->thread.fp_type; last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id(); /* * Toggle SVE and SME trapping for userspace if needed, these * are serialsied by ret_to_user(). */ if (system_supports_sme()) { if (test_thread_flag(TIF_SME)) sme_user_enable(); else sme_user_disable(); } if (system_supports_sve()) { if (test_thread_flag(TIF_SVE)) sve_user_enable(); else sve_user_disable(); } } void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state) { struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); WARN_ON(!system_supports_fpsimd()); WARN_ON(!in_softirq() && !irqs_disabled()); *last = *state; } /* * Load the userland FPSIMD state of 'current' from memory, but only if the * FPSIMD state already held in the registers is /not/ the most recent FPSIMD * state of 'current'. This is called when we are preparing to return to * userspace to ensure that userspace sees a good register state. */ void fpsimd_restore_current_state(void) { /* * TIF_FOREIGN_FPSTATE is set on the init task and copied by * arch_dup_task_struct() regardless of whether FP/SIMD is detected. * Thus user threads can have this set even when FP/SIMD hasn't been * detected. * * When FP/SIMD is detected, begin_new_exec() will set * TIF_FOREIGN_FPSTATE via flush_thread() -> fpsimd_flush_thread(), * and fpsimd_thread_switch() will set TIF_FOREIGN_FPSTATE when * switching tasks. We detect FP/SIMD before we exec the first user * process, ensuring this has TIF_FOREIGN_FPSTATE set and * do_notify_resume() will call fpsimd_restore_current_state() to * install the user FP/SIMD context. * * When FP/SIMD is not detected, nothing else will clear or set * TIF_FOREIGN_FPSTATE prior to the first return to userspace, and * we must clear TIF_FOREIGN_FPSTATE to avoid do_notify_resume() * looping forever calling fpsimd_restore_current_state(). */ if (!system_supports_fpsimd()) { clear_thread_flag(TIF_FOREIGN_FPSTATE); return; } get_cpu_fpsimd_context(); if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { task_fpsimd_load(); fpsimd_bind_task_to_cpu(); } put_cpu_fpsimd_context(); } /* * Load an updated userland FPSIMD state for 'current' from memory and set the * flag that indicates that the FPSIMD register contents are the most recent * FPSIMD state of 'current'. This is used by the signal code to restore the * register state when returning from a signal handler in FPSIMD only cases, * any SVE context will be discarded. */ void fpsimd_update_current_state(struct user_fpsimd_state const *state) { if (WARN_ON(!system_supports_fpsimd())) return; get_cpu_fpsimd_context(); current->thread.uw.fpsimd_state = *state; if (test_thread_flag(TIF_SVE)) fpsimd_to_sve(current); task_fpsimd_load(); fpsimd_bind_task_to_cpu(); clear_thread_flag(TIF_FOREIGN_FPSTATE); put_cpu_fpsimd_context(); } /* * Invalidate live CPU copies of task t's FPSIMD state * * This function may be called with preemption enabled. The barrier() * ensures that the assignment to fpsimd_cpu is visible to any * preemption/softirq that could race with set_tsk_thread_flag(), so * that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared. * * The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any * subsequent code. */ void fpsimd_flush_task_state(struct task_struct *t) { t->thread.fpsimd_cpu = NR_CPUS; /* * If we don't support fpsimd, bail out after we have * reset the fpsimd_cpu for this task and clear the * FPSTATE. */ if (!system_supports_fpsimd()) return; barrier(); set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE); barrier(); } /* * Save the FPSIMD state to memory and invalidate cpu view. * This function must be called with preemption disabled. */ void fpsimd_save_and_flush_cpu_state(void) { unsigned long flags; if (!system_supports_fpsimd()) return; WARN_ON(preemptible()); local_irq_save(flags); fpsimd_save_user_state(); fpsimd_flush_cpu_state(); local_irq_restore(flags); } #ifdef CONFIG_KERNEL_MODE_NEON /* * Kernel-side NEON support functions */ /* * kernel_neon_begin(): obtain the CPU FPSIMD registers for use by the calling * context * * Must not be called unless may_use_simd() returns true. * Task context in the FPSIMD registers is saved back to memory as necessary. * * A matching call to kernel_neon_end() must be made before returning from the * calling context. * * The caller may freely use the FPSIMD registers until kernel_neon_end() is * called. */ void kernel_neon_begin(void) { if (WARN_ON(!system_supports_fpsimd())) return; BUG_ON(!may_use_simd()); get_cpu_fpsimd_context(); /* Save unsaved fpsimd state, if any: */ if (test_thread_flag(TIF_KERNEL_FPSTATE)) { BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()); fpsimd_save_kernel_state(current); } else { fpsimd_save_user_state(); /* * Set the thread flag so that the kernel mode FPSIMD state * will be context switched along with the rest of the task * state. * * On non-PREEMPT_RT, softirqs may interrupt task level kernel * mode FPSIMD, but the task will not be preemptible so setting * TIF_KERNEL_FPSTATE for those would be both wrong (as it * would mark the task context FPSIMD state as requiring a * context switch) and unnecessary. * * On PREEMPT_RT, softirqs are serviced from a separate thread, * which is scheduled as usual, and this guarantees that these * softirqs are not interrupting use of the FPSIMD in kernel * mode in task context. So in this case, setting the flag here * is always appropriate. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()) set_thread_flag(TIF_KERNEL_FPSTATE); } /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); put_cpu_fpsimd_context(); } EXPORT_SYMBOL_GPL(kernel_neon_begin); /* * kernel_neon_end(): give the CPU FPSIMD registers back to the current task * * Must be called from a context in which kernel_neon_begin() was previously * called, with no call to kernel_neon_end() in the meantime. * * The caller must not use the FPSIMD registers after this function is called, * unless kernel_neon_begin() is called again in the meantime. */ void kernel_neon_end(void) { if (!system_supports_fpsimd()) return; /* * If we are returning from a nested use of kernel mode FPSIMD, restore * the task context kernel mode FPSIMD state. This can only happen when * running in softirq context on non-PREEMPT_RT. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() && test_thread_flag(TIF_KERNEL_FPSTATE)) fpsimd_load_kernel_state(current); else clear_thread_flag(TIF_KERNEL_FPSTATE); } EXPORT_SYMBOL_GPL(kernel_neon_end); #ifdef CONFIG_EFI static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); static DEFINE_PER_CPU(bool, efi_sve_state_used); static DEFINE_PER_CPU(bool, efi_sm_state); /* * EFI runtime services support functions * * The ABI for EFI runtime services allows EFI to use FPSIMD during the call. * This means that for EFI (and only for EFI), we have to assume that FPSIMD * is always used rather than being an optional accelerator. * * These functions provide the necessary support for ensuring FPSIMD * save/restore in the contexts from which EFI is used. * * Do not use them for any other purpose -- if tempted to do so, you are * either doing something wrong or you need to propose some refactoring. */ /* * __efi_fpsimd_begin(): prepare FPSIMD for making an EFI runtime services call */ void __efi_fpsimd_begin(void) { if (!system_supports_fpsimd()) return; WARN_ON(preemptible()); if (may_use_simd()) { kernel_neon_begin(); } else { /* * If !efi_sve_state, SVE can't be in use yet and doesn't need * preserving: */ if (system_supports_sve() && likely(efi_sve_state)) { char *sve_state = this_cpu_ptr(efi_sve_state); bool ffr = true; u64 svcr; __this_cpu_write(efi_sve_state_used, true); if (system_supports_sme()) { svcr = read_sysreg_s(SYS_SVCR); __this_cpu_write(efi_sm_state, svcr & SVCR_SM_MASK); /* * Unless we have FA64 FFR does not * exist in streaming mode. */ if (!system_supports_fa64()) ffr = !(svcr & SVCR_SM_MASK); } sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, ffr); if (system_supports_sme()) sysreg_clear_set_s(SYS_SVCR, SVCR_SM_MASK, 0); } else { fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state)); } __this_cpu_write(efi_fpsimd_state_used, true); } } /* * __efi_fpsimd_end(): clean up FPSIMD after an EFI runtime services call */ void __efi_fpsimd_end(void) { if (!system_supports_fpsimd()) return; if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) { kernel_neon_end(); } else { if (system_supports_sve() && likely(__this_cpu_read(efi_sve_state_used))) { char const *sve_state = this_cpu_ptr(efi_sve_state); bool ffr = true; /* * Restore streaming mode; EFI calls are * normal function calls so should not return in * streaming mode. */ if (system_supports_sme()) { if (__this_cpu_read(efi_sm_state)) { sysreg_clear_set_s(SYS_SVCR, 0, SVCR_SM_MASK); /* * Unless we have FA64 FFR does not * exist in streaming mode. */ if (!system_supports_fa64()) ffr = false; } } sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, ffr); __this_cpu_write(efi_sve_state_used, false); } else { fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state)); } } } #endif /* CONFIG_EFI */ #endif /* CONFIG_KERNEL_MODE_NEON */ #ifdef CONFIG_CPU_PM static int fpsimd_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { switch (cmd) { case CPU_PM_ENTER: fpsimd_save_and_flush_cpu_state(); break; case CPU_PM_EXIT: break; case CPU_PM_ENTER_FAILED: default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block fpsimd_cpu_pm_notifier_block = { .notifier_call = fpsimd_cpu_pm_notifier, }; static void __init fpsimd_pm_init(void) { cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block); } #else static inline void fpsimd_pm_init(void) { } #endif /* CONFIG_CPU_PM */ #ifdef CONFIG_HOTPLUG_CPU static int fpsimd_cpu_dead(unsigned int cpu) { per_cpu(fpsimd_last_state.st, cpu) = NULL; return 0; } static inline void fpsimd_hotplug_init(void) { cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead", NULL, fpsimd_cpu_dead); } #else static inline void fpsimd_hotplug_init(void) { } #endif void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__always_unused p) { unsigned long enable = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN; write_sysreg(read_sysreg(CPACR_EL1) | enable, CPACR_EL1); isb(); } /* * FP/SIMD support code initialisation. */ static int __init fpsimd_init(void) { if (cpu_have_named_feature(FP)) { fpsimd_pm_init(); fpsimd_hotplug_init(); } else { pr_notice("Floating-point is not implemented\n"); } if (!cpu_have_named_feature(ASIMD)) pr_notice("Advanced SIMD is not implemented\n"); sve_sysctl_init(); sme_sysctl_init(); return 0; } core_initcall(fpsimd_init); |
| 56 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 | // SPDX-License-Identifier: GPL-2.0-only /* * Handle detection, reporting and mitigation of Spectre v1, v2, v3a and v4, as * detailed at: * * https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability * * This code was originally written hastily under an awful lot of stress and so * aspects of it are somewhat hacky. Unfortunately, changing anything in here * instantly makes me feel ill. Thanks, Jann. Thann. * * Copyright (C) 2018 ARM Ltd, All Rights Reserved. * Copyright (C) 2020 Google LLC * * "If there's something strange in your neighbourhood, who you gonna call?" * * Authors: Will Deacon <will@kernel.org> and Marc Zyngier <maz@kernel.org> */ #include <linux/arm-smccc.h> #include <linux/bpf.h> #include <linux/cpu.h> #include <linux/device.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched/task_stack.h> #include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/spectre.h> #include <asm/traps.h> #include <asm/vectors.h> #include <asm/virt.h> /* * We try to ensure that the mitigation state can never change as the result of * onlining a late CPU. */ static void update_mitigation_state(enum mitigation_state *oldp, enum mitigation_state new) { enum mitigation_state state; do { state = READ_ONCE(*oldp); if (new <= state) break; /* Userspace almost certainly can't deal with this. */ if (WARN_ON(system_capabilities_finalized())) break; } while (cmpxchg_relaxed(oldp, state, new) != state); } /* * Spectre v1. * * The kernel can't protect userspace for this one: it's each person for * themselves. Advertise what we're doing and be done with it. */ ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } /* * Spectre v2. * * This one sucks. A CPU is either: * * - Mitigated in hardware and advertised by ID_AA64PFR0_EL1.CSV2. * - Mitigated in hardware and listed in our "safe list". * - Mitigated in software by firmware. * - Mitigated in software by a CPU-specific dance in the kernel and a * firmware call at EL2. * - Vulnerable. * * It's not unlikely for different CPUs in a big.LITTLE system to fall into * different camps. */ static enum mitigation_state spectre_v2_state; static bool __read_mostly __nospectre_v2; static int __init parse_spectre_v2_param(char *str) { __nospectre_v2 = true; return 0; } early_param("nospectre_v2", parse_spectre_v2_param); static bool spectre_v2_mitigations_off(void) { bool ret = __nospectre_v2 || cpu_mitigations_off(); if (ret) pr_info_once("spectre-v2 mitigation disabled by command line option\n"); return ret; } static const char *get_bhb_affected_string(enum mitigation_state bhb_state) { switch (bhb_state) { case SPECTRE_UNAFFECTED: return ""; default: case SPECTRE_VULNERABLE: return ", but not BHB"; case SPECTRE_MITIGATED: return ", BHB"; } } static bool _unprivileged_ebpf_enabled(void) { #ifdef CONFIG_BPF_SYSCALL return !sysctl_unprivileged_bpf_disabled; #else return false; #endif } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { enum mitigation_state bhb_state = arm64_get_spectre_bhb_state(); const char *bhb_str = get_bhb_affected_string(bhb_state); const char *v2_str = "Branch predictor hardening"; switch (spectre_v2_state) { case SPECTRE_UNAFFECTED: if (bhb_state == SPECTRE_UNAFFECTED) return sprintf(buf, "Not affected\n"); /* * Platforms affected by Spectre-BHB can't report * "Not affected" for Spectre-v2. */ v2_str = "CSV2"; fallthrough; case SPECTRE_MITIGATED: if (bhb_state == SPECTRE_MITIGATED && _unprivileged_ebpf_enabled()) return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n"); return sprintf(buf, "Mitigation: %s%s\n", v2_str, bhb_str); case SPECTRE_VULNERABLE: fallthrough; default: return sprintf(buf, "Vulnerable\n"); } } static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void) { u64 pfr0; static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; /* If the CPU has CSV2 set, we're safe */ pfr0 = read_cpuid(ID_AA64PFR0_EL1); if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_CSV2_SHIFT)) return SPECTRE_UNAFFECTED; /* Alternatively, we have a list of unaffected CPUs */ if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list)) return SPECTRE_UNAFFECTED; return SPECTRE_VULNERABLE; } static enum mitigation_state spectre_v2_get_cpu_fw_mitigation_state(void) { int ret; struct arm_smccc_res res; arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); ret = res.a0; switch (ret) { case SMCCC_RET_SUCCESS: return SPECTRE_MITIGATED; case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: return SPECTRE_UNAFFECTED; default: fallthrough; case SMCCC_RET_NOT_SUPPORTED: return SPECTRE_VULNERABLE; } } bool has_spectre_v2(const struct arm64_cpu_capabilities *entry, int scope) { WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); if (spectre_v2_get_cpu_hw_mitigation_state() == SPECTRE_UNAFFECTED) return false; if (spectre_v2_get_cpu_fw_mitigation_state() == SPECTRE_UNAFFECTED) return false; return true; } enum mitigation_state arm64_get_spectre_v2_state(void) { return spectre_v2_state; } DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); static void install_bp_hardening_cb(bp_hardening_cb_t fn) { __this_cpu_write(bp_hardening_data.fn, fn); /* * Vinz Clortho takes the hyp_vecs start/end "keys" at * the door when we're a guest. Skip the hyp-vectors work. */ if (!is_hyp_mode_available()) return; __this_cpu_write(bp_hardening_data.slot, HYP_VECTOR_SPECTRE_DIRECT); } /* Called during entry so must be noinstr */ static noinstr void call_smc_arch_workaround_1(void) { arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } /* Called during entry so must be noinstr */ static noinstr void call_hvc_arch_workaround_1(void) { arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } /* Called during entry so must be noinstr */ static noinstr void qcom_link_stack_sanitisation(void) { u64 tmp; asm volatile("mov %0, x30 \n" ".rept 16 \n" "bl . + 4 \n" ".endr \n" "mov x30, %0 \n" : "=&r" (tmp)); } static bp_hardening_cb_t spectre_v2_get_sw_mitigation_cb(void) { u32 midr = read_cpuid_id(); if (((midr & MIDR_CPU_MODEL_MASK) != MIDR_QCOM_FALKOR) && ((midr & MIDR_CPU_MODEL_MASK) != MIDR_QCOM_FALKOR_V1)) return NULL; return qcom_link_stack_sanitisation; } static enum mitigation_state spectre_v2_enable_fw_mitigation(void) { bp_hardening_cb_t cb; enum mitigation_state state; state = spectre_v2_get_cpu_fw_mitigation_state(); if (state != SPECTRE_MITIGATED) return state; if (spectre_v2_mitigations_off()) return SPECTRE_VULNERABLE; switch (arm_smccc_1_1_get_conduit()) { case SMCCC_CONDUIT_HVC: cb = call_hvc_arch_workaround_1; break; case SMCCC_CONDUIT_SMC: cb = call_smc_arch_workaround_1; break; default: return SPECTRE_VULNERABLE; } /* * Prefer a CPU-specific workaround if it exists. Note that we * still rely on firmware for the mitigation at EL2. */ cb = spectre_v2_get_sw_mitigation_cb() ?: cb; install_bp_hardening_cb(cb); return SPECTRE_MITIGATED; } void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused) { enum mitigation_state state; WARN_ON(preemptible()); state = spectre_v2_get_cpu_hw_mitigation_state(); if (state == SPECTRE_VULNERABLE) state = spectre_v2_enable_fw_mitigation(); update_mitigation_state(&spectre_v2_state, state); } /* * Spectre-v3a. * * Phew, there's not an awful lot to do here! We just instruct EL2 to use * an indirect trampoline for the hyp vectors so that guests can't read * VBAR_EL2 to defeat randomisation of the hypervisor VA layout. */ bool has_spectre_v3a(const struct arm64_cpu_capabilities *entry, int scope) { static const struct midr_range spectre_v3a_unsafe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), {}, }; WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); return is_midr_in_range_list(read_cpuid_id(), spectre_v3a_unsafe_list); } void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused) { struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); if (this_cpu_has_cap(ARM64_SPECTRE_V3A)) data->slot += HYP_VECTOR_INDIRECT; } /* * Spectre v4. * * If you thought Spectre v2 was nasty, wait until you see this mess. A CPU is * either: * * - Mitigated in hardware and listed in our "safe list". * - Mitigated in hardware via PSTATE.SSBS. * - Mitigated in software by firmware (sometimes referred to as SSBD). * * Wait, that doesn't sound so bad, does it? Keep reading... * * A major source of headaches is that the software mitigation is enabled both * on a per-task basis, but can also be forced on for the kernel, necessitating * both context-switch *and* entry/exit hooks. To make it even worse, some CPUs * allow EL0 to toggle SSBS directly, which can end up with the prctl() state * being stale when re-entering the kernel. The usual big.LITTLE caveats apply, * so you can have systems that have both firmware and SSBS mitigations. This * means we actually have to reject late onlining of CPUs with mitigations if * all of the currently onlined CPUs are safelisted, as the mitigation tends to * be opt-in for userspace. Yes, really, the cure is worse than the disease. * * The only good part is that if the firmware mitigation is present, then it is * present for all CPUs, meaning we don't have to worry about late onlining of a * vulnerable CPU if one of the boot CPUs is using the firmware mitigation. * * Give me a VAX-11/780 any day of the week... */ static enum mitigation_state spectre_v4_state; /* This is the per-cpu state tracking whether we need to talk to firmware */ DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required); enum spectre_v4_policy { SPECTRE_V4_POLICY_MITIGATION_DYNAMIC, SPECTRE_V4_POLICY_MITIGATION_ENABLED, SPECTRE_V4_POLICY_MITIGATION_DISABLED, }; static enum spectre_v4_policy __read_mostly __spectre_v4_policy; static const struct spectre_v4_param { const char *str; enum spectre_v4_policy policy; } spectre_v4_params[] = { { "force-on", SPECTRE_V4_POLICY_MITIGATION_ENABLED, }, { "force-off", SPECTRE_V4_POLICY_MITIGATION_DISABLED, }, { "kernel", SPECTRE_V4_POLICY_MITIGATION_DYNAMIC, }, }; static int __init parse_spectre_v4_param(char *str) { int i; if (!str || !str[0]) return -EINVAL; for (i = 0; i < ARRAY_SIZE(spectre_v4_params); i++) { const struct spectre_v4_param *param = &spectre_v4_params[i]; if (strncmp(str, param->str, strlen(param->str))) continue; __spectre_v4_policy = param->policy; return 0; } return -EINVAL; } early_param("ssbd", parse_spectre_v4_param); /* * Because this was all written in a rush by people working in different silos, * we've ended up with multiple command line options to control the same thing. * Wrap these up in some helpers, which prefer disabling the mitigation if faced * with contradictory parameters. The mitigation is always either "off", * "dynamic" or "on". */ static bool spectre_v4_mitigations_off(void) { bool ret = cpu_mitigations_off() || __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DISABLED; if (ret) pr_info_once("spectre-v4 mitigation disabled by command-line option\n"); return ret; } /* Do we need to toggle the mitigation state on entry to/exit from the kernel? */ static bool spectre_v4_mitigations_dynamic(void) { return !spectre_v4_mitigations_off() && __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_DYNAMIC; } static bool spectre_v4_mitigations_on(void) { return !spectre_v4_mitigations_off() && __spectre_v4_policy == SPECTRE_V4_POLICY_MITIGATION_ENABLED; } ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) { switch (spectre_v4_state) { case SPECTRE_UNAFFECTED: return sprintf(buf, "Not affected\n"); case SPECTRE_MITIGATED: return sprintf(buf, "Mitigation: Speculative Store Bypass disabled via prctl\n"); case SPECTRE_VULNERABLE: fallthrough; default: return sprintf(buf, "Vulnerable\n"); } } enum mitigation_state arm64_get_spectre_v4_state(void) { return spectre_v4_state; } static enum mitigation_state spectre_v4_get_cpu_hw_mitigation_state(void) { static const struct midr_range spectre_v4_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ }, }; if (is_midr_in_range_list(read_cpuid_id(), spectre_v4_safe_list)) return SPECTRE_UNAFFECTED; /* CPU features are detected first */ if (this_cpu_has_cap(ARM64_SSBS)) return SPECTRE_MITIGATED; return SPECTRE_VULNERABLE; } static enum mitigation_state spectre_v4_get_cpu_fw_mitigation_state(void) { int ret; struct arm_smccc_res res; arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); ret = res.a0; switch (ret) { case SMCCC_RET_SUCCESS: return SPECTRE_MITIGATED; case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: fallthrough; case SMCCC_RET_NOT_REQUIRED: return SPECTRE_UNAFFECTED; default: fallthrough; case SMCCC_RET_NOT_SUPPORTED: return SPECTRE_VULNERABLE; } } bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope) { enum mitigation_state state; WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); state = spectre_v4_get_cpu_hw_mitigation_state(); if (state == SPECTRE_VULNERABLE) state = spectre_v4_get_cpu_fw_mitigation_state(); return state != SPECTRE_UNAFFECTED; } bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr) { const u32 instr_mask = ~(1U << PSTATE_Imm_shift); const u32 instr_val = 0xd500401f | PSTATE_SSBS; if ((instr & instr_mask) != instr_val) return false; if (instr & BIT(PSTATE_Imm_shift)) regs->pstate |= PSR_SSBS_BIT; else regs->pstate &= ~PSR_SSBS_BIT; arm64_skip_faulting_instruction(regs, 4); return true; } static enum mitigation_state spectre_v4_enable_hw_mitigation(void) { enum mitigation_state state; /* * If the system is mitigated but this CPU doesn't have SSBS, then * we must be on the safelist and there's nothing more to do. */ state = spectre_v4_get_cpu_hw_mitigation_state(); if (state != SPECTRE_MITIGATED || !this_cpu_has_cap(ARM64_SSBS)) return state; if (spectre_v4_mitigations_off()) { sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS); set_pstate_ssbs(1); return SPECTRE_VULNERABLE; } /* SCTLR_EL1.DSSBS was initialised to 0 during boot */ set_pstate_ssbs(0); /* * SSBS is self-synchronizing and is intended to affect subsequent * speculative instructions, but some CPUs can speculate with a stale * value of SSBS. * * Mitigate this with an unconditional speculation barrier, as CPUs * could mis-speculate branches and bypass a conditional barrier. */ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386)) spec_bar(); return SPECTRE_MITIGATED; } /* * Patch a branch over the Spectre-v4 mitigation code with a NOP so that * we fallthrough and check whether firmware needs to be called on this CPU. */ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { BUG_ON(nr_inst != 1); /* Branch -> NOP */ if (spectre_v4_mitigations_off()) return; if (cpus_have_cap(ARM64_SSBS)) return; if (spectre_v4_mitigations_dynamic()) *updptr = cpu_to_le32(aarch64_insn_gen_nop()); } /* * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction * to call into firmware to adjust the mitigation state. */ void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { u32 insn; BUG_ON(nr_inst != 1); /* NOP -> HVC/SMC */ switch (arm_smccc_1_1_get_conduit()) { case SMCCC_CONDUIT_HVC: insn = aarch64_insn_get_hvc_value(); break; case SMCCC_CONDUIT_SMC: insn = aarch64_insn_get_smc_value(); break; default: return; } *updptr = cpu_to_le32(insn); } static enum mitigation_state spectre_v4_enable_fw_mitigation(void) { enum mitigation_state state; state = spectre_v4_get_cpu_fw_mitigation_state(); if (state != SPECTRE_MITIGATED) return state; if (spectre_v4_mitigations_off()) { arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, false, NULL); return SPECTRE_VULNERABLE; } arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, true, NULL); if (spectre_v4_mitigations_dynamic()) __this_cpu_write(arm64_ssbd_callback_required, 1); return SPECTRE_MITIGATED; } void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused) { enum mitigation_state state; WARN_ON(preemptible()); state = spectre_v4_enable_hw_mitigation(); if (state == SPECTRE_VULNERABLE) state = spectre_v4_enable_fw_mitigation(); update_mitigation_state(&spectre_v4_state, state); } static void __update_pstate_ssbs(struct pt_regs *regs, bool state) { u64 bit = compat_user_mode(regs) ? PSR_AA32_SSBS_BIT : PSR_SSBS_BIT; if (state) regs->pstate |= bit; else regs->pstate &= ~bit; } void spectre_v4_enable_task_mitigation(struct task_struct *tsk) { struct pt_regs *regs = task_pt_regs(tsk); bool ssbs = false, kthread = tsk->flags & PF_KTHREAD; if (spectre_v4_mitigations_off()) ssbs = true; else if (spectre_v4_mitigations_dynamic() && !kthread) ssbs = !test_tsk_thread_flag(tsk, TIF_SSBD); __update_pstate_ssbs(regs, ssbs); } /* * The Spectre-v4 mitigation can be controlled via a prctl() from userspace. * This is interesting because the "speculation disabled" behaviour can be * configured so that it is preserved across exec(), which means that the * prctl() may be necessary even when PSTATE.SSBS can be toggled directly * from userspace. */ static void ssbd_prctl_enable_mitigation(struct task_struct *task) { task_clear_spec_ssb_noexec(task); task_set_spec_ssb_disable(task); set_tsk_thread_flag(task, TIF_SSBD); } static void ssbd_prctl_disable_mitigation(struct task_struct *task) { task_clear_spec_ssb_noexec(task); task_clear_spec_ssb_disable(task); clear_tsk_thread_flag(task, TIF_SSBD); } static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { case PR_SPEC_ENABLE: /* Enable speculation: disable mitigation */ /* * Force disabled speculation prevents it from being * re-enabled. */ if (task_spec_ssb_force_disable(task)) return -EPERM; /* * If the mitigation is forced on, then speculation is forced * off and we again prevent it from being re-enabled. */ if (spectre_v4_mitigations_on()) return -EPERM; ssbd_prctl_disable_mitigation(task); break; case PR_SPEC_FORCE_DISABLE: /* Force disable speculation: force enable mitigation */ /* * If the mitigation is forced off, then speculation is forced * on and we prevent it from being disabled. */ if (spectre_v4_mitigations_off()) return -EPERM; task_set_spec_ssb_force_disable(task); fallthrough; case PR_SPEC_DISABLE: /* Disable speculation: enable mitigation */ /* Same as PR_SPEC_FORCE_DISABLE */ if (spectre_v4_mitigations_off()) return -EPERM; ssbd_prctl_enable_mitigation(task); break; case PR_SPEC_DISABLE_NOEXEC: /* Disable speculation until execve(): enable mitigation */ /* * If the mitigation state is forced one way or the other, then * we must fail now before we try to toggle it on execve(). */ if (task_spec_ssb_force_disable(task) || spectre_v4_mitigations_off() || spectre_v4_mitigations_on()) { return -EPERM; } ssbd_prctl_enable_mitigation(task); task_set_spec_ssb_noexec(task); break; default: return -ERANGE; } spectre_v4_enable_task_mitigation(task); return 0; } int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, unsigned long ctrl) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssbd_prctl_set(task, ctrl); default: return -ENODEV; } } static int ssbd_prctl_get(struct task_struct *task) { switch (spectre_v4_state) { case SPECTRE_UNAFFECTED: return PR_SPEC_NOT_AFFECTED; case SPECTRE_MITIGATED: if (spectre_v4_mitigations_on()) return PR_SPEC_NOT_AFFECTED; if (spectre_v4_mitigations_dynamic()) break; /* Mitigations are disabled, so we're vulnerable. */ fallthrough; case SPECTRE_VULNERABLE: fallthrough; default: return PR_SPEC_ENABLE; } /* Check the mitigation state for this task */ if (task_spec_ssb_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ssb_noexec(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC; if (task_spec_ssb_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssbd_prctl_get(task); default: return -ENODEV; } } /* * Spectre BHB. * * A CPU is either: * - Mitigated by a branchy loop a CPU specific number of times, and listed * in our "loop mitigated list". * - Mitigated in software by the firmware Spectre v2 call. * - Has the ClearBHB instruction to perform the mitigation. * - Has the 'Exception Clears Branch History Buffer' (ECBHB) feature, so no * software mitigation in the vectors is needed. * - Has CSV2.3, so is unaffected. */ static enum mitigation_state spectre_bhb_state; enum mitigation_state arm64_get_spectre_bhb_state(void) { return spectre_bhb_state; } enum bhb_mitigation_bits { BHB_LOOP, BHB_FW, BHB_HW, BHB_INSN, }; static unsigned long system_bhb_mitigations; /* * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any * SCOPE_SYSTEM call will give the right answer. */ u8 spectre_bhb_loop_affected(int scope) { u8 k = 0; static u8 max_bhb_k; if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), {}, }; static const struct midr_range spectre_bhb_k24_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), {}, }; static const struct midr_range spectre_bhb_k11_list[] = { MIDR_ALL_VERSIONS(MIDR_AMPERE1), {}, }; static const struct midr_range spectre_bhb_k8_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), {}, }; if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list)) k = 32; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) k = 24; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list)) k = 11; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) k = 8; max_bhb_k = max(max_bhb_k, k); } else { k = max_bhb_k; } return k; } static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void) { int ret; struct arm_smccc_res res; arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_3, &res); ret = res.a0; switch (ret) { case SMCCC_RET_SUCCESS: return SPECTRE_MITIGATED; case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: return SPECTRE_UNAFFECTED; default: fallthrough; case SMCCC_RET_NOT_SUPPORTED: return SPECTRE_VULNERABLE; } } static bool is_spectre_bhb_fw_affected(int scope) { static bool system_affected; enum mitigation_state fw_state; bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE; static const struct midr_range spectre_bhb_firmware_mitigated_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_CORTEX_A75), {}, }; bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(), spectre_bhb_firmware_mitigated_list); if (scope != SCOPE_LOCAL_CPU) return system_affected; fw_state = spectre_bhb_get_cpu_fw_mitigation_state(); if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) { system_affected = true; return true; } return false; } static bool supports_ecbhb(int scope) { u64 mmfr1; if (scope == SCOPE_LOCAL_CPU) mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1); else mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_ECBHB_SHIFT); } bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope) { WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); if (supports_csv2p3(scope)) return false; if (supports_clearbhb(scope)) return true; if (spectre_bhb_loop_affected(scope)) return true; if (is_spectre_bhb_fw_affected(scope)) return true; return false; } static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) { const char *v = arm64_get_bp_hardening_vector(slot); __this_cpu_write(this_cpu_vector, v); /* * When KPTI is in use, the vectors are switched when exiting to * user-space. */ if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0)) return; write_sysreg(v, vbar_el1); isb(); } static bool __read_mostly __nospectre_bhb; static int __init parse_spectre_bhb_param(char *str) { __nospectre_bhb = true; return 0; } early_param("nospectre_bhb", parse_spectre_bhb_param); void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) { bp_hardening_cb_t cpu_cb; enum mitigation_state fw_state, state = SPECTRE_VULNERABLE; struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU)) return; if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) { /* No point mitigating Spectre-BHB alone. */ } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { pr_info_once("spectre-bhb mitigation disabled by compile time option\n"); } else if (cpu_mitigations_off() || __nospectre_bhb) { pr_info_once("spectre-bhb mitigation disabled by command line option\n"); } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; set_bit(BHB_HW, &system_bhb_mitigations); } else if (supports_clearbhb(SCOPE_LOCAL_CPU)) { /* * Ensure KVM uses the indirect vector which will have ClearBHB * added. */ if (!data->slot) data->slot = HYP_VECTOR_INDIRECT; this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN); state = SPECTRE_MITIGATED; set_bit(BHB_INSN, &system_bhb_mitigations); } else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) { /* * Ensure KVM uses the indirect vector which will have the * branchy-loop added. A57/A72-r0 will already have selected * the spectre-indirect vector, which is sufficient for BHB * too. */ if (!data->slot) data->slot = HYP_VECTOR_INDIRECT; this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP); state = SPECTRE_MITIGATED; set_bit(BHB_LOOP, &system_bhb_mitigations); } else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) { fw_state = spectre_bhb_get_cpu_fw_mitigation_state(); if (fw_state == SPECTRE_MITIGATED) { /* * Ensure KVM uses one of the spectre bp_hardening * vectors. The indirect vector doesn't include the EL3 * call, so needs upgrading to * HYP_VECTOR_SPECTRE_INDIRECT. */ if (!data->slot || data->slot == HYP_VECTOR_INDIRECT) data->slot += 1; this_cpu_set_vectors(EL1_VECTOR_BHB_FW); /* * The WA3 call in the vectors supersedes the WA1 call * made during context-switch. Uninstall any firmware * bp_hardening callback. */ cpu_cb = spectre_v2_get_sw_mitigation_cb(); if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb) __this_cpu_write(bp_hardening_data.fn, NULL); state = SPECTRE_MITIGATED; set_bit(BHB_FW, &system_bhb_mitigations); } } update_mitigation_state(&spectre_bhb_state, state); } /* Patched to NOP when enabled */ void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { BUG_ON(nr_inst != 1); if (test_bit(BHB_LOOP, &system_bhb_mitigations)) *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); } /* Patched to NOP when enabled */ void noinstr spectre_bhb_patch_fw_mitigation_enabled(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { BUG_ON(nr_inst != 1); if (test_bit(BHB_FW, &system_bhb_mitigations)) *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); } /* Patched to correct the immediate */ void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { u8 rd; u32 insn; u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM); BUG_ON(nr_inst != 1); /* MOV -> MOV */ if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) return; insn = le32_to_cpu(*origptr); rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn); insn = aarch64_insn_gen_movewide(rd, loop_count, 0, AARCH64_INSN_VARIANT_64BIT, AARCH64_INSN_MOVEWIDE_ZERO); *updptr++ = cpu_to_le32(insn); } /* Patched to mov WA3 when supported */ void noinstr spectre_bhb_patch_wa3(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { u8 rd; u32 insn; BUG_ON(nr_inst != 1); /* MOV -> MOV */ if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) || !test_bit(BHB_FW, &system_bhb_mitigations)) return; insn = le32_to_cpu(*origptr); rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn); insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_ORR, AARCH64_INSN_VARIANT_32BIT, AARCH64_INSN_REG_ZR, rd, ARM_SMCCC_ARCH_WORKAROUND_3); if (WARN_ON_ONCE(insn == AARCH64_BREAK_FAULT)) return; *updptr++ = cpu_to_le32(insn); } /* Patched to NOP when not supported */ void __init spectre_bhb_patch_clearbhb(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { BUG_ON(nr_inst != 2); if (test_bit(BHB_INSN, &system_bhb_mitigations)) return; *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); } #ifdef CONFIG_BPF_SYSCALL #define EBPF_WARN "Unprivileged eBPF is enabled, data leaks possible via Spectre v2 BHB attacks!\n" void unpriv_ebpf_notify(int new_state) { if (spectre_v2_state == SPECTRE_VULNERABLE || spectre_bhb_state != SPECTRE_MITIGATED) return; if (!new_state) pr_err("WARNING: %s", EBPF_WARN); } #endif |
| 55 55 321 249 317 32 8 322 318 8 986 987 307 985 300 964 321 55 978 32 986 2 2 985 985 2 14 984 989 29 986 32 1001 1004 32 1003 1003 991 840 1000 1006 2 2 2 2 2 2 1002 1007 1004 55 999 1002 1005 981 974 32 1005 2 17 35 246 982 8 309 1003 1006 991 985 30 32 32 1001 2 2 246 982 8 309 269 990 985 32 31 972 253 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/sprintf.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #include <linux/notifier.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <linux/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); noinline static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); noinline static long long simple_strntoll(const char *cp, char **endp, unsigned int base, size_t max_chars) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, endp, base, max_chars - 1); return simple_strntoull(cp, endp, base, max_chars); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(SIGN == 1); static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static bool filled_random_ptr_key __read_mostly; static siphash_key_t ptr_key __read_mostly; static int fill_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Pairs with smp_rmb() before reading ptr_key. */ smp_wmb(); WRITE_ONCE(filled_random_ptr_key, true); return NOTIFY_DONE; } static int __init vsprintf_init_hashval(void) { static struct notifier_block fill_ptr_key_nb = { .notifier_call = fill_ptr_key }; execute_with_initialized_rng(&fill_ptr_key_nb); return 0; } subsys_initcall(vsprintf_init_hashval) /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (!READ_ONCE(filled_random_ptr_key)) return -EBUSY; /* Pairs with smp_wmb() after writing ptr_key. */ smp_rmb(); #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_hardirq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev_is_partition(bdev)) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev_partno(bdev), spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *hex_range(char *buf, char *end, u64 start_val, u64 end_val, struct printf_spec spec) { buf = number(buf, end, start_val, spec); if (start_val == end_val) return buf; if (buf < end) *buf = '-'; ++buf; return number(buf, end, end_val, spec); } static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = hex_range(p, pend, res->start, res->end, *specp); } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *range_string(char *buf, char *end, const struct range *range, struct printf_spec spec, const char *fmt) { char sym[sizeof("[range 0x0123456789abcdef-0x0123456789abcdef]")]; char *p = sym, *pend = sym + sizeof(sym); struct printf_spec range_spec = { .field_width = 2 + 2 * sizeof(range->start), /* 0x + 2 * 8 */ .flags = SPECIAL | SMALL | ZEROPAD, .base = 16, .precision = -1, }; if (check_pointer(&buf, end, range, spec)) return buf; p = string_nocheck(p, pend, "[range ", default_str_spec); p = hex_range(p, pend, range->start, range->end, range_spec); *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); bool first = true; int rbot, rtop; if (check_pointer(&buf, end, bitmap, spec)) return buf; for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) { if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rtop == rbot + 1) continue; if (buf < end) *buf = '-'; buf = number(++buf, end, rtop - 1, default_dec_spec); } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; u32 orig, val; if (fmt[1] != 'c' || fmt[2] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); val = orig & ~BIT(31); for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> (i * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } *p++ = ' '; strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian"); p += strlen(p); *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; buf = number(buf, end, flags, default_flag_spec); if (buf < end) *buf = '('; buf++; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } if (buf < end) *buf = ')'; buf++; return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { if (*fmt == 'r' && fmt[1] == 'a') return range_string(buf, end, ptr, spec, fmt); return resource_string(buf, end, ptr, spec, fmt); } int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* Used for Rust formatting ('%pA'). */ char *rust_fmt_argument(char *buf, char *end, void *ptr); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'ra' For struct ranges, e.g., [range 0x0000000000000000 - 0x00000000000000ff] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. * * There is also a '%pA' format specifier, but it is only intended to be used * from Rust code to format core::fmt::Arguments. Do *not* use it from C. * See rust/kernel/print.rs for details. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_or_range(fmt, buf, end, ptr, spec); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'A': if (!IS_ENABLED(CONFIG_RUST)) { WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); return error_string(buf, end, "(%pA?)", spec); } return rust_fmt_argument(buf, end, ptr); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; fallthrough; case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; break; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ fallthrough; default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; if (unlikely(!size)) return 0; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; return size - 1; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) __set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ __clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && !isodigit(digit)) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, &next, base, field_width >= 0 ? field_width : INT_MAX); else val.u = simple_strntoull(str, &next, base, field_width >= 0 ? field_width : INT_MAX); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_H #define _LINUX_WAIT_H /* * Linux wait queue related types and methods */ #include <linux/list.h> #include <linux/stddef.h> #include <linux/spinlock.h> #include <asm/current.h> typedef struct wait_queue_entry wait_queue_entry_t; typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_CUSTOM 0x04 #define WQ_FLAG_DONE 0x08 #define WQ_FLAG_PRIORITY 0x10 /* * A single wait-queue entry structure: */ struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; struct list_head entry; }; struct wait_queue_head { spinlock_t lock; struct list_head head; }; typedef struct wait_queue_head wait_queue_head_t; struct task_struct; /* * Macros for declaration and initialisaton of the datatypes */ #define __WAITQUEUE_INITIALIZER(name, tsk) { \ .private = tsk, \ .func = default_wake_function, \ .entry = { NULL, NULL } } #define DECLARE_WAITQUEUE(name, tsk) \ struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = LIST_HEAD_INIT(name.head) } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); #define init_waitqueue_head(wq_head) \ do { \ static struct lock_class_key __key; \ \ __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { wq_entry->flags = 0; wq_entry->private = p; wq_entry->func = default_wake_function; } static inline void init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { wq_entry->flags = 0; wq_entry->private = NULL; wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like:: * * CPU0 - waker CPU1 - waiter * * for (;;) { * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (waitqueue_active(wq_head)) if (@cond) * wake_up(wq_head); break; * schedule(); * } * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll * observe an empty wait list while the waiter might not observe @cond. * * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ static inline int waitqueue_active(struct wait_queue_head *wq_head) { return !list_empty(&wq_head->head); } /** * wq_has_single_sleeper - check if there is only one sleeper * @wq_head: wait queue head * * Returns true of wq_head has only one sleeper on the list. * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) { return list_is_singular(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier should be paired with one on the * waiting side. */ smp_mb(); return waitqueue_active(wq_head); } extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { struct list_head *head = &wq_head->head; struct wait_queue_entry *wq; list_for_each_entry(wq, &wq_head->head, entry) { if (!(wq->flags & WQ_FLAG_PRIORITY)) break; head = &wq->entry; } list_add(&wq_entry->entry, head); } /* * Used for wake-one threads: */ static inline void __add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq_head, wq_entry); } static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void __add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_del(&wq_entry->entry); } int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) #define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE) /* * Wakeup macros to be used to report events to the targets. */ #define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m)) #define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m)) #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, poll_to_key(m)) #define wake_up_poll_on_current_cpu(x, m) \ __wake_up_on_current_cpu(x, TASK_NORMAL, poll_to_key(m)) #define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) /** * wake_up_pollfree - signal that a polled waitqueue is going away * @wq_head: the wait queue head * * In the very rare cases where a ->poll() implementation uses a waitqueue whose * lifetime is tied to a task rather than to the 'struct file' being polled, * this function must be called before the waitqueue is freed so that * non-blocking polls (e.g. epoll) are notified that the queue is going away. * * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. */ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) { /* * For performance reasons, we don't always take the queue lock here. * Therefore, we might race with someone removing the last entry from * the queue, and proceed while they still hold the queue lock. * However, rcu_read_lock() is required to be held in such cases, so we * can safely proceed with an RCU-delayed free. */ if (waitqueue_active(wq_head)) __wake_up_pollfree(wq_head); } #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ if (__cond && !__ret) \ __ret = 1; \ __cond || !__ret; \ }) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret * variable when used from the wait_event_*() macros. * * This is so that both can use the ___wait_cond_timeout() construct * to wrap the condition. * * The type inconsistency of the wait_event_*() __ret variable is also * on purpose; we use long where we can return timeout values and int * otherwise. */ #define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_entry __wq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ }) #define __wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_event(wq_head, condition); \ } while (0) #define __io_wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ #define io_wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __io_wait_event(wq_head, condition); \ } while (0) #define __wait_event_freezable(wq_head, condition) \ ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_freezable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable(wq_head, condition); \ __ret; \ }) #define __wait_event_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ #define wait_event_freezable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ #define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_interruptible(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible(wq_head, condition); \ __ret; \ }) #define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ #define wait_event_interruptible_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_interruptible_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ ({ \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ hrtimer_setup_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \ } \ \ __ret = ___wait_event(wq_head, condition, state, 0, 0, \ if (!__t.task) { \ __ret = -ETIME; \ break; \ } \ schedule()); \ \ hrtimer_cancel(&__t.timer); \ destroy_hrtimer_on_stack(&__t.timer); \ __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ #define wait_event_hrtimeout(wq_head, condition, timeout) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ #define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ ({ \ long __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq, condition, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define __wait_event_interruptible_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) #define wait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_killable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) #define wait_event_killable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_freezable_exclusive(wq, condition) \ ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable_exclusive(wq, condition); \ __ret; \ }) /** * wait_event_idle - wait for a condition without contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \ } while (0) /** * wait_event_idle_exclusive - wait for a condition with contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle_exclusive(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \ } while (0) #define __wait_event_idle_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 1, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\ __ret; \ }) extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); #define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ __ret = fn(&(wq), &__wait); \ if (__ret) \ break; \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ __ret; \ }) /** * wait_event_interruptible_locked - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** * wait_event_killable - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_killable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable(wq_head, condition); \ __ret; \ }) #define __wait_event_state(wq, condition, state) \ ___wait_event(wq, condition, state, 0, 0, schedule()) /** * wait_event_state - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @state: state to sleep in * * The process is put to sleep (@state) until the @condition evaluates to true * or a signal is received (when allowed by @state). The @condition is checked * each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a signal * (when allowed by @state) and 0 if @condition evaluated to true. */ #define wait_event_state(wq_head, condition, state) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_state(wq_head, condition, state); \ __ret; \ }) #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a kill signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a kill signal. * * Only kill signals interrupt this process. */ #define wait_event_killable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_killable_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_lock_irq_cmd - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ #define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** * wait_event_lock_irq - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ #define wait_event_lock_irq(wq_head, condition, lock) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) #define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock, cmd); \ __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock,); \ __ret; \ }) #define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ #define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_FUNC(name, function) \ struct wait_queue_entry name = { \ .private = current, \ .func = function, \ .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) #define init_wait(wait) \ do { \ (wait)->private = current; \ (wait)->func = autoremove_wake_function; \ INIT_LIST_HEAD(&(wait)->entry); \ (wait)->flags = 0; \ } while (0) typedef int (*task_call_f)(struct task_struct *p, void *arg); extern int task_call_func(struct task_struct *p, task_call_f func, void *arg); #endif /* _LINUX_WAIT_H */ |
| 2 4 41 2 36 4 5 1 4 3 1 2 35 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 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-only /* * Copyright (C) 2015, 2016 ARM Ltd. */ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <trace/events/kvm.h> #include <kvm/arm_vgic.h> #include "vgic.h" /* * vgic_irqfd_set_irq: inject the IRQ corresponding to the * irqchip routing entry * * This is the entry point for irqfd IRQ injection */ static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { unsigned int spi_id = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS; if (!vgic_valid_spi(kvm, spi_id)) return -EINVAL; return kvm_vgic_inject_irq(kvm, NULL, spi_id, level, NULL); } /** * kvm_set_routing_entry: populate a kvm routing entry * from a user routing entry * * @kvm: the VM this entry is applied to * @e: kvm kernel routing entry handle * @ue: user api routing entry handle * return 0 on success, -EINVAL on errors. */ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: e->set = vgic_irqfd_set_irq; e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin; if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) || (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)) goto out; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; e->msi.address_lo = ue->u.msi.address_lo; e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; e->msi.flags = ue->flags; e->msi.devid = ue->u.msi.devid; break; default: goto out; } r = 0; out: return r; } static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm_msi *msi) { msi->address_lo = e->msi.address_lo; msi->address_hi = e->msi.address_hi; msi->data = e->msi.data; msi->flags = e->msi.flags; msi->devid = e->msi.devid; } /* * kvm_set_msi: inject the MSI corresponding to the * MSI routing entry * * This is the entry point for irqfd MSI injection * and userspace MSI injection. */ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_msi msi; if (!vgic_has_its(kvm)) return -ENODEV; if (!level) return -1; kvm_populate_msi(e, &msi); return vgic_its_inject_msi(kvm, &msi); } /* * kvm_arch_set_irq_inatomic: fast-path for irqfd injection */ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { if (!level) return -EWOULDBLOCK; switch (e->type) { case KVM_IRQ_ROUTING_MSI: { struct kvm_msi msi; if (!vgic_has_its(kvm)) break; kvm_populate_msi(e, &msi); return vgic_its_inject_cached_translation(kvm, &msi); } case KVM_IRQ_ROUTING_IRQCHIP: /* * Injecting SPIs is always possible in atomic context * as long as the damn vgic is initialized. */ if (unlikely(!vgic_initialized(kvm))) break; return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status); } return -EWOULDBLOCK; } int kvm_vgic_setup_default_irq_routing(struct kvm *kvm) { struct kvm_irq_routing_entry *entries; struct vgic_dist *dist = &kvm->arch.vgic; u32 nr = dist->nr_spis; int i, ret; entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL_ACCOUNT); if (!entries) return -ENOMEM; for (i = 0; i < nr; i++) { entries[i].gsi = i; entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; entries[i].u.irqchip.irqchip = 0; entries[i].u.irqchip.pin = i; } ret = kvm_set_irq_routing(kvm, entries, nr, 0); kfree(entries); return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_POLL_H #define _LINUX_POLL_H #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #define MAX_STACK_ALLOC 832 #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) #define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; /* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* * Do not touch the structure directly, use the access functions * poll_does_not_wait() and poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; __poll_t _key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { if (p && p->_qproc && wait_address) p->_qproc(filp, wait_address, p); } /* * Return true if it is guaranteed that poll will not wait. This is the case * if the poll() of another file descriptor in the set got an event, so there * is no need for waiting. */ static inline bool poll_does_not_wait(const poll_table *p) { return p == NULL || p->_qproc == NULL; } /* * Return the set of events that the application wants to poll for. * This is useful for drivers that need to know whether a DMA transfer has * to be started implicitly on poll(). You typically only want to do that * if the application is actually polling for POLLIN and/or POLLOUT. */ static inline __poll_t poll_requested_events(const poll_table *p) { return p ? p->_key : ~(__poll_t)0; } static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->_qproc = qproc; pt->_key = ~(__poll_t)0; /* all events enabled */ } static inline bool file_can_poll(struct file *file) { return file->f_op->poll; } static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { if (unlikely(!file->f_op->poll)) return DEFAULT_POLLMASK; return file->f_op->poll(file, pt); } struct poll_table_entry { struct file *filp; __poll_t key; wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; /* * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; struct poll_table_page *table; struct task_struct *polling_task; int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); #define __MAP(v, from, to) \ (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) static inline __u16 mangle_poll(__poll_t val) { __u16 v = (__force __u16)val; #define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } static inline __poll_t demangle_poll(u16 val) { #define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } #undef __MAP #endif /* _LINUX_POLL_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | /* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* Copyright (c) 2002-2007 Volkswagen Group Electronic Research * Copyright (c) 2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> * * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #ifndef CAN_ML_H #define CAN_ML_H #include <linux/can.h> #include <linux/list.h> #include <linux/netdevice.h> #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; struct can_dev_rcv_lists { struct hlist_head rx[RX_MAX]; struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; int entries; }; struct can_ml_priv { struct can_dev_rcv_lists dev_rcv_lists; #ifdef CAN_J1939 struct j1939_priv *j1939_priv; #endif }; static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) { return netdev_get_ml_priv(dev, ML_PRIV_CAN); } static inline void can_set_ml_priv(struct net_device *dev, struct can_ml_priv *ml_priv) { netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); } #endif /* CAN_ML_H */ |
| 162 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up(struct file_lock *fl) { wake_up(&fl->c.flc_wait); } static inline bool locks_can_async_lock(const struct file_operations *fops) { return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 226 259 226 1 1 226 15 14 226 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the AF_INET socket handler. * * Version: @(#)sock.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche <flla@stud.uni-sb.de> * * Fixes: * Alan Cox : Volatiles in skbuff pointers. See * skbuff comments. May be overdone, * better to prove they can be removed * than the reverse. * Alan Cox : Added a zapped field for tcp to note * a socket is reset and must stay shut up * Alan Cox : New fields for options * Pauline Middelink : identd support * Alan Cox : Eliminate low level recv/recvfrom * David S. Miller : New socket lookup architecture. * Steve Whitehouse: Default routines for sock_ops * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made * protinfo be just a void pointer, as the * protocol specific parts were moved to * respective headers and ipv4/v6, etc now * use private slabcaches for its socks * Pedro Hortas : New flags field for socket options */ #ifndef _SOCK_H #define _SOCK_H #include <linux/hardirq.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/timer.h> #include <linux/cache.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* struct sk_buff */ #include <linux/mm.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/static_key.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> #include <linux/rbtree.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> #include <linux/indirect_call_wrapper.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/llist.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> #include <uapi/linux/socket.h> /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of * the other protocols. */ /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. */ typedef struct { spinlock_t slock; int owned; wait_queue_head_t wq; /* * We express the mutex-alike socket_lock semantics * to the lock validator by explicitly managing * the slock as a lock variant (in addition to * the slock itself): */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } socket_lock_t; struct sock; struct proto; struct net; typedef __u32 __bitwise __portpair; typedef __u64 __bitwise __addrpair; /** * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @skc_v6_daddr: IPV6 destination address * @skc_v6_rcv_saddr: IPV6 source address * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_listener: connection request listener socket (aka rsk_listener) * [union with @skc_flags] * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) * [union with @skc_incoming_cpu] * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { union { __addrpair skc_addrpair; struct { __be32 skc_daddr; __be32 skc_rcv_saddr; }; }; union { unsigned int skc_hash; __u16 skc_u16hashes[2]; }; /* skc_dport && skc_num must be grouped as well */ union { __portpair skc_portpair; struct { __be16 skc_dport; __u16 skc_num; }; }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse:4; unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; struct hlist_node skc_portaddr_node; }; struct proto *skc_prot; possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; struct in6_addr skc_v6_rcv_saddr; #endif atomic64_t skc_cookie; /* following fields are padding to force * offset(struct sock, sk_refcnt) == 128 on 64bit arches * assuming IPV6 is enabled. We use this padding differently * for different kind of 'sockets' */ union { unsigned long skc_flags; struct sock *skc_listener; /* request_sock */ struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() */ /* private: */ int skc_dontcopy_begin[0]; /* public: */ union { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING unsigned short skc_rx_queue_mapping; #endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; refcount_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; union { u32 skc_rxhash; u32 skc_window_clamp; u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; struct bpf_local_storage; struct sk_filter; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_rx_dst_ifindex: ifindex for @sk_rx_dst * @sk_rx_dst_cookie: cookie for @sk_rx_dst * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags * @sk_write_queue: Packet sending queue * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward * @sk_reserved_mem: space reserved and non-reclaimable for the socket * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_gso_disabled: if set, NETIF_F_GSO_MASK is forbidden. * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, * IPV6_ADDRFORM for instance) * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' * @sk_drops: raw/udp drops counter * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner * @sk_prefer_busy_poll: prefer busypolling over softirq processing * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. * Sockets that can be used under memory reclaim should * set this to false. * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_disconnects: number of disconnect operations performed on this sock * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; #define sk_node __sk_common.skc_node #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_portpair __sk_common.skc_portpair #define sk_num __sk_common.skc_num #define sk_dport __sk_common.skc_dport #define sk_addrpair __sk_common.skc_addrpair #define sk_daddr __sk_common.skc_daddr #define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash __cacheline_group_begin(sock_write_rx); atomic_t sk_drops; __s32 sk_peek_off; struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. * Note : rmem_alloc is in this structure to fill a hole * on 64bit arches, not because its logically part of * backlog. */ struct { atomic_t rmem_alloc; int len; struct sk_buff *head; struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc __cacheline_group_end(sock_write_rx); __cacheline_group_begin(sock_read_rx); /* early demux fields */ struct dst_entry __rcu *sk_rx_dst; int sk_rx_dst_ifindex; u32 sk_rx_dst_cookie; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; unsigned int sk_napi_id; u16 sk_busy_poll_budget; u8 sk_prefer_busy_poll; #endif u8 sk_userlocks; int sk_rcvbuf; struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; /* private: */ struct socket_wq *sk_wq_raw; /* public: */ }; void (*sk_data_ready)(struct sock *sk); long sk_rcvtimeo; int sk_rcvlowat; __cacheline_group_end(sock_read_rx); __cacheline_group_begin(sock_read_rxtx); int sk_err; struct socket *sk_socket; struct mem_cgroup *sk_memcg; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif __cacheline_group_end(sock_read_rxtx); __cacheline_group_begin(sock_write_rxtx); socket_lock_t sk_lock; u32 sk_reserved_mem; int sk_forward_alloc; u32 sk_tsflags; __cacheline_group_end(sock_write_rxtx); __cacheline_group_begin(sock_write_tx); int sk_write_pending; atomic_t sk_omem_alloc; int sk_sndbuf; int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; union { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ struct page_frag sk_frag; struct timer_list sk_timer; unsigned long sk_pacing_rate; /* bytes per second */ atomic_t sk_zckey; atomic_t sk_tskey; __cacheline_group_end(sock_write_tx); __cacheline_group_begin(sock_read_tx); unsigned long sk_max_pacing_rate; long sk_sndtimeo; u32 sk_priority; u32 sk_mark; struct dst_entry __rcu *sk_dst_cache; netdev_features_t sk_route_caps; #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); #endif u16 sk_gso_type; u16 sk_gso_max_segs; unsigned int sk_gso_max_size; gfp_t sk_allocation; u32 sk_txhash; u8 sk_pacing_shift; bool sk_use_task_frag; __cacheline_group_end(sock_read_tx); /* * Because of non atomicity rules, all * changes are protected by socket lock. */ u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1; u8 sk_shutdown; u16 sk_type; u16 sk_protocol; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; spinlock_t sk_peer_lock; int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif int sk_disconnects; u8 sk_txrehash; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; void (*sk_state_change)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; struct xarray sk_user_frags; }; struct sock_bh_locked { struct sock *sock; local_lock_t bh_lock; }; enum sk_pacing { SK_PACING_NONE = 0, SK_PACING_NEEDED = 1, SK_PACING_FQ = 2, }; /* flag bits in sk_user_data * * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might * not be suitable for copying when cloning the socket. For instance, * it can point to a reference counted object. sk_user_data bottom * bit is set if pointer must not be copied. * * - SK_USER_DATA_BPF: Mark whether sk_user_data field is * managed/owned by a BPF reuseport array. This bit should be set * when sk_user_data's sk is added to the bpf's reuseport_array. * * - SK_USER_DATA_PSOCK: Mark whether pointer stored in * sk_user_data points to psock type. This bit should be set * when sk_user_data is assigned to a psock object. */ #define SK_USER_DATA_NOCOPY 1UL #define SK_USER_DATA_BPF 2UL #define SK_USER_DATA_PSOCK 4UL #define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\ SK_USER_DATA_PSOCK) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied * @sk: socket */ static inline bool sk_user_data_is_nocopy(const struct sock *sk) { return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); } #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) /** * __locked_read_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits * * The caller must be holding sk->sk_callback_lock. */ static inline void * __locked_read_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference_check(__sk_user_data(sk), lockdep_is_held(&sk->sk_callback_lock)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } /** * __rcu_dereference_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits */ static inline void * __rcu_dereference_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } #define rcu_dereference_sk_user_data(sk) \ __rcu_dereference_sk_user_data_with_flags(sk, 0) #define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ ({ \ uintptr_t __tmp1 = (uintptr_t)(ptr), \ __tmp2 = (uintptr_t)(flags); \ WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \ WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), \ __tmp1 | __tmp2); \ }) #define rcu_assign_sk_user_data(sk, ptr) \ __rcu_assign_sk_user_data_with_flags(sk, ptr, 0) static inline struct net *sock_net(const struct sock *sk) { return read_pnet(&sk->sk_net); } static inline void sock_net_set(struct sock *sk, struct net *net) { write_pnet(&sk->sk_net, net); } /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE * on a socket means that the socket will reuse everybody else's port * without looking at the other's sk_reuse value. */ #define SK_NO_REUSE 0 #define SK_CAN_REUSE 1 #define SK_FORCE_REUSE 2 int sk_set_peek_off(struct sock *sk, int val); static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); } return 0; } static inline void sk_peek_offset_bwd(struct sock *sk, int val) { s32 off = READ_ONCE(sk->sk_peek_off); if (unlikely(off >= 0)) { off = max_t(s32, off - val, 0); WRITE_ONCE(sk->sk_peek_off, off); } } static inline void sk_peek_offset_fwd(struct sock *sk, int val) { sk_peek_offset_bwd(sk, -val); } /* * Hashed lists helper routines */ static inline struct sock *sk_entry(const struct hlist_node *node) { return hlist_entry(node, struct sock, sk_node); } static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); } static inline struct sock *sk_head(const struct hlist_head *head) { return hlist_empty(head) ? NULL : __sk_head(head); } static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); } static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); } static inline struct sock *sk_next(const struct sock *sk) { return hlist_entry_safe(sk->sk_node.next, struct sock, sk_node); } static inline struct sock *sk_nulls_next(const struct sock *sk) { return (!is_a_nulls(sk->sk_nulls_node.next)) ? hlist_nulls_entry(sk->sk_nulls_node.next, struct sock, sk_nulls_node) : NULL; } static inline bool sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } static inline bool sk_hashed(const struct sock *sk) { return !sk_unhashed(sk); } static inline void sk_node_init(struct hlist_node *node) { node->pprev = NULL; } static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); } /* NB: equivalent to hlist_del_init_rcu */ static inline bool __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { __sk_del_node(sk); sk_node_init(&sk->sk_node); return true; } return false; } /* Grab socket reference count. This operation is valid only when sk is ALREADY grabbed f.e. it is found in hash table or a list and the lookup is made under lock preventing hash table modifications. */ static __always_inline void sock_hold(struct sock *sk) { refcount_inc(&sk->sk_refcnt); } /* Ungrab socket in the context, which assumes that socket refcnt cannot hit zero, f.e. it is true in context of any socketcall. */ static __always_inline void __sock_put(struct sock *sk) { refcount_dec(&sk->sk_refcnt); } static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk) { if (sk_hashed(sk)) { hlist_nulls_del_init_rcu(&sk->sk_nulls_node); return true; } return false; } static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); } static inline void sk_add_node(struct sock *sk, struct hlist_head *list) { sock_hold(sk); __sk_add_node(sk, list); } static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&sk->sk_node, list); else hlist_add_head_rcu(&sk->sk_node, list); } static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); hlist_add_tail_rcu(&sk->sk_node, list); } static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); __sk_nulls_add_node_rcu(sk, list); } static inline void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); } static inline void sk_add_bind_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_bind_node, list); } #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) #define sk_for_each_from(__sk) \ hlist_for_each_entry_from(__sk, sk_node) #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) #define sk_for_each_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) #define sk_for_each_bound_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @offset: offset of hlist_node within the struct. * */ #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from * userspace. */ return sk->sk_socket->file->f_cred->user_ns; } /* Sock flags */ enum sock_flags { SOCK_DEAD, SOCK_DONE, SOCK_URGINLINE, SOCK_KEEPOPEN, SOCK_LINGER, SOCK_DESTROY, SOCK_BROADCAST, SOCK_TIMESTAMP, SOCK_ZAPPED, SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG, /* %SO_DEBUG setting */ SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ SOCK_RXQ_OVFL, SOCK_ZEROCOPY, /* buffers from userspace */ SOCK_WIFI_STATUS, /* push wifi status to userspace */ SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS. * Will use last 4 bytes of packet sent from * user-space instead. */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) /* * The highest bit of sk_tsflags is reserved for kernel-internal * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that * SOF_TIMESTAMPING* values do not reach this reserved area */ #define SOCKCM_FLAG_TS_OPT_ID BIT(31) static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } static inline void sock_set_flag(struct sock *sk, enum sock_flags flag) { __set_bit(flag, &sk->sk_flags); } static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) { __clear_bit(flag, &sk->sk_flags); } static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, int valbool) { if (valbool) sock_set_flag(sk, bit); else sock_reset_flag(sk, bit); } static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); } #ifdef CONFIG_NET DECLARE_STATIC_KEY_FALSE(memalloc_socks_key); static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) { return 0; } static inline void __receive_sock(struct file *file) { } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) { return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1); } static inline void sk_acceptq_added(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } /* Note: If you think the test should be: * return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.") */ static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); } /* * Compute minimal free write space needed to queue new packets. */ static inline int sk_stream_min_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); } static inline void sk_wmem_queued_add(struct sock *sk, int val) { WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } static inline void sk_forward_alloc_add(struct sock *sk, int val) { /* Paired with lockless reads of sk->sk_forward_alloc */ WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val); } void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ skb_dst_force(skb); if (!sk->sk_backlog.tail) WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } /* * Take into account size of receive queue and backlog queue * Do not take into account this skb truesize, * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); return qsize > limit; } /* The per-socket spinlock must be held here. */ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, unsigned int limit) { if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) return -ENOMEM; __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; } int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)); static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); return INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) { int cpu = raw_smp_processor_id(); if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu)) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in sock_rps_record_flow(). */ if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS /* Paired with READ_ONCE() in sock_rps_record_flow() */ WRITE_ONCE(sk->sk_rxhash, 0); #endif } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc, __dis = __sk->sk_disconnects; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ *(__timeo) = wait_woken(__wait, \ TASK_INTERRUPTIBLE, \ *(__timeo)); \ } \ sched_annotate_sleep(); \ lock_sock(__sk); \ __rc = __dis == __sk->sk_disconnects ? __condition : -EPIPE; \ __rc; \ }) int sk_stream_wait_connect(struct sock *sk, long *timeo_p); int sk_stream_wait_memory(struct sock *sk, long *timeo_p); void sk_stream_wait_close(struct sock *sk, long timeo_p); int sk_stream_error(struct sock *sk, int flags, int err); void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); void __sk_flush_backlog(struct sock *sk); static inline bool sk_flush_backlog(struct sock *sk) { if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { __sk_flush_backlog(sk); return true; } return false; } int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; struct inet_hashinfo; struct raw_hashinfo; struct smc_hashinfo; struct module; struct sk_psock; /* * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes * un-modified. Special care is taken when initializing object to zero. */ static inline void sk_prot_clear_nulls(struct sock *sk, int size) { if (offsetof(struct sock, sk_node.next) != 0) memset(sk, 0, offsetof(struct sock, sk_node.next)); memset(&sk->sk_node.pprev, 0, size - offsetof(struct sock, sk_node.pprev)); } struct proto_accept_arg { int flags; int err; int is_empty; bool kern; }; /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); struct sock * (*accept)(struct sock *sk, struct proto_accept_arg *arg); int (*ioctl)(struct sock *sk, int cmd, int *karg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); bool (*bpf_bypass_getsockopt)(int level, int optname); void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); #endif /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif #if IS_ENABLED(CONFIG_MPTCP) int (*forward_alloc_get)(const struct sock *sk); #endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; u32 sysctl_wmem_offset; u32 sysctl_rmem_offset; int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; unsigned int ipv6_pinfo_offset; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; struct udp_table *udp_table; struct raw_hashinfo *raw_hash; struct smc_hashinfo *smc_hash; } h; struct module *owner; char name[32]; struct list_head node; int (*diag_destroy)(struct sock *sk, int err); } __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); int sock_load_diag_module(int family, int protocol); INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); static inline int sk_forward_alloc_get(const struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP) if (sk->sk_prot->forward_alloc_get) return sk->sk_prot->forward_alloc_get(sk); #endif return READ_ONCE(sk->sk_forward_alloc); } static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? INDIRECT_CALL_INET_1(sk->sk_prot->stream_memory_free, tcp_stream_memory_free, sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) { return __sk_stream_memory_free(sk, 0); } static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && __sk_stream_memory_free(sk, wake); } static inline bool sk_stream_is_writeable(const struct sock *sk) { return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, struct cgroup *ancestor) { #ifdef CONFIG_SOCK_CGROUP_DATA return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), ancestor); #else return -ENOTSUPP; #endif } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 static inline void sk_sockets_allocated_dec(struct sock *sk) { percpu_counter_add_batch(sk->sk_prot->sockets_allocated, -1, SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline void sk_sockets_allocated_inc(struct sock *sk) { percpu_counter_add_batch(sk->sk_prot->sockets_allocated, 1, SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int proto_sockets_allocated_sum_positive(struct proto *prot) { return percpu_counter_sum_positive(prot->sockets_allocated); } #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { int all; int val[PROTO_INUSE_NR]; }; static inline void sock_prot_inuse_add(const struct net *net, const struct proto *prot, int val) { this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } static inline void sock_inuse_add(const struct net *net, int val) { this_cpu_add(net->core.prot_inuse->all, val); } int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(const struct net *net, const struct proto *prot, int val) { } static inline void sock_inuse_add(const struct net *net, int val) { } #endif /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); return sk->sk_prot->hash(sk); } /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) /* Sockets 0-1023 can't be bound to unless you are superuser */ #define PROT_SOCK 1024 #define SHUTDOWN_MASK 3 #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 struct socket_alloc { struct socket socket; struct inode vfs_inode; }; static inline struct socket *SOCKET_I(struct inode *inode) { return &container_of(inode, struct socket_alloc, vfs_inode)->socket; } static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } /* * Functions for memory accounting */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 /* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { return READ_ONCE(sk->sk_prot->sysctl_mem[index]); } static inline int sk_mem_pages(int amt) { return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) { /* return true if protocol supports memory accounting */ return !!sk->sk_prot->memory_allocated; } static inline bool sk_wmem_schedule(struct sock *sk, int size) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || skb_pfmemalloc(skb); } static inline int sk_unused_reserved_mem(const struct sock *sk) { int unused_mem; if (likely(!sk->sk_reserved_mem)) return 0; unused_mem = sk->sk_reserved_mem - sk->sk_wmem_queued - atomic_read(&sk->sk_rmem_alloc); return unused_mem > 0 ? unused_mem : 0; } static inline void sk_mem_reclaim(struct sock *sk) { int reclaimable; if (!sk_has_account(sk)) return; reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } static inline void sk_mem_reclaim_final(struct sock *sk) { sk->sk_reserved_mem = 0; sk_mem_reclaim(sk); } static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk_forward_alloc_add(sk, -size); } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk_forward_alloc_add(sk, size); sk_mem_reclaim(sk); } /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. * * Mark both the sk_lock and the sk_lock.slock as a * per-address-family lock class. */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) static inline bool lockdep_sock_is_held(const struct sock *sk) { return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } void lock_sock_nested(struct sock *sk, int subclass); static inline void lock_sock(struct sock *sk) { lock_sock_nested(sk, 0); } void __lock_sock(struct sock *sk); void __release_sock(struct sock *sk); void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock)) #define bh_lock_sock_nested(__sk) \ spin_lock_nested(&((__sk)->sk_lock.slock), \ SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); /** * lock_sock_fast - fast version of lock_sock * @sk: socket * * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled * * return true if slow path is taken: * * sk_lock.slock unlocked, owned = 1, BH enabled */ static inline bool lock_sock_fast(struct sock *sk) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); return __lock_sock_fast(sk); } /* fast socket lock variant for caller already holding a [different] socket lock */ static inline bool lock_sock_fast_nested(struct sock *sk) { mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); return __lock_sock_fast(sk); } /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket * @slow: slow mode * * fast unlock socket for user context. * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) __releases(&sk->sk_lock.slock) { if (slow) { release_sock(sk); __release(&sk->sk_lock.slock); } else { mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } void sockopt_lock_sock(struct sock *sk); void sockopt_release_sock(struct sock *sk); bool sockopt_ns_capable(struct user_namespace *ns, int cap); bool sockopt_capable(int cap); /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming * packets, so that we won't get any new data or any * packets that change the state of the socket. * * While locked, BH processing will add new packets to * the backlog queue. This queue is processed by the * owner of the socket lock right before it is released. * * Since ~2.3.5 it is also exclusive sleep lock serializing * accesses from user process context. */ static inline void sock_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks); #endif } static inline void sock_not_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); #endif } static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); return sk->sk_lock.owned; } static inline bool sock_owned_by_user_nocheck(const struct sock *sk) { return sk->sk_lock.owned; } static inline void sock_release_ownership(struct sock *sk) { DEBUG_NET_WARN_ON_ONCE(!sock_owned_by_user_nocheck(sk)); sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; return !sock_owned_by_user_nocheck(sk) && !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); void sk_free_unlock_clone(struct sock *sk); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); if (refcount_inc_not_zero(&sk->sk_refcnt)) { skb->sk = sk; skb->destructor = sock_edemux; } } #else #define sock_edemux sock_efree #endif int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen); int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen); int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); static inline void sock_replace_proto(struct sock *sk, struct proto *proto) { if (sk->sk_socket) clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); WRITE_ONCE(sk->sk_prot, proto); } struct sockcm_cookie { u64 transmit_time; u32 mark; u32 tsflags; u32 ts_opt_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags) }; } int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *); int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); /* * Functions to fill in entries in struct proto_ops when a protocol * uses the inet style. */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); void sk_common_release(struct sock *sk); /* * Default socket callbacks and setup code */ /* Initialise core socket variables using an explicit uid. */ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); /* Initialise core socket variables. * Assumes struct socket *sock is embedded in a struct socket_alloc. */ void sock_init_data(struct socket *sock, struct sock *sk); /* * Socket reference counting postulates. * * * Each user of socket SHOULD hold a reference count. * * Each access point to socket (an hash table bucket, reference from a list, * running timer, skb in flight MUST hold a reference count. * * When reference count hits 0, it means it will never increase back. * * When reference count hits 0, it means that no references from * outside exist to this socket and current process on current CPU * is last user and may/should destroy this socket. * * sk_free is called from any context: process, BH, IRQ. When * it is called, socket has no references from outside -> sk_free * may release descendant resources allocated by the socket, but * to the time when it is called, socket is NOT referenced by any * hash tables, lists etc. * * Packets, delivered from outside (from network or from another process) * and enqueued on receive/error queues SHOULD NOT grab reference count, * when they sit in queue. Otherwise, packets will leak to hole, when * socket is looked up by one cpu and unhasing is made by another CPU. * It is true for udp/raw, netlink (leak to receive and error queues), tcp * (leak to backlog). Packet socket does all the processing inside * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets * use separate SMP lock, so that they are prone too. */ /* Ungrab socket and destroy it, if it was the last reference. */ static inline void sock_put(struct sock *sk) { if (refcount_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } static inline int sk_tx_queue_get(const struct sock *sk) { if (sk) { /* Paired with WRITE_ONCE() in sk_tx_queue_clear() * and sk_tx_queue_set(). */ int val = READ_ONCE(sk->sk_tx_queue_mapping); if (val != NO_QUEUE_MAPPING) return val; } return -1; } static inline void __sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb, bool force_set) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); if (force_set || unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) { __sk_rx_queue_set(sk, skb, true); } static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb) { __sk_rx_queue_set(sk, skb, false); } static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING WRITE_ONCE(sk->sk_rx_queue_mapping, NO_QUEUE_MAPPING); #endif } static inline int sk_rx_queue_get(const struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (sk) { int res = READ_ONCE(sk->sk_rx_queue_mapping); if (res != NO_QUEUE_MAPPING) return res; } #endif return -1; } static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk->sk_socket = sock; } static inline wait_queue_head_t *sk_sleep(struct sock *sk) { BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, * we do not release it in this function, because protocol * probably wants some additional cleanups or even continuing * to work with this socket (TCP). */ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } kuid_t sock_i_uid(struct sock *sk); unsigned long __sock_i_ino(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); } static inline u32 net_tx_rndhash(void) { u32 v = get_random_u32(); return v ?: 1; } static inline void sk_set_txhash(struct sock *sk) { /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } static inline bool sk_rethink_txhash(struct sock *sk) { if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } return false; } static inline struct dst_entry * __sk_dst_get(const struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, lockdep_sock_is_held(sk)); } static inline struct dst_entry * sk_dst_get(const struct sock *sk) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); if (dst && !rcuref_get(&dst->__rcuref)) dst = NULL; rcu_read_unlock(); return dst; } static inline void __dst_negative_advice(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->ops->negative_advice) dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) { sk_rethink_txhash(sk); __dst_negative_advice(sk); } static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst))); dst_release(old_dst); } static inline void __sk_dst_reset(struct sock *sk) { __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { sk_dst_set(sk, NULL); } struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { if (!READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); neigh_confirm(n); } } bool sk_mc_loop(const struct sock *sk); static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst); static inline void sk_gso_disable(struct sock *sk) { sk->sk_gso_disabled = 1; sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; } static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, int copy) { int err, offset = skb->len; err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy), copy, offset); if (err) __skb_trim(skb, offset); return err; } static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from, struct sk_buff *skb, struct page *page, int off, int copy) { int err; err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off, copy, skb->len); if (err) return err; skb_len_add(skb, copy); sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } /** * sk_wmem_alloc_get - returns write allocations * @sk: socket * * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) - 1; } /** * sk_rmem_alloc_get - returns read allocations * @sk: socket * * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { return atomic_read(&sk->sk_rmem_alloc); } /** * sk_has_allocations - check if allocations are outstanding * @sk: socket * * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); } /** * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths:: * * CPU1 CPU2 * sys_select receive packet * ... ... * __add_wait_queue update tp->rcv_nxt * ... ... * tp->rcv_nxt check sock_def_readable * ... { * schedule rcu_read_lock(); * wq = rcu_dereference(sk->sk_wq); * if (wq && waitqueue_active(&wq->wait)) * wake_up_interruptible(&wq->wait) * ... * } * * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 * could then endup calling schedule and sleep forever if there are no more * data on the socket. * */ static inline bool skwq_has_sleeper(struct socket_wq *wq) { return wq && wq_has_sleeper(&wq->wait); } /** * sock_poll_wait - place memory barrier behind the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table * * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { if (!poll_does_not_wait(p)) { poll_wait(filp, &sock->wq.wait, p); /* We need to be sure we are in sync with the * socket flags modification. * * This memory barrier is paired in the wq_has_sleeper. */ smp_mb(); } } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { /* This pairs with WRITE_ONCE() in sk_set_txhash() */ u32 txhash = READ_ONCE(sk->sk_txhash); if (txhash) { skb->l4_hash = 1; skb->hash = txhash; } } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in * and play with them. * * Inlined as it's very short and called for pretty much every * packet ever received. */ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; return true; } return false; } static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) { skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (skb) { if (sk_rmem_schedule(sk, skb, skb->truesize)) { skb_set_owner_r(skb, sk); return skb; } __kfree_skb(skb); } return NULL; } static inline void skb_prepare_for_gro(struct sk_buff *skb) { if (skb->destructor != sock_wfree) { skb_orphan(skb); return; } skb->slow_gro = 1; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); void sk_stop_timer(struct sock *sk, struct timer_list *timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { return sock_queue_rcv_skb_reason(sk, skb, NULL); } int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); /* * Recover an error report and clear atomically */ static inline int sock_error(struct sock *sk) { int err; /* Avoid an atomic operation for the common case. * This is racy since another cpu/thread can change sk_err under us. */ if (likely(data_race(!sk->sk_err))) return 0; err = xchg(&sk->sk_err, 0); return -err; } void sk_error_report(struct sock *sk); static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc); if (amt < 0) amt = 0; } return amt; } /* Note: * We use sk->sk_wq_raw, from contexts knowing this * pointer is not NULL and cannot disappear/change. */ static inline void sk_set_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; clear_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_wake_async(const struct sock *sk, int how, int band) { if (sock_flag(sk, SOCK_FASYNC)) { rcu_read_lock(); sock_wake_async(rcu_dereference(sk->sk_wq), how, band); rcu_read_unlock(); } } static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) { if (unlikely(sock_flag(sk, SOCK_FASYNC))) sock_wake_async(rcu_dereference(sk->sk_wq), how, band); } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at * minimum. */ #define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff))) #define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2) #define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE static inline void sk_stream_moderate_sndbuf(struct sock *sk) { u32 val; if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); val = max_t(u32, val, sk_unused_reserved_mem(sk)); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } /** * sk_page_frag - return an appropriate page_frag * @sk: socket * * Use the per task page_frag instead of the per socket one for * optimization when we know that we're in process context and own * everything that's associated with %current. * * Both direct reclaim and page faults can nest inside other * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag * when users disable sk_use_task_frag. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { if (sk->sk_use_task_frag) return ¤t->task_frag; return &sk->sk_frag; } bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); } static inline gfp_t gfp_any(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline gfp_t gfp_memcg_charge(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; } static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_sndtimeo; } static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); return v ?: 1; } /* Alas, with timeout socket operations are not restartable. * Compare this to poll(). */ static inline int sock_intr_errno(long timeo) { return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } struct sock_skb_cb { u32 dropcount; }; /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? atomic_read(&sk->sk_drops) : 0; } static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) { int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); atomic_add(segs, &sk->sk_drops); } static inline ktime_t sock_read_timestamp(struct sock *sk) { #if BITS_PER_LONG==32 unsigned int seq; ktime_t kt; do { seq = read_seqbegin(&sk->sk_stamp_seq); kt = sk->sk_stamp; } while (read_seqretry(&sk->sk_stamp_seq, seq)); return kt; #else return READ_ONCE(sk->sk_stamp); #endif } static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) { #if BITS_PER_LONG==32 write_seqlock(&sk->sk_stamp_seq); sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else WRITE_ONCE(sk->sk_stamp, kt); #endif } void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); u32 tsflags = READ_ONCE(sk->sk_tsflags); ktime_t kt = skb->tstamp; /* * generate control messages if * - receive time stamping in software requested * - software time stamp available and wanted * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb_wifi_acked_valid(skb)) __sock_recv_wifi_status(msg, sk, skb); } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ (1UL << SOCK_RCVMARK)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) if (sk->sk_flags & FLAGS_RECV_CMSGS || READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @sockc: pointer to socket cmsg cookie to get timestamping info * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ static inline void _sock_tx_timestamp(struct sock *sk, const struct sockcm_cookie *sockc, __u8 *tx_flags, __u32 *tskey) { __u32 tsflags = sockc->tsflags; if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { if (tsflags & SOCKCM_FLAG_TS_OPT_ID) *tskey = sockc->ts_opt_id; else *tskey = atomic_inc_return(&sk->sk_tskey) - 1; } } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } static inline void sock_tx_timestamp(struct sock *sk, const struct sockcm_cookie *sockc, __u8 *tx_flags) { _sock_tx_timestamp(sk, sockc, tx_flags, NULL); } static inline void skb_setup_tx_timestamp(struct sk_buff *skb, const struct sockcm_cookie *sockc) { _sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } static inline bool sk_is_inet(const struct sock *sk) { int family = READ_ONCE(sk->sk_family); return family == AF_INET || family == AF_INET6; } static inline bool sk_is_tcp(const struct sock *sk) { return sk_is_inet(sk) && sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } static inline bool sk_is_udp(const struct sock *sk) { return sk_is_inet(sk) && sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP; } static inline bool sk_is_stream_unix(const struct sock *sk) { return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; } static inline bool sk_is_vsock(const struct sock *sk) { return sk->sk_family == AF_VSOCK; } /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { #ifdef CONFIG_INET return skb->destructor == sock_pfree; #else return false; #endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, * ie _not_ a timewait or request socket. */ static inline bool sk_fullsock(const struct sock *sk) { return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } static inline bool sk_is_refcounted(struct sock *sk) { /* Only full sockets have sk->sk_flags. */ return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. */ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); } else if (unlikely(skb_is_decrypted(skb))) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; } #endif return skb; } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) */ static inline bool sk_listener(const struct sock *sk) { return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE) * TCP RST and ACK can be attached to TIME_WAIT. */ static inline bool sk_listener_or_tw(const struct sock *sk) { return (1 << READ_ONCE(sk->sk_state)) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT); } void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap); bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); void sk_get_meminfo(const struct sock *sk, u32 *meminfo); /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; #define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_wmem ? */ if (proto->sysctl_wmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset)); return READ_ONCE(*proto->sysctl_wmem); } static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_rmem ? */ if (proto->sysctl_rmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset)); return READ_ONCE(*proto->sysctl_rmem); } /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) * Some wifi drivers need to tweak it to get more chunks. * They can use this helper from their ndo_start_xmit() */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device * index is either the same or that the socket is bound to an L3 * master device and the given device index is also enslaved to * that L3 master */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); if (mdif && mdif == bound_dev_if) return true; return false; } void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_set_timestamp(struct sock *sk, int optname, bool valbool); int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping); void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); void sock_set_rcvbuf(struct sock *sk, int val); void sock_set_mark(struct sock *sk, u32 val); void sock_set_reuseaddr(struct sock *sk); void sock_set_reuseport(struct sock *sk); void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval); int sock_ioctl_inout(struct sock *sk, unsigned int cmd, void __user *arg, void *karg, size_t size); int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); static inline bool sk_is_readable(struct sock *sk) { if (sk->sk_prot->sock_is_readable) return sk->sk_prot->sock_is_readable(sk); return false; } #endif /* _SOCK_H */ |
| 34 34 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fsnotify_backend.h> static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL static struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static void __init dnotify_sysctl_init(void) { register_sysctl_init("fs", dnotify_sysctls); } #else #define dnotify_sysctl_init() do { } while (0) #endif static struct kmem_cache *dnotify_struct_cache __ro_after_init; static struct kmem_cache *dnotify_mark_cache __ro_after_init; static struct fsnotify_group *dnotify_group __ro_after_init; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = file_f_owner(dn->dn_filp); send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned int arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } error = file_f_owner_allocate(filp); if (error) goto out_err; /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } f = fget_raw(fd); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); if (f) fput(f); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); dnotify_sysctl_init(); return 0; } module_init(dnotify_init) |
| 582 585 584 582 586 586 585 586 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/page_ext.h> #include <linux/memory.h> #include <linux/vmalloc.h> #include <linux/kmemleak.h> #include <linux/page_owner.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate.h> #include <linux/pgalloc_tag.h> /* * struct page extension * * This is the feature to manage memory for extended data per page. * * Until now, we must modify struct page itself to store extra data per page. * This requires rebuilding the kernel and it is really time consuming process. * And, sometimes, rebuild is impossible due to third party module dependency. * At last, enlarging struct page could cause un-wanted system behaviour change. * * This feature is intended to overcome above mentioned problems. This feature * allocates memory for extended data per page in certain place rather than * the struct page itself. This memory can be accessed by the accessor * functions provided by this code. During the boot process, it checks whether * allocation of huge chunk of memory is needed or not. If not, it avoids * allocating memory at all. With this advantage, we can include this feature * into the kernel in default and can avoid rebuild and solve related problems. * * To help these things to work well, there are two callbacks for clients. One * is the need callback which is mandatory if user wants to avoid useless * memory allocation at boot-time. The other is optional, init callback, which * is used to do proper initialization after memory is allocated. * * The need callback is used to decide whether extended memory allocation is * needed or not. Sometimes users want to deactivate some features in this * boot and extra memory would be unnecessary. In this case, to avoid * allocating huge chunk of memory, each clients represent their need of * extra memory through the need callback. If one of the need callbacks * returns true, it means that someone needs extra memory so that * page extension core should allocates memory for page extension. If * none of need callbacks return true, memory isn't needed at all in this boot * and page extension core can skip to allocate memory. As result, * none of memory is wasted. * * When need callback returns true, page_ext checks if there is a request for * extra memory through size in struct page_ext_operations. If it is non-zero, * extra space is allocated for each page_ext entry and offset is returned to * user through offset in struct page_ext_operations. * * The init callback is used to do proper initialization after page extension * is completely initialized. In sparse memory system, extra memory is * allocated some time later than memmap is allocated. In other words, lifetime * of memory for page extension isn't same with memmap for struct page. * Therefore, clients can't store extra data until page extension is * initialized, even if pages are allocated and used freely. This could * cause inadequate state of extra data per page, so, to prevent it, client * can utilize this callback to initialize the state of it correctly. */ #ifdef CONFIG_SPARSEMEM #define PAGE_EXT_INVALID (0x1) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) static bool need_page_idle(void) { return true; } static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, .need_shared_flags = true, }; #endif static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif #ifdef CONFIG_MEM_ALLOC_PROFILING &page_alloc_tagging_ops, #endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif }; unsigned long page_ext_size; static unsigned long total_usage; #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG /* * To ensure correct allocation tagging for pages, page_ext should be available * before the first page allocation. Otherwise early task stacks will be * allocated before page_ext initialization and missing tags will be flagged. */ bool early_page_ext __meminitdata = true; #else bool early_page_ext __meminitdata; #endif static int __init setup_early_page_ext(char *str) { early_page_ext = true; return 0; } early_param("early_page_ext", setup_early_page_ext); static bool __init invoke_need_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); bool need = false; for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { if (page_ext_ops[i]->need_shared_flags) { page_ext_size = sizeof(struct page_ext); break; } } } for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { page_ext_ops[i]->offset = page_ext_size; page_ext_size += page_ext_ops[i]->size; need = true; } } return need; } static void __init invoke_init_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); for (i = 0; i < entries; i++) { if (page_ext_ops[i]->init) page_ext_ops[i]->init(); } } static inline struct page_ext *get_entry(void *base, unsigned long index) { return base + page_ext_size * index; } #ifndef CONFIG_SPARSEMEM void __init page_ext_init_flatmem_late(void) { invoke_init_callbacks(); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { pgdat->node_page_ext = NULL; } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned long index; struct page_ext *base; WARN_ON_ONCE(!rcu_read_lock_held()); base = NODE_DATA(page_to_nid(page))->node_page_ext; /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (unlikely(!base)) return NULL; index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); } static int __init alloc_node_page_ext(int nid) { struct page_ext *base; unsigned long table_size; unsigned long nr_pages; nr_pages = NODE_DATA(nid)->node_spanned_pages; if (!nr_pages) return 0; /* * Need extra space if node range is not aligned with * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm * checks buddy's status, range could be out of exact node range. */ if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } void __init page_ext_init_flatmem(void) { int nid, fail; if (!invoke_need_callbacks()) return; for_each_online_node(nid) { fail = alloc_node_page_ext(nid); if (fail) goto fail; } pr_info("allocated %ld bytes of page_ext\n", total_usage); return; fail: pr_crit("allocation of page_ext failed.\n"); panic("Out of memory"); } #else /* CONFIG_SPARSEMEM */ static bool page_ext_invalid(struct page_ext *page_ext) { return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID); } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); struct page_ext *page_ext = READ_ONCE(section->page_ext); WARN_ON_ONCE(!rcu_read_lock_held()); /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (page_ext_invalid(page_ext)) return NULL; return get_entry(page_ext, pfn); } static void *__meminit alloc_page_ext(size_t size, int nid) { gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; void *addr = NULL; addr = alloc_pages_exact_nid(nid, size, flags); if (addr) kmemleak_alloc(addr, size, 1, flags); else addr = vzalloc_node(size, nid); if (addr) memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } static int __meminit init_section_page_ext(unsigned long pfn, int nid) { struct mem_section *section; struct page_ext *base; unsigned long table_size; section = __pfn_to_section(pfn); if (section->page_ext) return 0; table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* * The value stored in section->page_ext is (base - pfn) * and it does not point to the memory block allocated above, * causing kmemleak false positives. */ kmemleak_not_leak(base); if (!base) { pr_err("page ext allocation failure\n"); return -ENOMEM; } /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } static void free_page_ext(void *addr) { size_t table_size; struct page *page; table_size = page_ext_size * PAGES_PER_SECTION; memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { vfree(addr); } else { page = virt_to_page(addr); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } } static void __free_page_ext(unsigned long pfn) { struct mem_section *ms; struct page_ext *base; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; base = READ_ONCE(ms->page_ext); /* * page_ext here can be valid while doing the roll back * operation in online_page_ext(). */ if (page_ext_invalid(base)) base = (void *)base - PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, NULL); base = get_entry(base, pfn); free_page_ext(base); } static void __invalidate_page_ext(unsigned long pfn) { struct mem_section *ms; void *val; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; val = (void *)ms->page_ext + PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, val); } static int __meminit online_page_ext(unsigned long start_pfn, unsigned long nr_pages, int nid) { unsigned long start, end, pfn; int fail = 0; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for * online__pages(), and start_pfn should exist. */ nid = pfn_to_nid(start_pfn); VM_BUG_ON(!node_online(nid)); } for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) fail = init_section_page_ext(pfn, nid); if (!fail) return 0; /* rollback */ end = pfn - PAGES_PER_SECTION; for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); return -ENOMEM; } static void __meminit offline_page_ext(unsigned long start_pfn, unsigned long nr_pages) { unsigned long start, end, pfn; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); /* * Freeing of page_ext is done in 3 steps to avoid * use-after-free of it: * 1) Traverse all the sections and mark their page_ext * as invalid. * 2) Wait for all the existing users of page_ext who * started before invalidation to finish. * 3) Free the page_ext. */ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __invalidate_page_ext(pfn); synchronize_rcu(); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); } static int __meminit page_ext_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; int ret = 0; switch (action) { case MEM_GOING_ONLINE: ret = online_page_ext(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; case MEM_OFFLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_CANCEL_ONLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_GOING_OFFLINE: break; case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; } return notifier_from_errno(ret); } void __init page_ext_init(void) { unsigned long pfn; int nid; if (!invoke_need_callbacks()) return; for_each_node_state(nid, N_MEMORY) { unsigned long start_pfn, end_pfn; start_pfn = node_start_pfn(nid); end_pfn = node_end_pfn(nid); /* * start_pfn and end_pfn may not be aligned to SECTION and the * page->flags of out of node pages are not initialized. So we * scan [start_pfn, the biggest section's pfn < end_pfn) here. */ for (pfn = start_pfn; pfn < end_pfn; pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { if (!pfn_valid(pfn)) continue; /* * Nodes's pfns can be overlapping. * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... */ if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; cond_resched(); } } hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI); pr_info("allocated %ld bytes of page_ext\n", total_usage); invoke_init_callbacks(); return; oom: panic("Out of memory"); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { } #endif /** * page_ext_get() - Get the extended information for a page. * @page: The page we're interested in. * * Ensures that the page_ext will remain valid until page_ext_put() * is called. * * Return: NULL if no page_ext exists for this page. * Context: Any context. Caller may not sleep until they have called * page_ext_put(). */ struct page_ext *page_ext_get(const struct page *page) { struct page_ext *page_ext; rcu_read_lock(); page_ext = lookup_page_ext(page); if (!page_ext) { rcu_read_unlock(); return NULL; } return page_ext; } /** * page_ext_put() - Working with page extended information is done. * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. * * Return: None. * Context: Any context with corresponding page_ext_get() is called. */ void page_ext_put(struct page_ext *page_ext) { if (unlikely(!page_ext)) return; rcu_read_unlock(); } |
| 372 | 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. */ #include <linux/completion.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rbtree.h> #include <linux/igmp.h> #include <linux/xarray.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/module.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netevent.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip_fib.h> #include <net/ip6_route.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> #include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> #include <rdma/iw_cm.h> #include "core_priv.h" #include "cma_priv.h" #include "cma_trace.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("Generic RDMA CM Agent"); MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24) #define CMA_IBOE_PACKET_LIFETIME 16 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", [RDMA_CM_EVENT_ADDR_ERROR] = "address error", [RDMA_CM_EVENT_ROUTE_RESOLVED] = "route resolved ", [RDMA_CM_EVENT_ROUTE_ERROR] = "route error", [RDMA_CM_EVENT_CONNECT_REQUEST] = "connect request", [RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response", [RDMA_CM_EVENT_CONNECT_ERROR] = "connect error", [RDMA_CM_EVENT_UNREACHABLE] = "unreachable", [RDMA_CM_EVENT_REJECTED] = "rejected", [RDMA_CM_EVENT_ESTABLISHED] = "established", [RDMA_CM_EVENT_DISCONNECTED] = "disconnected", [RDMA_CM_EVENT_DEVICE_REMOVAL] = "device removal", [RDMA_CM_EVENT_MULTICAST_JOIN] = "multicast join", [RDMA_CM_EVENT_MULTICAST_ERROR] = "multicast error", [RDMA_CM_EVENT_ADDR_CHANGE] = "address change", [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ? cma_events[index] : "unrecognized event"; } EXPORT_SYMBOL(rdma_event_msg); const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return ibcm_reject_msg(reason); if (rdma_protocol_iwarp(id->device, id->port_num)) return iwcm_reject_msg(reason); WARN_ON_ONCE(1); return "unrecognized transport"; } EXPORT_SYMBOL(rdma_reject_msg); /** * rdma_is_consumer_reject - return true if the consumer rejected the connect * request. * @id: Communication identifier that received the REJECT event. * @reason: Value returned in the REJECT event status field. */ static bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return reason == IB_CM_REJ_CONSUMER_DEFINED; if (rdma_protocol_iwarp(id->device, id->port_num)) return reason == -ECONNREFUSED; WARN_ON_ONCE(1); return false; } const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len) { const void *p; if (rdma_is_consumer_reject(id, ev->status)) { *data_len = ev->param.conn.private_data_len; p = ev->param.conn.private_data; } else { *data_len = 0; p = NULL; } return p; } EXPORT_SYMBOL(rdma_consumer_reject_data); /** * rdma_iw_cm_id() - return the iw_cm_id pointer for this cm_id. * @id: Communication Identifier */ struct iw_cm_id *rdma_iw_cm_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); if (id->device->node_type == RDMA_NODE_RNIC) return id_priv->cm_id.iw; return NULL; } EXPORT_SYMBOL(rdma_iw_cm_id); /** * rdma_res_to_id() - return the rdma_cm_id pointer for this restrack. * @res: rdma resource tracking entry pointer */ struct rdma_cm_id *rdma_res_to_id(struct rdma_restrack_entry *res) { struct rdma_id_private *id_priv = container_of(res, struct rdma_id_private, res); return &id_priv->id; } EXPORT_SYMBOL(rdma_res_to_id); static int cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device, void *client_data); static struct ib_client cma_client = { .name = "cma", .add = cma_add_one, .remove = cma_remove_one }; static struct ib_sa_client sa_client; static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct rb_root id_table = RB_ROOT; /* Serialize operations of id_table tree */ static DEFINE_SPINLOCK(id_table_lock); static struct workqueue_struct *cma_wq; static unsigned int cma_pernet_id; struct cma_pernet { struct xarray tcp_ps; struct xarray udp_ps; struct xarray ipoib_ps; struct xarray ib_ps; }; static struct cma_pernet *cma_pernet(struct net *net) { return net_generic(net, cma_pernet_id); } static struct xarray *cma_pernet_xa(struct net *net, enum rdma_ucm_port_space ps) { struct cma_pernet *pernet = cma_pernet(net); switch (ps) { case RDMA_PS_TCP: return &pernet->tcp_ps; case RDMA_PS_UDP: return &pernet->udp_ps; case RDMA_PS_IPOIB: return &pernet->ipoib_ps; case RDMA_PS_IB: return &pernet->ib_ps; default: return NULL; } } struct id_table_entry { struct list_head id_list; struct rb_node rb_node; }; struct cma_device { struct list_head list; struct ib_device *device; struct completion comp; refcount_t refcount; struct list_head id_list; enum ib_gid_type *default_gid_type; u8 *default_roce_tos; }; struct rdma_bind_list { enum rdma_ucm_port_space ps; struct hlist_head owners; unsigned short port; }; static int cma_ps_alloc(struct net *net, enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_insert(xa, snum, bind_list, GFP_KERNEL); } static struct rdma_bind_list *cma_ps_find(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_load(xa, snum); } static void cma_ps_remove(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); xa_erase(xa, snum); } enum { CMA_OPTION_AFONLY, }; void cma_dev_get(struct cma_device *cma_dev) { refcount_inc(&cma_dev->refcount); } void cma_dev_put(struct cma_device *cma_dev) { if (refcount_dec_and_test(&cma_dev->refcount)) complete(&cma_dev->comp); } struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter filter, void *cookie) { struct cma_device *cma_dev; struct cma_device *found_cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) if (filter(cma_dev->device, cookie)) { found_cma_dev = cma_dev; break; } if (found_cma_dev) cma_dev_get(found_cma_dev); mutex_unlock(&lock); return found_cma_dev; } int cma_get_default_gid_type(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_gid_type(struct cma_device *cma_dev, u32 port, enum ib_gid_type default_gid_type) { unsigned long supported_gids; if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; if (default_gid_type == IB_GID_TYPE_IB && rdma_protocol_roce_eth_encap(cma_dev->device, port)) default_gid_type = IB_GID_TYPE_ROCE; supported_gids = roce_gid_type_mask_support(cma_dev->device, port); if (!(supported_gids & 1 << default_gid_type)) return -EINVAL; cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)] = default_gid_type; return 0; } int cma_get_default_roce_tos(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_roce_tos(struct cma_device *cma_dev, u32 port, u8 default_roce_tos) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] = default_roce_tos; return 0; } struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) { return cma_dev->device; } /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. * We do this by disabling removal notification while a callback is in process, * and reporting it after the callback completes. */ struct cma_multicast { struct rdma_id_private *id_priv; union { struct ib_sa_multicast *sa_mc; struct { struct work_struct work; struct rdma_cm_event event; } iboe_join; }; struct list_head list; void *context; struct sockaddr_storage addr; u8 join_state; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; enum rdma_cm_state old_state; enum rdma_cm_state new_state; struct rdma_cm_event event; }; union cma_ip_addr { struct in6_addr ip6; struct { __be32 pad[3]; __be32 addr; } ip4; }; struct cma_hdr { u8 cma_version; u8 ip_version; /* IP version: 7:4 */ __be16 port; union cma_ip_addr src_addr; union cma_ip_addr dst_addr; }; #define CMA_VERSION 0x00 struct cma_req_info { struct sockaddr_storage listen_addr_storage; struct sockaddr_storage src_addr_storage; struct ib_device *device; union ib_gid local_gid; __be64 service_id; int port; bool has_gid; u16 pkey; }; static int cma_comp_exch(struct rdma_id_private *id_priv, enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; /* * The FSM uses a funny double locking where state is protected by both * the handler_mutex and the spinlock. State is not allowed to change * to/from a handler_mutex protected value without also holding * handler_mutex. */ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT) lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); if ((ret = (id_priv->state == comp))) id_priv->state = exch; spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } static inline u8 cma_get_ip_ver(const struct cma_hdr *hdr) { return hdr->ip_version >> 4; } static void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) { hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } static struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.src_addr; } static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.dst_addr; } static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool join) { struct in_device *in_dev = NULL; if (ndev) { rtnl_lock(); in_dev = __in_dev_get_rtnl(ndev); if (in_dev) { if (join) ip_mc_inc_group(in_dev, *(__be32 *)(mgid->raw + 12)); else ip_mc_dec_group(in_dev, *(__be32 *)(mgid->raw + 12)); } rtnl_unlock(); } return (in_dev) ? 0 : -ENODEV; } static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa, struct id_table_entry *entry_b) { struct rdma_id_private *id_priv = list_first_entry( &entry_b->id_list, struct rdma_id_private, id_list_entry); int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if; struct sockaddr *sb = cma_dst_addr(id_priv); if (ifindex_a != ifindex_b) return (ifindex_a > ifindex_b) ? 1 : -1; if (sa->sa_family != sb->sa_family) return sa->sa_family - sb->sa_family; if (sa->sa_family == AF_INET && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in)) { return memcmp(&((struct sockaddr_in *)sa)->sin_addr, &((struct sockaddr_in *)sb)->sin_addr, sizeof(((struct sockaddr_in *)sa)->sin_addr)); } if (sa->sa_family == AF_INET6 && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in6)) { return ipv6_addr_cmp(&((struct sockaddr_in6 *)sa)->sin6_addr, &((struct sockaddr_in6 *)sb)->sin6_addr); } return -1; } static int cma_add_id_to_tree(struct rdma_id_private *node_id_priv) { struct rb_node **new, *parent = NULL; struct id_table_entry *this, *node; unsigned long flags; int result; node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; spin_lock_irqsave(&id_table_lock, flags); new = &id_table.rb_node; while (*new) { this = container_of(*new, struct id_table_entry, rb_node); result = compare_netdev_and_ip( node_id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(node_id_priv), this); parent = *new; if (result < 0) new = &((*new)->rb_left); else if (result > 0) new = &((*new)->rb_right); else { list_add_tail(&node_id_priv->id_list_entry, &this->id_list); kfree(node); goto unlock; } } INIT_LIST_HEAD(&node->id_list); list_add_tail(&node_id_priv->id_list_entry, &node->id_list); rb_link_node(&node->rb_node, parent, new); rb_insert_color(&node->rb_node, &id_table); unlock: spin_unlock_irqrestore(&id_table_lock, flags); return 0; } static struct id_table_entry * node_from_ndev_ip(struct rb_root *root, int ifindex, struct sockaddr *sa) { struct rb_node *node = root->rb_node; struct id_table_entry *data; int result; while (node) { data = container_of(node, struct id_table_entry, rb_node); result = compare_netdev_and_ip(ifindex, sa, data); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return data; } return NULL; } static void cma_remove_id_from_tree(struct rdma_id_private *id_priv) { struct id_table_entry *data; unsigned long flags; spin_lock_irqsave(&id_table_lock, flags); if (list_empty(&id_priv->id_list_entry)) goto out; data = node_from_ndev_ip(&id_table, id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(id_priv)); if (!data) goto out; list_del_init(&id_priv->id_list_entry); if (list_empty(&data->id_list)) { rb_erase(&data->rb_node, &id_table); kfree(data); } out: spin_unlock_irqrestore(&id_table_lock, flags); } static void _cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { cma_dev_get(cma_dev); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; id_priv->id.route.addr.dev_addr.transport = rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->device_item, &cma_dev->id_list); trace_cm_id_attach(id_priv, cma_dev->device); } static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { _cma_attach_to_dev(id_priv, cma_dev); id_priv->gid_type = cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(cma_dev->device)]; } static void cma_release_dev(struct rdma_id_private *id_priv) { mutex_lock(&lock); list_del_init(&id_priv->device_item); cma_dev_put(id_priv->cma_dev); id_priv->cma_dev = NULL; id_priv->id.device = NULL; if (id_priv->id.route.addr.dev_addr.sgid_attr) { rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = NULL; } mutex_unlock(&lock); } static inline unsigned short cma_family(struct rdma_id_private *id_priv) { return id_priv->id.route.addr.src_addr.ss_family; } static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: ib_addr_get_mgid(&id_priv->id.route.addr.dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (!ret) id_priv->qkey = be32_to_cpu(rec.qkey); break; default: break; } return ret; } static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { if (!qkey || (id_priv->qkey && (id_priv->qkey != qkey))) return -EINVAL; id_priv->qkey = qkey; return 0; } static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); } static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) { int ret; if (addr->sa_family != AF_IB) { ret = rdma_translate_ip(addr, dev_addr); } else { cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); ret = 0; } return ret; } static const struct ib_gid_attr * cma_validate_port(struct ib_device *device, u32 port, enum ib_gid_type gid_type, union ib_gid *gid, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr = ERR_PTR(-ENODEV); int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) goto out; if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) goto out; /* * For drivers that do not associate more than one net device with * their gid tables, such as iWARP drivers, it is sufficient to * return the first table entry. * * Other driver classes might be included in the future. */ if (rdma_protocol_iwarp(device, port)) { sgid_attr = rdma_get_gid_attr(device, port, 0); if (IS_ERR(sgid_attr)) goto out; rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); sgid_attr = ERR_PTR(-ENODEV); } rcu_read_unlock(); goto out; } if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } else { gid_type = IB_GID_TYPE_IB; } sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev); dev_put(ndev); out: return sgid_attr; } static void cma_bind_sgid_attr(struct rdma_id_private *id_priv, const struct ib_gid_attr *sgid_attr) { WARN_ON(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = sgid_attr; } /** * cma_acquire_dev_by_src_ip - Acquire cma device, port, gid attribute * based on source ip address. * @id_priv: cm_id which should be bound to cma device * * cma_acquire_dev_by_src_ip() binds cm id to cma device, port and GID attribute * based on source IP address. It returns 0 on success or error code otherwise. * It is applicable to active and passive side cm_id. */ static int cma_acquire_dev_by_src_ip(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; union ib_gid gid, iboe_gid, *gidp; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &iboe_gid); memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { gidp = rdma_protocol_roce(cma_dev->device, port) ? &iboe_gid : &gid; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, gidp, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); cma_attach_to_dev(id_priv, cma_dev); ret = 0; goto out; } } } out: mutex_unlock(&lock); return ret; } /** * cma_ib_acquire_dev - Acquire cma device, port and SGID attribute * @id_priv: cm id to bind to cma device * @listen_id_priv: listener cm id to match against * @req: Pointer to req structure containaining incoming * request information * cma_ib_acquire_dev() acquires cma device, port and SGID attribute when * rdma device matches for listen_id and incoming request. It also verifies * that a GID table entry is present for the source address. * Returns 0 on success, or returns error code otherwise. */ static int cma_ib_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv, struct cma_req_info *req) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; enum ib_gid_type gid_type; union ib_gid gid; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; if (rdma_protocol_roce(req->device, req->port)) rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &gid); else memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); gid_type = listen_id_priv->cma_dev->default_gid_type[req->port - 1]; sgid_attr = cma_validate_port(req->device, req->port, gid_type, &gid, id_priv); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); id_priv->id.port_num = req->port; cma_bind_sgid_attr(id_priv, sgid_attr); /* Need to acquire lock to protect against reader * of cma_dev->id_list such as cma_netdev_callback() and * cma_process_remove(). */ mutex_lock(&lock); cma_attach_to_dev(id_priv, listen_id_priv->cma_dev); mutex_unlock(&lock); rdma_restrack_add(&id_priv->res); return 0; } static int cma_iw_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; union ib_gid gid; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); cma_dev = listen_id_priv->cma_dev; port = listen_id_priv->id.port_num; gid_type = listen_id_priv->gid_type; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { if (listen_id_priv->cma_dev == cma_dev && listen_id_priv->id.port_num == port) continue; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } } } out: if (!ret) { cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); } mutex_unlock(&lock); return ret; } /* * Select the source IB device and address to reach the destination IB address. */ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; struct sockaddr_ib *addr; union ib_gid gid, sgid, *dgid; unsigned int p; u16 pkey, index; enum ib_port_state port_state; int ret; int i; cma_dev = NULL; addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { rdma_for_each_port (cur_dev->device, p) { if (!rdma_cap_af_ib(cur_dev->device, p)) continue; if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) continue; if (ib_get_cached_port_state(cur_dev->device, p, &port_state)) continue; for (i = 0; i < cur_dev->device->port_data[p].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(cur_dev->device, p, i, &gid); if (ret) continue; if (!memcmp(&gid, dgid, sizeof(gid))) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } if (!cma_dev && (gid.global.subnet_prefix == dgid->global.subnet_prefix) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } } } } mutex_unlock(&lock); return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); mutex_unlock(&lock); addr = (struct sockaddr_ib *)cma_src_addr(id_priv); memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } static void cma_id_get(struct rdma_id_private *id_priv) { refcount_inc(&id_priv->refcount); } static void cma_id_put(struct rdma_id_private *id_priv) { if (refcount_dec_and_test(&id_priv->refcount)) complete(&id_priv->comp); } static struct rdma_id_private * __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const struct rdma_id_private *parent) { struct rdma_id_private *id_priv; id_priv = kzalloc(sizeof *id_priv, GFP_KERNEL); if (!id_priv) return ERR_PTR(-ENOMEM); id_priv->state = RDMA_CM_IDLE; id_priv->id.context = context; id_priv->id.event_handler = event_handler; id_priv->id.ps = ps; id_priv->id.qp_type = qp_type; id_priv->tos_set = false; id_priv->timeout_set = false; id_priv->min_rnr_timer_set = false; id_priv->gid_type = IB_GID_TYPE_IB; spin_lock_init(&id_priv->lock); mutex_init(&id_priv->qp_mutex); init_completion(&id_priv->comp); refcount_set(&id_priv->refcount, 1); mutex_init(&id_priv->handler_mutex); INIT_LIST_HEAD(&id_priv->device_item); INIT_LIST_HEAD(&id_priv->id_list_entry); INIT_LIST_HEAD(&id_priv->listen_list); INIT_LIST_HEAD(&id_priv->mc_list); get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num); id_priv->id.route.addr.dev_addr.net = get_net(net); id_priv->seq_num &= 0x00ffffff; rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID); if (parent) rdma_restrack_parent_name(&id_priv->res, &parent->res); return id_priv; } struct rdma_cm_id * __rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const char *caller) { struct rdma_id_private *ret; ret = __rdma_create_id(net, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, caller); return &ret->id; } EXPORT_SYMBOL(__rdma_create_kernel_id); struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type) { struct rdma_id_private *ret; ret = __rdma_create_id(current->nsproxy->net_ns, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, NULL); return &ret->id; } EXPORT_SYMBOL(rdma_create_user_id); static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTR; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTS; qp_attr.sq_psn = 0; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE | IB_QP_SQ_PSN); return ret; } static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; return ib_modify_qp(qp, &qp_attr, qp_attr_mask); } int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr) { struct rdma_id_private *id_priv; struct ib_qp *qp; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (id->device != pd->device) { ret = -EINVAL; goto out_err; } qp_init_attr->port_num = id->port_num; qp = ib_create_qp(pd, qp_init_attr); if (IS_ERR(qp)) { ret = PTR_ERR(qp); goto out_err; } if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); else ret = cma_init_conn_qp(id_priv, qp); if (ret) goto out_destroy; id->qp = qp; id_priv->qp_num = qp->qp_num; id_priv->srq = (qp->srq != NULL); trace_cm_qp_create(id_priv, pd, qp_init_attr, 0); return 0; out_destroy: ib_destroy_qp(qp); out_err: trace_cm_qp_create(id_priv, pd, qp_init_attr, ret); return ret; } EXPORT_SYMBOL(rdma_create_qp); void rdma_destroy_qp(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); trace_cm_qp_destroy(id_priv); mutex_lock(&id_priv->qp_mutex); ib_destroy_qp(id_priv->id.qp); id_priv->id.qp = NULL; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_destroy_qp); static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } /* Need to update QP attributes from default values. */ qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); if (ret) goto out; qp_attr.qp_state = IB_QPS_RTR; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; BUG_ON(id_priv->cma_dev->device != id_priv->id.device); if (conn_param) qp_attr.max_dest_rd_atomic = conn_param->responder_resources; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_rts(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_RTS; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; if (conn_param) qp_attr.max_rd_atomic = conn_param->initiator_depth; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_err(struct rdma_id_private *id_priv) { struct ib_qp_attr qp_attr; int ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_ERR; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; u16 pkey; if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num)) pkey = 0xffff; else pkey = ib_addr_get_pkey(dev_addr); ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, pkey, &qp_attr->pkey_index); if (ret) return ret; qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; qp_attr->qkey = id_priv->qkey; *qp_attr_mask |= IB_QP_QKEY; } else { qp_attr->qp_access_flags = 0; *qp_attr_mask |= IB_QP_ACCESS_FLAGS; } return 0; } int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_id_private *id_priv; int ret = 0; id_priv = container_of(id, struct rdma_id_private, id); if (rdma_cap_ib_cm(id->device, id->port_num)) { if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr, qp_attr_mask); if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; } else if (rdma_cap_iw_cm(id->device, id->port_num)) { if (!id_priv->cm_id.iw) { qp_attr->qp_access_flags = 0; *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask |= IB_QP_PORT; } else { ret = -ENOSYS; } if ((*qp_attr_mask & IB_QP_TIMEOUT) && id_priv->timeout_set) qp_attr->timeout = id_priv->timeout; if ((*qp_attr_mask & IB_QP_MIN_RNR_TIMER) && id_priv->min_rnr_timer_set) qp_attr->min_rnr_timer = id_priv->min_rnr_timer; return ret; } EXPORT_SYMBOL(rdma_init_qp_attr); static inline bool cma_zero_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_any(&((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_any(&((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_loopback_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_loopback( ((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_loopback( &((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_loopback( &((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_any_addr(const struct sockaddr *addr) { return cma_zero_addr(addr) || cma_loopback_addr(addr); } static int cma_addr_cmp(const struct sockaddr *src, const struct sockaddr *dst) { if (src->sa_family != dst->sa_family) return -1; switch (src->sa_family) { case AF_INET: return ((struct sockaddr_in *)src)->sin_addr.s_addr != ((struct sockaddr_in *)dst)->sin_addr.s_addr; case AF_INET6: { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)src; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst; bool link_local; if (ipv6_addr_cmp(&src_addr6->sin6_addr, &dst_addr6->sin6_addr)) return 1; link_local = ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL; /* Link local must match their scope_ids */ return link_local ? (src_addr6->sin6_scope_id != dst_addr6->sin6_scope_id) : 0; } default: return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, &((struct sockaddr_ib *) dst)->sib_addr); } } static __be16 cma_port(const struct sockaddr *addr) { struct sockaddr_ib *sib; switch (addr->sa_family) { case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; case AF_IB: sib = (struct sockaddr_ib *) addr; return htons((u16) (be64_to_cpu(sib->sib_sid) & be64_to_cpu(sib->sib_sid_mask))); default: return 0; } } static inline int cma_any_port(const struct sockaddr *addr) { return !cma_port(addr); } static void cma_save_ib_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct sa_path_rec *path) { struct sockaddr_ib *listen_ib, *ib; listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; if (src_addr) { ib = (struct sockaddr_ib *)src_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->sgid, 16); ib->sib_sid = path->service_id; ib->sib_scope_id = 0; } else { ib->sib_pkey = listen_ib->sib_pkey; ib->sib_flowinfo = listen_ib->sib_flowinfo; ib->sib_addr = listen_ib->sib_addr; ib->sib_sid = listen_ib->sib_sid; ib->sib_scope_id = listen_ib->sib_scope_id; } ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); } if (dst_addr) { ib = (struct sockaddr_ib *)dst_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->dgid, 16); } } } static void cma_save_ip4_info(struct sockaddr_in *src_addr, struct sockaddr_in *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->dst_addr.ip4.addr, .sin_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->src_addr.ip4.addr, .sin_port = hdr->port, }; } } static void cma_save_ip6_info(struct sockaddr_in6 *src_addr, struct sockaddr_in6 *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->dst_addr.ip6, .sin6_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->src_addr.ip6, .sin6_port = hdr->port, }; } } static u16 cma_port_from_service_id(__be64 service_id) { return (u16)be64_to_cpu(service_id); } static int cma_save_ip_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct ib_cm_event *ib_event, __be64 service_id) { struct cma_hdr *hdr; __be16 port; hdr = ib_event->private_data; if (hdr->cma_version != CMA_VERSION) return -EINVAL; port = htons(cma_port_from_service_id(service_id)); switch (cma_get_ip_ver(hdr)) { case 4: cma_save_ip4_info((struct sockaddr_in *)src_addr, (struct sockaddr_in *)dst_addr, hdr, port); break; case 6: cma_save_ip6_info((struct sockaddr_in6 *)src_addr, (struct sockaddr_in6 *)dst_addr, hdr, port); break; default: return -EAFNOSUPPORT; } return 0; } static int cma_save_net_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, sa_family_t sa_family, __be64 service_id) { if (sa_family == AF_IB) { if (ib_event->event == IB_CM_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, ib_event->param.req_rcvd.primary_path); else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, NULL); return 0; } return cma_save_ip_info(src_addr, dst_addr, ib_event, service_id); } static int cma_save_req_info(const struct ib_cm_event *ib_event, struct cma_req_info *req) { const struct ib_cm_req_event_param *req_param = &ib_event->param.req_rcvd; const struct ib_cm_sidr_req_event_param *sidr_param = &ib_event->param.sidr_req_rcvd; switch (ib_event->event) { case IB_CM_REQ_RECEIVED: req->device = req_param->listen_id->device; req->port = req_param->port; memcpy(&req->local_gid, &req_param->primary_path->sgid, sizeof(req->local_gid)); req->has_gid = true; req->service_id = req_param->primary_path->service_id; req->pkey = be16_to_cpu(req_param->primary_path->pkey); if (req->pkey != req_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and primary path P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", req_param->bth_pkey, req->pkey); break; case IB_CM_SIDR_REQ_RECEIVED: req->device = sidr_param->listen_id->device; req->port = sidr_param->port; req->has_gid = false; req->service_id = sidr_param->service_id; req->pkey = sidr_param->pkey; if (req->pkey != sidr_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and SIDR request payload P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", sidr_param->bth_pkey, req->pkey); break; default: return -EINVAL; } return 0; } static bool validate_ipv4_net_dev(struct net_device *net_dev, const struct sockaddr_in *dst_addr, const struct sockaddr_in *src_addr) { __be32 daddr = dst_addr->sin_addr.s_addr, saddr = src_addr->sin_addr.s_addr; struct fib_result res; struct flowi4 fl4; int err; bool ret; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || ipv4_is_lbcast(daddr) || ipv4_is_zeronet(saddr) || ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr) || ipv4_is_loopback(saddr)) return false; memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; rcu_read_lock(); err = fib_lookup(dev_net(net_dev), &fl4, &res, 0); ret = err == 0 && FIB_RES_DEV(res) == net_dev; rcu_read_unlock(); return ret; } static bool validate_ipv6_net_dev(struct net_device *net_dev, const struct sockaddr_in6 *dst_addr, const struct sockaddr_in6 *src_addr) { #if IS_ENABLED(CONFIG_IPV6) const int strict = ipv6_addr_type(&dst_addr->sin6_addr) & IPV6_ADDR_LINKLOCAL; struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr, &src_addr->sin6_addr, net_dev->ifindex, NULL, strict); bool ret; if (!rt) return false; ret = rt->rt6i_idev->dev == net_dev; ip6_rt_put(rt); return ret; #else return false; #endif } static bool validate_net_dev(struct net_device *net_dev, const struct sockaddr *daddr, const struct sockaddr *saddr) { const struct sockaddr_in *daddr4 = (const struct sockaddr_in *)daddr; const struct sockaddr_in *saddr4 = (const struct sockaddr_in *)saddr; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; const struct sockaddr_in6 *saddr6 = (const struct sockaddr_in6 *)saddr; switch (daddr->sa_family) { case AF_INET: return saddr->sa_family == AF_INET && validate_ipv4_net_dev(net_dev, daddr4, saddr4); case AF_INET6: return saddr->sa_family == AF_INET6 && validate_ipv6_net_dev(net_dev, daddr6, saddr6); default: return false; } } static struct net_device * roce_get_net_dev_by_cm_event(const struct ib_cm_event *ib_event) { const struct ib_gid_attr *sgid_attr = NULL; struct net_device *ndev; if (ib_event->event == IB_CM_REQ_RECEIVED) sgid_attr = ib_event->param.req_rcvd.ppath_sgid_attr; else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) sgid_attr = ib_event->param.sidr_req_rcvd.sgid_attr; if (!sgid_attr) return NULL; rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(sgid_attr); if (IS_ERR(ndev)) ndev = NULL; else dev_hold(ndev); rcu_read_unlock(); return ndev; } static struct net_device *cma_get_net_dev(const struct ib_cm_event *ib_event, struct cma_req_info *req) { struct sockaddr *listen_addr = (struct sockaddr *)&req->listen_addr_storage; struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage; struct net_device *net_dev; const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL; int err; err = cma_save_ip_info(listen_addr, src_addr, ib_event, req->service_id); if (err) return ERR_PTR(err); if (rdma_protocol_roce(req->device, req->port)) net_dev = roce_get_net_dev_by_cm_event(ib_event); else net_dev = ib_get_net_dev_by_params(req->device, req->port, req->pkey, gid, listen_addr); if (!net_dev) return ERR_PTR(-ENODEV); return net_dev; } static enum rdma_ucm_port_space rdma_ps_from_service_id(__be64 service_id) { return (be64_to_cpu(service_id) >> 16) & 0xffff; } static bool cma_match_private_data(struct rdma_id_private *id_priv, const struct cma_hdr *hdr) { struct sockaddr *addr = cma_src_addr(id_priv); __be32 ip4_addr; struct in6_addr ip6_addr; if (cma_any_addr(addr) && !id_priv->afonly) return true; switch (addr->sa_family) { case AF_INET: ip4_addr = ((struct sockaddr_in *)addr)->sin_addr.s_addr; if (cma_get_ip_ver(hdr) != 4) return false; if (!cma_any_addr(addr) && hdr->dst_addr.ip4.addr != ip4_addr) return false; break; case AF_INET6: ip6_addr = ((struct sockaddr_in6 *)addr)->sin6_addr; if (cma_get_ip_ver(hdr) != 6) return false; if (!cma_any_addr(addr) && memcmp(&hdr->dst_addr.ip6, &ip6_addr, sizeof(ip6_addr))) return false; break; case AF_IB: return true; default: return false; } return true; } static bool cma_protocol_roce(const struct rdma_cm_id *id) { struct ib_device *device = id->device; const u32 port_num = id->port_num ?: rdma_start_port(device); return rdma_protocol_roce(device, port_num); } static bool cma_is_req_ipv6_ll(const struct cma_req_info *req) { const struct sockaddr *daddr = (const struct sockaddr *)&req->listen_addr_storage; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; /* Returns true if the req is for IPv6 link local */ return (daddr->sa_family == AF_INET6 && (ipv6_addr_type(&daddr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)); } static bool cma_match_net_dev(const struct rdma_cm_id *id, const struct net_device *net_dev, const struct cma_req_info *req) { const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request */ return (!id->port_num || id->port_num == req->port) && (addr->src_addr.ss_family == AF_IB); /* * If the request is not for IPv6 link local, allow matching * request to any netdevice of the one or multiport rdma device. */ if (!cma_is_req_ipv6_ll(req)) return true; /* * Net namespaces must match, and if the listner is listening * on a specific netdevice than netdevice must match as well. */ if (net_eq(dev_net(net_dev), addr->dev_addr.net) && (!!addr->dev_addr.bound_dev_if == (addr->dev_addr.bound_dev_if == net_dev->ifindex))) return true; else return false; } static struct rdma_id_private *cma_find_listener( const struct rdma_bind_list *bind_list, const struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, const struct cma_req_info *req, const struct net_device *net_dev) { struct rdma_id_private *id_priv, *id_priv_dev; lockdep_assert_held(&lock); if (!bind_list) return ERR_PTR(-EINVAL); hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && cma_match_net_dev(&id_priv->id, net_dev, req)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_item) { if (id_priv_dev->id.device == cm_id->device && cma_match_net_dev(&id_priv_dev->id, net_dev, req)) return id_priv_dev; } } } return ERR_PTR(-EINVAL); } static struct rdma_id_private * cma_ib_id_from_event(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, struct cma_req_info *req, struct net_device **net_dev) { struct rdma_bind_list *bind_list; struct rdma_id_private *id_priv; int err; err = cma_save_req_info(ib_event, req); if (err) return ERR_PTR(err); *net_dev = cma_get_net_dev(ib_event, req); if (IS_ERR(*net_dev)) { if (PTR_ERR(*net_dev) == -EAFNOSUPPORT) { /* Assuming the protocol is AF_IB */ *net_dev = NULL; } else { return ERR_CAST(*net_dev); } } mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice * validation, cm_id lookup under rcu lock. * RCU lock along with netdevice state check, synchronizes with * netdevice migrating to different net namespace and also avoids * case where net namespace doesn't get deleted while lookup is in * progress. * If the device state is not IFF_UP, its properties such as ifindex * and nd_net cannot be trusted to remain valid without rcu lock. * net/core/dev.c change_net_namespace() ensures to synchronize with * ongoing operations on net device after device is closed using * synchronize_net(). */ rcu_read_lock(); if (*net_dev) { /* * If netdevice is down, it is likely that it is administratively * down or it might be migrating to different namespace. * In that case avoid further processing, as the net namespace * or ifindex may change. */ if (((*net_dev)->flags & IFF_UP) == 0) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } if (!validate_net_dev(*net_dev, (struct sockaddr *)&req->src_addr_storage, (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } } bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net, rdma_ps_from_service_id(req->service_id), cma_port_from_service_id(req->service_id)); id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; } return id_priv; } static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } static void cma_cancel_route(struct rdma_id_private *id_priv) { if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) { if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); } } static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; lockdep_assert_held(&lock); /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ list_del_init(&id_priv->listen_any_item); while (!list_empty(&id_priv->listen_list)) { dev_id_priv = list_first_entry(&id_priv->listen_list, struct rdma_id_private, listen_item); /* sync with device removal to avoid duplicate destruction */ list_del_init(&dev_id_priv->device_item); list_del_init(&dev_id_priv->listen_item); mutex_unlock(&lock); rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } } static void cma_cancel_listens(struct rdma_id_private *id_priv) { mutex_lock(&lock); _cma_cancel_listens(id_priv); mutex_unlock(&lock); } static void cma_cancel_operation(struct rdma_id_private *id_priv, enum rdma_cm_state state) { switch (state) { case RDMA_CM_ADDR_QUERY: /* * We can avoid doing the rdma_addr_cancel() based on state, * only RDMA_CM_ADDR_QUERY has a work that could still execute. * Notice that the addr_handler work could still be exiting * outside this state, however due to the interaction with the * handler_mutex the work is guaranteed not to touch id_priv * during exit. */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: cma_cancel_route(id_priv); break; case RDMA_CM_LISTEN: if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) cma_cancel_listens(id_priv); break; default: break; } } static void cma_release_port(struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list = id_priv->bind_list; struct net *net = id_priv->id.route.addr.dev_addr.net; if (!bind_list) return; mutex_lock(&lock); hlist_del(&id_priv->node); if (hlist_empty(&bind_list->owners)) { cma_ps_remove(net, bind_list->ps, bind_list->port); kfree(bind_list); } mutex_unlock(&lock); } static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (ndev && !send_only) { enum ib_gid_type gid_type; union ib_gid mgid; gid_type = id_priv->cma_dev->default_gid_type [id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; cma_iboe_set_mgid((struct sockaddr *)&mc->addr, &mgid, gid_type); cma_igmp_send(ndev, &mgid, false); } dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); } kfree(mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) { struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, list); list_del(&mc->list); destroy_mc(id_priv, mc); } } static void _destroy_id(struct rdma_id_private *id_priv, enum rdma_cm_state state) { cma_cancel_operation(id_priv, state); rdma_restrack_del(&id_priv->res); cma_remove_id_from_tree(id_priv); if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); } else if (rdma_cap_iw_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); } cma_leave_mc_groups(id_priv); cma_release_dev(id_priv); } cma_release_port(id_priv); cma_id_put(id_priv); wait_for_completion(&id_priv->comp); if (id_priv->internal_id) cma_id_put(id_priv->id.context); kfree(id_priv->id.route.path_rec); kfree(id_priv->id.route.path_rec_inbound); kfree(id_priv->id.route.path_rec_outbound); put_net(id_priv->id.route.addr.dev_addr.net); kfree(id_priv); } /* * destroy an ID from within the handler_mutex. This ensures that no other * handlers can start running concurrently. */ static void destroy_id_handler_unlock(struct rdma_id_private *id_priv) __releases(&idprv->handler_mutex) { enum rdma_cm_state state; unsigned long flags; trace_cm_id_destroy(id_priv); /* * Setting the state to destroyed under the handler mutex provides a * fence against calling handler callbacks. If this is invoked due to * the failure of a handler callback then it guarentees that no future * handlers will be called. */ lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; id_priv->state = RDMA_CM_DESTROYING; spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); _destroy_id(id_priv, state); } void rdma_destroy_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); destroy_id_handler_unlock(id_priv); } EXPORT_SYMBOL(rdma_destroy_id); static int cma_rep_recv(struct rdma_id_private *id_priv) { int ret; ret = cma_modify_qp_rtr(id_priv, NULL); if (ret) goto reject; ret = cma_modify_qp_rts(id_priv, NULL); if (ret) goto reject; trace_cm_send_rtu(id_priv); ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0); if (ret) goto reject; return 0; reject: pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret); cma_modify_qp_err(id_priv); trace_cm_send_rej(id_priv); ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, NULL, 0); return ret; } static void cma_set_rep_event_data(struct rdma_cm_event *event, const struct ib_cm_rep_event_param *rep_data, void *private_data) { event->param.conn.private_data = private_data; event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; event->param.conn.responder_resources = rep_data->responder_resources; event->param.conn.initiator_depth = rep_data->initiator_depth; event->param.conn.flow_control = rep_data->flow_control; event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; event->param.conn.srq = rep_data->srq; event->param.conn.qp_num = rep_data->remote_qpn; event->ece.vendor_id = rep_data->ece.vendor_id; event->ece.attr_mod = rep_data->ece.attr_mod; } static int cma_cm_event_handler(struct rdma_id_private *id_priv, struct rdma_cm_event *event) { int ret; lockdep_assert_held(&id_priv->handler_mutex); trace_cm_event_handler(id_priv, event); ret = id_priv->id.event_handler(&id_priv->id, event); trace_cm_event_done(id_priv, event, ret); return ret; } static int cma_ib_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; enum rdma_cm_state state; int ret; mutex_lock(&id_priv->handler_mutex); state = READ_ONCE(id_priv->state); if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_CONNECT) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_DISCONNECT)) goto out; switch (ib_event->event) { case IB_CM_REQ_ERROR: case IB_CM_REP_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: if (state == RDMA_CM_CONNECT && (id_priv->id.qp_type != IB_QPT_UD)) { trace_cm_send_mra(id_priv); ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); } if (id_priv->id.qp) { event.status = cma_rep_recv(id_priv); event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : RDMA_CM_EVENT_ESTABLISHED; } else { event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; } cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, ib_event->private_data); break; case IB_CM_RTU_RECEIVED: case IB_CM_USER_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: event.status = -ETIMEDOUT; fallthrough; case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_DISCONNECT)) goto out; event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IB_CM_TIMEWAIT_EXIT: event.event = RDMA_CM_EVENT_TIMEWAIT_EXIT; break; case IB_CM_MRA_RECEIVED: /* ignore event */ goto out; case IB_CM_REJ_RECEIVED: pr_debug_ratelimited("RDMA CM: REJECTED: %s\n", rdma_reject_msg(&id_priv->id, ib_event->param.rej_rcvd.reason)); cma_modify_qp_err(id_priv); event.status = ib_event->param.rej_rcvd.reason; event.event = RDMA_CM_EVENT_REJECTED; event.param.conn.private_data = ib_event->private_data; event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static struct rdma_id_private * cma_ib_new_conn_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; struct rdma_route *rt; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct sa_path_rec *path = ib_event->param.req_rcvd.primary_path; const __be64 service_id = ib_event->param.req_rcvd.primary_path->service_id; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(listen_id->route.addr.dev_addr.net, listen_id->event_handler, listen_id->context, listen_id->ps, ib_event->param.req_rcvd.qp_type, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, service_id)) goto err; rt = &id->route; rt->num_pri_alt_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1; rt->path_rec = kmalloc_array(rt->num_pri_alt_paths, sizeof(*rt->path_rec), GFP_KERNEL); if (!rt->path_rec) goto err; rt->path_rec[0] = *path; if (rt->num_pri_alt_paths == 2) rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path; if (net_dev) { rdma_copy_src_l2_addr(&rt->addr.dev_addr, net_dev); } else { if (!cma_protocol_roce(listen_id) && cma_any_addr(cma_src_addr(id_priv))) { rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); } else if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); if (ret) goto err; } } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static struct rdma_id_private * cma_ib_new_udp_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { const struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct net *net = listen_id->route.addr.dev_addr.net; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(net, listen_id->event_handler, listen_id->context, listen_id->ps, IB_QPT_UD, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, ib_event->param.sidr_req_rcvd.service_id)) goto err; if (net_dev) { rdma_copy_src_l2_addr(&id->route.addr.dev_addr, net_dev); } else { if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &id->route.addr.dev_addr); if (ret) goto err; } } id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static void cma_set_req_event_data(struct rdma_cm_event *event, const struct ib_cm_req_event_param *req_data, void *private_data, int offset) { event->param.conn.private_data = private_data + offset; event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset; event->param.conn.responder_resources = req_data->responder_resources; event->param.conn.initiator_depth = req_data->initiator_depth; event->param.conn.flow_control = req_data->flow_control; event->param.conn.retry_count = req_data->retry_count; event->param.conn.rnr_retry_count = req_data->rnr_retry_count; event->param.conn.srq = req_data->srq; event->param.conn.qp_num = req_data->remote_qpn; event->ece.vendor_id = req_data->ece.vendor_id; event->ece.attr_mod = req_data->ece.attr_mod; } static int cma_ib_check_req_qp_type(const struct rdma_cm_id *id, const struct ib_cm_event *ib_event) { return (((ib_event->event == IB_CM_REQ_RECEIVED) && (ib_event->param.req_rcvd.qp_type == id->qp_type)) || ((ib_event->event == IB_CM_SIDR_REQ_RECEIVED) && (id->qp_type == IB_QPT_UD)) || (!id->qp_type)); } static int cma_ib_req_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event = {}; struct cma_req_info req = {}; struct net_device *net_dev; u8 offset; int ret; listen_id = cma_ib_id_from_event(cm_id, ib_event, &req, &net_dev); if (IS_ERR(listen_id)) return PTR_ERR(listen_id); trace_cm_req_handler(listen_id, ib_event->event); if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) { ret = -EINVAL; goto net_dev_put; } mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) { ret = -ECONNABORTED; goto err_unlock; } offset = cma_user_data_offset(listen_id); event.event = RDMA_CM_EVENT_CONNECT_REQUEST; if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) { conn_id = cma_ib_new_udp_id(&listen_id->id, ib_event, net_dev); event.param.ud.private_data = ib_event->private_data + offset; event.param.ud.private_data_len = IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset; } else { conn_id = cma_ib_new_conn_id(&listen_id->id, ib_event, net_dev); cma_set_req_event_data(&event, &ib_event->param.req_rcvd, ib_event->private_data, offset); } if (!conn_id) { ret = -ENOMEM; goto err_unlock; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); ret = cma_ib_acquire_dev(conn_id, listen_id, &req); if (ret) { destroy_id_handler_unlock(conn_id); goto err_unlock; } conn_id->cm_id.ib = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ conn_id->cm_id.ib = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); goto net_dev_put; } if (READ_ONCE(conn_id->state) == RDMA_CM_CONNECT && conn_id->id.qp_type != IB_QPT_UD) { trace_cm_send_mra(cm_id->context); ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); } mutex_unlock(&conn_id->handler_mutex); err_unlock: mutex_unlock(&listen_id->handler_mutex); net_dev_put: dev_put(net_dev); return ret; } __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) { if (addr->sa_family == AF_IB) return ((struct sockaddr_ib *) addr)->sib_sid; return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr))); } EXPORT_SYMBOL(rdma_get_service_id); void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, union ib_gid *dgid) { struct rdma_addr *addr = &cm_id->route.addr; if (!cm_id->device) { if (sgid) memset(sgid, 0, sizeof(*sgid)); if (dgid) memset(dgid, 0, sizeof(*dgid)); return; } if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) { if (sgid) rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid); if (dgid) rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid); } else { if (sgid) rdma_addr_get_sgid(&addr->dev_addr, sgid); if (dgid) rdma_addr_get_dgid(&addr->dev_addr, dgid); } } EXPORT_SYMBOL(rdma_read_gids); static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; struct rdma_cm_event event = {}; int ret = 0; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (iw_event->event) { case IW_CM_EVENT_CLOSE: event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: memcpy(cma_src_addr(id_priv), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(id_priv), raddr, rdma_addr_size(raddr)); switch (iw_event->status) { case 0: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; case -ECONNRESET: case -ECONNREFUSED: event.event = RDMA_CM_EVENT_REJECTED; break; case -ETIMEDOUT: event.event = RDMA_CM_EVENT_UNREACHABLE; break; default: event.event = RDMA_CM_EVENT_CONNECT_ERROR; break; } break; case IW_CM_EVENT_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; default: goto out; } event.status = iw_event->status; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return ret; } static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct iw_cm_event *iw_event) { struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event = {}; int ret = -ECONNABORTED; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; event.event = RDMA_CM_EVENT_CONNECT_REQUEST; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; listen_id = cm_id->context; mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) goto out; /* Create a new RDMA id for the new IW CM ID */ conn_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net, listen_id->id.event_handler, listen_id->id.context, RDMA_PS_TCP, IB_QPT_RC, listen_id); if (IS_ERR(conn_id)) { ret = -ENOMEM; goto out; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); conn_id->state = RDMA_CM_CONNECT; ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } ret = cma_iw_acquire_dev(conn_id, listen_id); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; memcpy(cma_src_addr(conn_id), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(conn_id), raddr, rdma_addr_size(raddr)); ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } mutex_unlock(&conn_id->handler_mutex); out: mutex_unlock(&listen_id->handler_mutex); return ret; } static int cma_ib_listen(struct rdma_id_private *id_priv) { struct sockaddr *addr; struct ib_cm_id *id; __be64 svc_id; addr = cma_src_addr(id_priv); svc_id = rdma_get_service_id(&id_priv->id, addr); id = ib_cm_insert_listen(id_priv->id.device, cma_ib_req_handler, svc_id); if (IS_ERR(id)) return PTR_ERR(id); id_priv->cm_id.ib = id; return 0; } static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog) { int ret; struct iw_cm_id *id; id = iw_create_cm_id(id_priv->id.device, iw_conn_req_handler, id_priv); if (IS_ERR(id)) return PTR_ERR(id); mutex_lock(&id_priv->qp_mutex); id->tos = id_priv->tos; id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id->afonly = id_priv->afonly; id_priv->cm_id.iw = id; memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); ret = iw_cm_listen(id_priv->cm_id.iw, backlog); if (ret) { iw_destroy_cm_id(id_priv->cm_id.iw); id_priv->cm_id.iw = NULL; } return ret; } static int cma_listen_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct rdma_id_private *id_priv = id->context; /* Listening IDs are always destroyed on removal */ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) return -1; id->context = id_priv->id.context; id->event_handler = id_priv->id.event_handler; trace_cm_event_handler(id_priv, event); return id_priv->id.event_handler(id, event); } static int cma_listen_on_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev, struct rdma_id_private **to_destroy) { struct rdma_id_private *dev_id_priv; struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; lockdep_assert_held(&lock); *to_destroy = NULL; if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return 0; dev_id_priv = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps, id_priv->id.qp_type, id_priv); if (IS_ERR(dev_id_priv)) return PTR_ERR(dev_id_priv); dev_id_priv->state = RDMA_CM_ADDR_BOUND; memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); _cma_attach_to_dev(dev_id_priv, cma_dev); rdma_restrack_add(&dev_id_priv->res); cma_id_get(id_priv); dev_id_priv->internal_id = 1; dev_id_priv->afonly = id_priv->afonly; mutex_lock(&id_priv->qp_mutex); dev_id_priv->tos_set = id_priv->tos_set; dev_id_priv->tos = id_priv->tos; mutex_unlock(&id_priv->qp_mutex); ret = rdma_listen(&dev_id_priv->id, id_priv->backlog); if (ret) goto err_listen; list_add_tail(&dev_id_priv->listen_item, &id_priv->listen_list); return 0; err_listen: /* Caller must destroy this after releasing lock */ *to_destroy = dev_id_priv; dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret); return ret; } static int cma_listen_on_all(struct rdma_id_private *id_priv) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; int ret; mutex_lock(&lock); list_add_tail(&id_priv->listen_any_item, &listen_any_list); list_for_each_entry(cma_dev, &dev_list, list) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) { /* Prevent racing with cma_process_remove() */ if (to_destroy) list_del_init(&to_destroy->device_item); goto err_listen; } } mutex_unlock(&lock); return 0; err_listen: _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); return ret; } void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->tos = (u8) tos; id_priv->tos_set = true; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_set_service_type); /** * rdma_set_ack_timeout() - Set the ack timeout of QP associated * with a connection identifier. * @id: Communication identifier to associated with service type. * @timeout: Ack timeout to set a QP, expressed as 4.096 * 2^(timeout) usec. * * This function should be called before rdma_connect() on active side, * and on passive side before rdma_accept(). It is applicable to primary * path only. The timeout will affect the local side of the QP, it is not * negotiated with remote side and zero disables the timer. In case it is * set before rdma_resolve_route, the value will also be used to determine * PacketLifeTime for RoCE. * * Return: 0 for success */ int rdma_set_ack_timeout(struct rdma_cm_id *id, u8 timeout) { struct rdma_id_private *id_priv; if (id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_INI) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->timeout = timeout; id_priv->timeout_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_ack_timeout); /** * rdma_set_min_rnr_timer() - Set the minimum RNR Retry timer of the * QP associated with a connection identifier. * @id: Communication identifier to associated with service type. * @min_rnr_timer: 5-bit value encoded as Table 45: "Encoding for RNR NAK * Timer Field" in the IBTA specification. * * This function should be called before rdma_connect() on active * side, and on passive side before rdma_accept(). The timer value * will be associated with the local QP. When it receives a send it is * not read to handle, typically if the receive queue is empty, an RNR * Retry NAK is returned to the requester with the min_rnr_timer * encoded. The requester will then wait at least the time specified * in the NAK before retrying. The default is zero, which translates * to a minimum RNR Timer value of 655 ms. * * Return: 0 for success */ int rdma_set_min_rnr_timer(struct rdma_cm_id *id, u8 min_rnr_timer) { struct rdma_id_private *id_priv; /* It is a five-bit value */ if (min_rnr_timer & 0xe0) return -EINVAL; if (WARN_ON(id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_TGT)) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->min_rnr_timer = min_rnr_timer; id_priv->min_rnr_timer_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_min_rnr_timer); static int route_set_path_rec_inbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_inbound) { route->path_rec_inbound = kzalloc(sizeof(*route->path_rec_inbound), GFP_KERNEL); if (!route->path_rec_inbound) return -ENOMEM; } *route->path_rec_inbound = *path_rec; return 0; } static int route_set_path_rec_outbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_outbound) { route->path_rec_outbound = kzalloc(sizeof(*route->path_rec_outbound), GFP_KERNEL); if (!route->path_rec_outbound) return -ENOMEM; } *route->path_rec_outbound = *path_rec; return 0; } static void cma_query_handler(int status, struct sa_path_rec *path_rec, unsigned int num_prs, void *context) { struct cma_work *work = context; struct rdma_route *route; int i; route = &work->id->id.route; if (status) goto fail; for (i = 0; i < num_prs; i++) { if (!path_rec[i].flags || (path_rec[i].flags & IB_PATH_GMP)) *route->path_rec = path_rec[i]; else if (path_rec[i].flags & IB_PATH_INBOUND) status = route_set_path_rec_inbound(work, &path_rec[i]); else if (path_rec[i].flags & IB_PATH_OUTBOUND) status = route_set_path_rec_outbound(work, &path_rec[i]); else status = -EINVAL; if (status) goto fail; } route->num_pri_alt_paths = 1; queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_ERROR; work->event.status = status; pr_debug_ratelimited("RDMA CM: ROUTE_ERROR: failed to query path. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_query_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms, struct cma_work *work) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sa_path_rec path_rec; ib_sa_comp_mask comp_mask; struct sockaddr_in6 *sin6; struct sockaddr_ib *sib; memset(&path_rec, 0, sizeof path_rec); if (rdma_cap_opa_ah(id_priv->id.device, id_priv->id.port_num)) path_rec.rec_type = SA_PATH_REC_TYPE_OPA; else path_rec.rec_type = SA_PATH_REC_TYPE_IB; rdma_addr_get_sgid(dev_addr, &path_rec.sgid); rdma_addr_get_dgid(dev_addr, &path_rec.dgid); path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); path_rec.numb_path = 1; path_rec.reversible = 1; path_rec.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID; switch (cma_family(id_priv)) { case AF_INET: path_rec.qos_class = cpu_to_be16((u16) id_priv->tos); comp_mask |= IB_SA_PATH_REC_QOS_CLASS; break; case AF_INET6: sin6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; case AF_IB: sib = (struct sockaddr_ib *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sib->sib_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; } id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &path_rec, comp_mask, timeout_ms, GFP_KERNEL, cma_query_handler, work, &id_priv->query); return (id_priv->query_id < 0) ? id_priv->query_id : 0; } static void cma_iboe_join_work_handler(struct work_struct *work) { struct cma_multicast *mc = container_of(work, struct cma_multicast, iboe_join.work); struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_id_private *id_priv = mc->id_priv; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; ret = cma_cm_event_handler(id_priv, event); WARN_ON(ret); out_unlock: mutex_unlock(&id_priv->handler_mutex); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } static void cma_work_handler(struct work_struct *_work) { struct cma_work *work = container_of(_work, struct cma_work, work); struct rdma_id_private *id_priv = work->id; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; if (work->old_state != 0 || work->new_state != 0) { if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) goto out_unlock; } if (cma_cm_event_handler(id_priv, &work->event)) { cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); goto out_free; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); out_free: if (work->event.event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&work->event.param.ud.ah_attr); kfree(work); } static void cma_init_resolve_route_work(struct cma_work *work, struct rdma_id_private *id_priv) { work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; } static void enqueue_resolve_addr_work(struct cma_work *work, struct rdma_id_private *id_priv) { /* Balances with cma_id_put() in cma_work_handler */ cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDR_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; queue_work(cma_wq, &work->work); } static int cma_resolve_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms) { struct rdma_route *route = &id_priv->id.route; struct cma_work *work; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); if (!route->path_rec) route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; goto err1; } ret = cma_query_ib_route(id_priv, timeout_ms, work); if (ret) goto err2; return 0; err2: kfree(route->path_rec); route->path_rec = NULL; err1: kfree(work); return ret; } static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, unsigned long supported_gids, enum ib_gid_type default_gid) { if ((network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) && test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) return IB_GID_TYPE_ROCE_UDP_ENCAP; return default_gid; } /* * cma_iboe_set_path_rec_l2_fields() is helper function which sets * path record type based on GID type. * It also sets up other L2 fields which includes destination mac address * netdev ifindex, of the path record. * It returns the netdev of the bound interface for this path record entry. */ static struct net_device * cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; enum ib_gid_type gid_type = IB_GID_TYPE_ROCE; struct rdma_addr *addr = &route->addr; unsigned long supported_gids; struct net_device *ndev; if (!addr->dev_addr.bound_dev_if) return NULL; ndev = dev_get_by_index(addr->dev_addr.net, addr->dev_addr.bound_dev_if); if (!ndev) return NULL; supported_gids = roce_gid_type_mask_support(id_priv->id.device, id_priv->id.port_num); gid_type = cma_route_gid_type(addr->dev_addr.network, supported_gids, id_priv->gid_type); /* Use the hint from IP Stack to select GID Type */ if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) gid_type = ib_network_to_gid_type(addr->dev_addr.network); route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); route->path_rec->roce.route_resolved = true; sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); return ndev; } int rdma_set_ib_path(struct rdma_cm_id *id, struct sa_path_rec *path_rec) { struct rdma_id_private *id_priv; struct net_device *ndev; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec), GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } if (rdma_protocol_roce(id->device, id->port_num)) { ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err_free; } dev_put(ndev); } id->route.num_pri_alt_paths = 1; return 0; err_free: kfree(id->route.path_rec); id->route.path_rec = NULL; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_set_ib_path); static int cma_resolve_iw_route(struct rdma_id_private *id_priv) { struct cma_work *work; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; } static int get_vlan_ndev_tc(struct net_device *vlan_ndev, int prio) { struct net_device *dev; dev = vlan_dev_real_dev(vlan_ndev); if (dev->num_tc) return netdev_get_prio_tc_map(dev, prio); return (vlan_dev_get_egress_qos_mask(vlan_ndev, prio) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } struct iboe_prio_tc_map { int input_prio; int output_tc; bool found; }; static int get_lower_vlan_dev_tc(struct net_device *dev, struct netdev_nested_priv *priv) { struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); else if (dev->num_tc) map->output_tc = netdev_get_prio_tc_map(dev, map->input_prio); else map->output_tc = 0; /* We are interested only in first level VLAN device, so always * return 1 to stop iterating over next level devices. */ map->found = true; return 1; } static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. */ if (prio_tc_map.found) return prio_tc_map.output_tc; else if (ndev->num_tc) return netdev_get_prio_tc_map(ndev, prio); else return 0; } static __be32 cma_get_roce_udp_flow_label(struct rdma_id_private *id_priv) { struct sockaddr_in6 *addr6; u16 dport, sport; u32 hash, fl; addr6 = (struct sockaddr_in6 *)cma_src_addr(id_priv); fl = be32_to_cpu(addr6->sin6_flowinfo) & IB_GRH_FLOWLABEL_MASK; if ((cma_family(id_priv) != AF_INET6) || !fl) { dport = be16_to_cpu(cma_port(cma_dst_addr(id_priv))); sport = be16_to_cpu(cma_port(cma_src_addr(id_priv))); hash = (u32)sport * 31 + dport; fl = hash & IB_GRH_FLOWLABEL_MASK; } return cpu_to_be32(fl); } static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; struct rdma_addr *addr = &route->addr; struct cma_work *work; int ret; struct net_device *ndev; u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; u8 tos; mutex_lock(&id_priv->qp_mutex); tos = id_priv->tos_set ? id_priv->tos : default_roce_tos; mutex_unlock(&id_priv->qp_mutex); work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; goto err1; } route->num_pri_alt_paths = 1; ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err2; } rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &route->path_rec->sgid); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, &route->path_rec->dgid); if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB) /* TODO: get the hoplimit from the inet/inet6 device */ route->path_rec->hop_limit = addr->dev_addr.hoplimit; else route->path_rec->hop_limit = 1; route->path_rec->reversible = 1; route->path_rec->pkey = cpu_to_be16(0xffff); route->path_rec->mtu_selector = IB_SA_EQ; route->path_rec->sl = iboe_tos_to_sl(ndev, tos); route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate * PacketLifeTime. As per IBTA 12.7.34, * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). * Assuming a negligible local ACK delay, we can use * PacketLifeTime = local ACK timeout/2 * as a reasonable approximation for RoCE networks. */ mutex_lock(&id_priv->qp_mutex); if (id_priv->timeout_set && id_priv->timeout) route->path_rec->packet_life_time = id_priv->timeout - 1; else route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; mutex_unlock(&id_priv->qp_mutex); if (!route->path_rec->mtu) { ret = -EINVAL; goto err2; } if (rdma_protocol_roce_udp_encap(id_priv->id.device, id_priv->id.port_num)) route->path_rec->flow_label = cma_get_roce_udp_flow_label(id_priv); cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err2: kfree(route->path_rec); route->path_rec = NULL; route->num_pri_alt_paths = 0; err1: kfree(work); return ret; } int rdma_resolve_route(struct rdma_cm_id *id, unsigned long timeout_ms) { struct rdma_id_private *id_priv; int ret; if (!timeout_ms) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY)) return -EINVAL; cma_id_get(id_priv); if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_route(id_priv, timeout_ms); else if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_resolve_iboe_route(id_priv); if (!ret) cma_add_id_to_tree(id_priv); } else if (rdma_protocol_iwarp(id->device, id->port_num)) ret = cma_resolve_iw_route(id_priv); else ret = -ENOSYS; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_QUERY, RDMA_CM_ADDR_RESOLVED); cma_id_put(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_route); static void cma_set_loopback(struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); break; case AF_INET6: ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr, 0, 0, 0, htonl(1)); break; default: ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr, 0, 0, 0, htonl(1)); break; } } static int cma_bind_loopback(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; union ib_gid gid; enum ib_port_state port_state; unsigned int p; u16 pkey; int ret; cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cur_dev->device, 1)) continue; if (!cma_dev) cma_dev = cur_dev; rdma_for_each_port (cur_dev->device, p) { if (!ib_get_cached_port_state(cur_dev->device, p, &port_state) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; goto port_found; } } } if (!cma_dev) { ret = -ENODEV; goto out; } p = 1; port_found: ret = rdma_query_gid(cma_dev->device, p, 0, &gid); if (ret) goto out; ret = ib_get_cached_pkey(cma_dev->device, p, 0, &pkey); if (ret) goto out; id_priv->id.route.addr.dev_addr.dev_type = (rdma_protocol_ib(cma_dev->device, p)) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey); id_priv->id.port_num = p; cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); cma_set_loopback(cma_src_addr(id_priv)); out: mutex_unlock(&lock); return ret; } static void addr_handler(int status, struct sockaddr *src_addr, struct rdma_dev_addr *dev_addr, void *context) { struct rdma_id_private *id_priv = context; struct rdma_cm_event event = {}; struct sockaddr *addr; struct sockaddr_storage old_addr; mutex_lock(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_RESOLVED)) goto out; /* * Store the previous src address, so that if we fail to acquire * matching rdma device, old address can be restored back, which helps * to cancel the cma listen operation correctly. */ addr = cma_src_addr(id_priv); memcpy(&old_addr, addr, rdma_addr_size(addr)); memcpy(addr, src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) { status = cma_acquire_dev_by_src_ip(id_priv); if (status) pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n", status); rdma_restrack_add(&id_priv->res); } else if (status) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status); } if (status) { memcpy(addr, &old_addr, rdma_addr_size((struct sockaddr *)&old_addr)); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ADDR_BOUND)) goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; if (cma_cm_event_handler(id_priv, &event)) { destroy_id_handler_unlock(id_priv); return; } out: mutex_unlock(&id_priv->handler_mutex); } static int cma_resolve_loopback(struct rdma_id_private *id_priv) { struct cma_work *work; union ib_gid gid; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_bind_loopback(id_priv); if (ret) goto err; } rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) { struct cma_work *work; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_resolve_ib_dev(id_priv); if (ret) goto err; } rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if ((reuse && id_priv->state != RDMA_CM_LISTEN) || id_priv->state == RDMA_CM_IDLE) { id_priv->reuseaddr = reuse; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_reuseaddr); int rdma_set_afonly(struct rdma_cm_id *id, int afonly) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if (id_priv->state == RDMA_CM_IDLE || id_priv->state == RDMA_CM_ADDR_BOUND) { id_priv->options |= (1 << CMA_OPTION_AFONLY); id_priv->afonly = afonly; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_afonly); static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct sockaddr *addr; struct sockaddr_ib *sib; u64 sid, mask; __be16 port; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); port = htons(bind_list->port); switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_port = port; break; case AF_INET6: ((struct sockaddr_in6 *) addr)->sin6_port = port; break; case AF_IB: sib = (struct sockaddr_ib *) addr; sid = be64_to_cpu(sib->sib_sid); mask = be64_to_cpu(sib->sib_sid_mask); sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port)); sib->sib_sid_mask = cpu_to_be64(~0ULL); break; } id_priv->bind_list = bind_list; hlist_add_head(&id_priv->node, &bind_list->owners); } static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; int ret; lockdep_assert_held(&lock); bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; ret = cma_ps_alloc(id_priv->id.route.addr.dev_addr.net, ps, bind_list, snum); if (ret < 0) goto err; bind_list->ps = ps; bind_list->port = snum; cma_bind_port(bind_list, id_priv); return 0; err: kfree(bind_list); return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct rdma_id_private *cur_id; struct sockaddr *daddr = cma_dst_addr(id_priv); struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); lockdep_assert_held(&lock); hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); __be16 cur_dport = cma_port(cur_daddr); if (id_priv == cur_id) continue; /* different dest port -> unique */ if (!cma_any_port(daddr) && !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; /* different src address -> unique */ if (!cma_any_addr(saddr) && !cma_any_addr(cur_saddr) && cma_addr_cmp(saddr, cur_saddr)) continue; /* different dst address -> unique */ if (!cma_any_addr(daddr) && !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; return -EADDRNOTAVAIL; } return 0; } static int cma_alloc_any_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { static unsigned int last_used_port; int low, high, remaining; unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; lockdep_assert_held(&lock); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_inclusive(low, remaining + low - 1); retry: if (last_used_port != rover) { struct rdma_bind_list *bind_list; int ret; bind_list = cma_ps_find(net, ps, (unsigned short)rover); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, rover); } else { ret = cma_port_is_unique(bind_list, id_priv); if (!ret) cma_bind_port(bind_list, id_priv); } /* * Remember previously used port number in order to avoid * re-using same port immediately after it is closed. */ if (!ret) last_used_port = rover; if (ret != -EADDRNOTAVAIL) return ret; } if (--remaining) { rover++; if ((rover < low) || (rover > high)) rover = low; goto retry; } return -EADDRNOTAVAIL; } /* * Check that the requested port is available. This is called when trying to * bind to a specific port, or when trying to listen on a bound port. In * the latter case, the provided id_priv may already be on the bind_list, but * we still need to check that it's okay to start listening. */ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv, uint8_t reuseaddr) { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) continue; if (reuseaddr && cur_id->reuseaddr) continue; cur_addr = cma_src_addr(cur_id); if (id_priv->afonly && cur_id->afonly && (addr->sa_family != cur_addr->sa_family)) continue; if (cma_any_addr(addr) || cma_any_addr(cur_addr)) return -EADDRNOTAVAIL; if (!cma_addr_cmp(addr, cur_addr)) return -EADDRINUSE; } return 0; } static int cma_use_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list; unsigned short snum; int ret; lockdep_assert_held(&lock); snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; bind_list = cma_ps_find(id_priv->id.route.addr.dev_addr.net, ps, snum); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, snum); } else { ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); if (!ret) cma_bind_port(bind_list, id_priv); } return ret; } static enum rdma_ucm_port_space cma_select_inet_ps(struct rdma_id_private *id_priv) { switch (id_priv->id.ps) { case RDMA_PS_TCP: case RDMA_PS_UDP: case RDMA_PS_IPOIB: case RDMA_PS_IB: return id_priv->id.ps; default: return 0; } } static enum rdma_ucm_port_space cma_select_ib_ps(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps = 0; struct sockaddr_ib *sib; u64 sid_ps, mask, sid; sib = (struct sockaddr_ib *) cma_src_addr(id_priv); mask = be64_to_cpu(sib->sib_sid_mask) & RDMA_IB_IP_PS_MASK; sid = be64_to_cpu(sib->sib_sid) & mask; if ((id_priv->id.ps == RDMA_PS_IB) && (sid == (RDMA_IB_IP_PS_IB & mask))) { sid_ps = RDMA_IB_IP_PS_IB; ps = RDMA_PS_IB; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_TCP)) && (sid == (RDMA_IB_IP_PS_TCP & mask))) { sid_ps = RDMA_IB_IP_PS_TCP; ps = RDMA_PS_TCP; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_UDP)) && (sid == (RDMA_IB_IP_PS_UDP & mask))) { sid_ps = RDMA_IB_IP_PS_UDP; ps = RDMA_PS_UDP; } if (ps) { sib->sib_sid = cpu_to_be64(sid_ps | ntohs(cma_port((struct sockaddr *) sib))); sib->sib_sid_mask = cpu_to_be64(RDMA_IB_IP_PS_MASK | be64_to_cpu(sib->sib_sid_mask)); } return ps; } static int cma_get_port(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps; int ret; if (cma_family(id_priv) != AF_IB) ps = cma_select_inet_ps(id_priv); else ps = cma_select_ib_ps(id_priv); if (!ps) return -EPROTONOSUPPORT; mutex_lock(&lock); if (cma_any_port(cma_src_addr(id_priv))) ret = cma_alloc_any_port(ps, id_priv); else ret = cma_use_port(ps, id_priv); mutex_unlock(&lock); return ret; } static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, struct sockaddr *addr) { #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 *sin6; if (addr->sa_family != AF_INET6) return 0; sin6 = (struct sockaddr_in6 *) addr; if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) return 0; if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; #endif return 0; } int rdma_listen(struct rdma_cm_id *id, int backlog) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { struct sockaddr_in any_in = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN))) return -EINVAL; } /* * Once the ID reaches RDMA_CM_LISTEN it is not allowed to be reusable * any more, and has to be unique in the bind list. */ if (id_priv->reuseaddr) { mutex_lock(&lock); ret = cma_check_port(id_priv->bind_list, id_priv, 0); if (!ret) id_priv->reuseaddr = 0; mutex_unlock(&lock); if (ret) goto err; } id_priv->backlog = backlog; if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id->device, 1)) { ret = cma_ib_listen(id_priv); if (ret) goto err; } else if (rdma_cap_iw_cm(id->device, 1)) { ret = cma_iw_listen(id_priv, backlog); if (ret) goto err; } else { ret = -ENOSYS; goto err; } } else { ret = cma_listen_on_all(id_priv); if (ret) goto err; } return 0; err: id_priv->backlog = 0; /* * All the failure paths that lead here will not allow the req_handler's * to have run. */ cma_comp_exch(id_priv, RDMA_CM_LISTEN, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_listen); static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, struct sockaddr *addr, const struct sockaddr *daddr) { struct sockaddr *id_daddr; int ret; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT; if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1; memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1; ret = cma_acquire_dev_by_src_ip(id_priv); if (ret) goto err1; } if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { if (addr->sa_family == AF_INET) id_priv->afonly = 1; #if IS_ENABLED(CONFIG_IPV6) else if (addr->sa_family == AF_INET6) { struct net *net = id_priv->id.route.addr.dev_addr.net; id_priv->afonly = net->ipv6.sysctl.bindv6only; } #endif } id_daddr = cma_dst_addr(id_priv); if (daddr != id_daddr) memcpy(id_daddr, daddr, rdma_addr_size(addr)); id_daddr->sa_family = addr->sa_family; ret = cma_get_port(id_priv); if (ret) goto err2; if (!cma_any_addr(addr)) rdma_restrack_add(&id_priv->res); return 0; err2: if (id_priv->cma_dev) cma_release_dev(id_priv); err1: cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct sockaddr_storage zero_sock = {}; if (src_addr && src_addr->sa_family) return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); /* * When the src_addr is not specified, automatically supply an any addr */ zero_sock.ss_family = dst_addr->sa_family; if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)&zero_sock; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; } else if (dst_addr->sa_family == AF_IB) { ((struct sockaddr_ib *)&zero_sock)->sib_pkey = ((struct sockaddr_ib *)dst_addr)->sib_pkey; } return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); } /* * If required, resolve the source address for bind and leave the id_priv in * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior * calls made by ULP, a previously bound ID will not be re-bound and src_addr is * ignored. */ static int resolve_prepare_src(struct rdma_id_private *id_priv, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))) return -EINVAL; } else { memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); } if (cma_family(id_priv) != dst_addr->sa_family) { ret = -EINVAL; goto err_state; } return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr, unsigned long timeout_ms) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; ret = resolve_prepare_src(id_priv, src_addr, dst_addr); if (ret) return ret; if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); } else { if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { /* * The FSM can return back to RDMA_CM_ADDR_BOUND after * rdma_resolve_ip() is called, eg through the error * path in addr_handler(). If this happens the existing * request must be canceled before issuing a new one. * Since canceling a request is a bit slow and this * oddball path is rare, keep track once a request has * been issued. The track turns out to be a permanent * state since this is the only cancel as it is * immediately before rdma_resolve_ip(). */ if (id_priv->used_resolve_ip) rdma_addr_cancel(&id->route.addr.dev_addr); else id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, false, id_priv); } } if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_addr); int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); } EXPORT_SYMBOL(rdma_bind_addr); static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) { struct cma_hdr *cma_hdr; cma_hdr = hdr; cma_hdr->cma_version = CMA_VERSION; if (cma_family(id_priv) == AF_INET) { struct sockaddr_in *src4, *dst4; src4 = (struct sockaddr_in *) cma_src_addr(id_priv); dst4 = (struct sockaddr_in *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 4); cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; cma_hdr->port = src4->sin_port; } else if (cma_family(id_priv) == AF_INET6) { struct sockaddr_in6 *src6, *dst6; src6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); dst6 = (struct sockaddr_in6 *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 6); cma_hdr->src_addr.ip6 = src6->sin6_addr; cma_hdr->dst_addr.ip6 = dst6->sin6_addr; cma_hdr->port = src6->sin6_port; } return 0; } static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; const struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (ib_event->event) { case IB_CM_SIDR_REQ_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_SIDR_REP_RECEIVED: event.param.ud.private_data = ib_event->private_data; event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE; if (rep->status != IB_SIDR_SUCCESS) { event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = ib_event->param.sidr_rep_rcvd.status; pr_debug_ratelimited("RDMA CM: UNREACHABLE: bad SIDR reply. status %d\n", event.status); break; } ret = cma_set_qkey(id_priv, rep->qkey); if (ret) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to set qkey. status %d\n", ret); event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = ret; break; } ib_init_ah_attr_from_path(id_priv->id.device, id_priv->id.port_num, id_priv->id.route.path_rec, &event.param.ud.ah_attr, rep->sgid_attr); event.param.ud.qp_num = rep->qpn; event.param.ud.qkey = rep->qkey; event.event = RDMA_CM_EVENT_ESTABLISHED; event.status = 0; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); rdma_destroy_ah_attr(&event.param.ud.ah_attr); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; req.path = id_priv->id.route.path_rec; req.sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); req.max_cm_retries = CMA_MAX_CM_RETRIES; trace_cm_send_sidr_req(id_priv); ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req); if (ret) { ib_destroy_cm_id(id_priv->cm_id.ib); id_priv->cm_id.ib = NULL; } out: kfree(private_data); return ret; } static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_req_param req; struct rdma_route *route; void *private_data; struct ib_cm_id *id; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; route = &id_priv->id.route; if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } req.primary_path = &route->path_rec[0]; req.primary_path_inbound = route->path_rec_inbound; req.primary_path_outbound = route->path_rec_outbound; if (route->num_pri_alt_paths == 2) req.alternate_path = &route->path_rec[1]; req.ppath_sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; /* Alternate path SGID attribute currently unsupported */ req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.qp_num = id_priv->qp_num; req.qp_type = id_priv->id.qp_type; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; req.flow_control = conn_param->flow_control; req.retry_count = min_t(u8, 7, conn_param->retry_count); req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.max_cm_retries = CMA_MAX_CM_RETRIES; req.srq = id_priv->srq ? 1 : 0; req.ece.vendor_id = id_priv->ece.vendor_id; req.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_req(id_priv); ret = ib_send_cm_req(id_priv->cm_id.ib, &req); out: if (ret && !IS_ERR(id)) { ib_destroy_cm_id(id); id_priv->cm_id.ib = NULL; } kfree(private_data); return ret; } static int cma_connect_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_id *cm_id; int ret; struct iw_cm_conn_param iw_param; cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); mutex_lock(&id_priv->qp_mutex); cm_id->tos = id_priv->tos; cm_id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id_priv->cm_id.iw = cm_id; memcpy(&cm_id->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); memcpy(&cm_id->remote_addr, cma_dst_addr(id_priv), rdma_addr_size(cma_dst_addr(id_priv))); ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; if (conn_param) { iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; iw_param.qpn = id_priv->id.qp ? id_priv->qp_num : conn_param->qp_num; } else { memset(&iw_param, 0, sizeof iw_param); iw_param.qpn = id_priv->qp_num; } ret = iw_cm_connect(cm_id, &iw_param); out: if (ret) { iw_destroy_cm_id(cm_id); id_priv->cm_id.iw = NULL; } return ret; } /** * rdma_connect_locked - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Same as rdma_connect() but can only be called from the * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback. */ int rdma_connect_locked(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_connect_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto err_state; return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_connect_locked); /** * rdma_connect - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Users must have resolved a route for the rdma_cm_id to connect with by having * called rdma_resolve_route before calling this routine. * * This call will either connect to a remote QP or obtain remote QP information * for unconnected rdma_cm_id's. The actual operation is based on the * rdma_cm_id's port space. */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; mutex_lock(&id_priv->handler_mutex); ret = rdma_connect_locked(id, conn_param); mutex_unlock(&id_priv->handler_mutex); return ret; } EXPORT_SYMBOL(rdma_connect); /** * rdma_connect_ece - Initiate an active connection request with ECE data. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * @ece: ECE parameters * * See rdma_connect() explanation. */ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_connect(id, conn_param); } EXPORT_SYMBOL(rdma_connect_ece); static int cma_accept_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_rep_param rep; int ret; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; ret = cma_modify_qp_rts(id_priv, conn_param); if (ret) goto out; memset(&rep, 0, sizeof rep); rep.qp_num = id_priv->qp_num; rep.starting_psn = id_priv->seq_num; rep.private_data = conn_param->private_data; rep.private_data_len = conn_param->private_data_len; rep.responder_resources = conn_param->responder_resources; rep.initiator_depth = conn_param->initiator_depth; rep.failover_accepted = 0; rep.flow_control = conn_param->flow_control; rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); rep.srq = id_priv->srq ? 1 : 0; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_rep(id_priv); ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); out: return ret; } static int cma_accept_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_conn_param iw_param; int ret; if (!conn_param) return -EINVAL; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) return ret; iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; if (id_priv->id.qp) iw_param.qpn = id_priv->qp_num; else iw_param.qpn = conn_param->qp_num; return iw_cm_accept(id_priv->cm_id.iw, &iw_param); } static int cma_send_sidr_rep(struct rdma_id_private *id_priv, enum ib_cm_sidr_status status, u32 qkey, const void *private_data, int private_data_len) { struct ib_cm_sidr_rep_param rep; int ret; memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { if (qkey) ret = cma_set_qkey(id_priv, qkey); else ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; rep.qkey = id_priv->qkey; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; } rep.private_data = private_data; rep.private_data_len = private_data_len; trace_cm_send_sidr_rep(id_priv); return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep); } /** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request. * @conn_param: Information needed to establish the connection. This must be * provided if accepting a connection request. If accepting a connection * response, this parameter must be NULL. * * Typically, this routine is only called by the listener to accept a connection * request. It must also be called on the active side of a connection if the * user is performing their own QP transitions. * * In the case of error, a reject message is sent to the remote side and the * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. * * This function is for use by kernel ULPs and must be called from under the * handler callback. */ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) return -EINVAL; if (!id->qp && conn_param) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { if (conn_param) ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, conn_param->qkey, conn_param->private_data, conn_param->private_data_len); else ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, 0, NULL, 0); } else { if (conn_param) ret = cma_accept_ib(id_priv, conn_param); else ret = cma_rep_recv(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_accept_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto reject; return 0; reject: cma_modify_qp_err(id_priv); rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED); return ret; } EXPORT_SYMBOL(rdma_accept); int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_accept(id, conn_param); } EXPORT_SYMBOL(rdma_accept_ece); void rdma_lock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_lock_handler); void rdma_unlock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_unlock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_unlock_handler); int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; switch (id->device->node_type) { case RDMA_NODE_IB_CA: ret = ib_cm_notify(id_priv->cm_id.ib, event); break; default: ret = 0; break; } return ret; } EXPORT_SYMBOL(rdma_notify); int rdma_reject(struct rdma_cm_id *id, const void *private_data, u8 private_data_len, u8 reason) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); } else { trace_cm_send_rej(id_priv); ret = ib_send_cm_rej(id_priv->cm_id.ib, reason, NULL, 0, private_data, private_data_len); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw, private_data, private_data_len); } else { ret = -ENOSYS; } return ret; } EXPORT_SYMBOL(rdma_reject); int rdma_disconnect(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { ret = cma_modify_qp_err(id_priv); if (ret) goto out; /* Initiate or respond to a disconnect. */ trace_cm_disconnect(id_priv); if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) { if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0)) trace_cm_sent_drep(id_priv); } else { trace_cm_sent_dreq(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_disconnect(id_priv->cm_id.iw, 0); } else ret = -EINVAL; out: return ret; } EXPORT_SYMBOL(rdma_disconnect); static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, struct ib_sa_multicast *multicast, struct rdma_cm_event *event, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr; enum ib_gid_type gid_type; struct net_device *ndev; if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); event->status = status; event->param.ud.private_data = mc->context; if (status) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; return; } dev_addr = &id_priv->id.route.addr.dev_addr; ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); gid_type = id_priv->cma_dev ->default_gid_type[id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; event->event = RDMA_CM_EVENT_MULTICAST_JOIN; if (ib_init_ah_from_mcmember(id_priv->id.device, id_priv->id.port_num, &multicast->rec, ndev, gid_type, &event->param.ud.ah_attr)) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; goto out; } event->param.ud.qp_num = 0xFFFFFF; event->param.ud.qkey = id_priv->qkey; out: dev_put(ndev); } static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) { struct cma_multicast *mc = multicast->context; struct rdma_id_private *id_priv = mc->id_priv; struct rdma_cm_event event = {}; int ret = 0; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL || READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); if (!ret) { cma_make_mc_event(status, id_priv, multicast, &event, mc); ret = cma_cm_event_handler(id_priv, &event); } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); out: mutex_unlock(&id_priv->handler_mutex); return 0; } static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, union ib_gid *mgid) { unsigned char mc_map[MAX_ADDR_LEN]; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sockaddr_in *sin = (struct sockaddr_in *) addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if ((addr->sa_family == AF_INET6) && ((be32_to_cpu(sin6->sin6_addr.s6_addr32[0]) & 0xFFF0FFFF) == 0xFF10A01B)) { /* IPv6 address is an SA assigned MGID. */ memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else if (addr->sa_family == AF_IB) { memcpy(mgid, &((struct sockaddr_ib *) addr)->sib_addr, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { ipv6_ib_mc_map(&sin6->sin6_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } else { ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } } static int cma_join_ib_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct ib_sa_mcmember_rec rec; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; ib_sa_comp_mask comp_mask; int ret; ib_addr_get_mgid(dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (ret) return ret; if (!id_priv->qkey) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); rdma_addr_get_sgid(dev_addr, &rec.port_gid); rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = mc->join_state; comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE | IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL | IB_SA_MCMEMBER_REC_FLOW_LABEL | IB_SA_MCMEMBER_REC_TRAFFIC_CLASS; if (id_priv->id.ps == RDMA_PS_IPOIB) comp_mask |= IB_SA_MCMEMBER_REC_RATE | IB_SA_MCMEMBER_REC_RATE_SELECTOR | IB_SA_MCMEMBER_REC_MTU_SELECTOR | IB_SA_MCMEMBER_REC_MTU | IB_SA_MCMEMBER_REC_HOP_LIMIT; mc->sa_mc = ib_sa_join_multicast(&sa_client, id_priv->id.device, id_priv->id.port_num, &rec, comp_mask, GFP_KERNEL, cma_ib_mc_handler, mc); return PTR_ERR_OR_ZERO(mc->sa_mc); } static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type) { struct sockaddr_in *sin = (struct sockaddr_in *)addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else { mgid->raw[0] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0xff; mgid->raw[1] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0x0e; mgid->raw[2] = 0; mgid->raw[3] = 0; mgid->raw[4] = 0; mgid->raw[5] = 0; mgid->raw[6] = 0; mgid->raw[7] = 0; mgid->raw[8] = 0; mgid->raw[9] = 0; mgid->raw[10] = 0xff; mgid->raw[11] = 0xff; *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; } } static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (cma_zero_addr(addr)) return -EINVAL; gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) return -ENODEV; ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } } else { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) err = -ENOTSUPP; } dev_put(ndev); if (err || !ib.rec.mtu) return err ?: -EINVAL; if (!id_priv->qkey) cma_set_default_qkey(id_priv); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); cma_make_mc_event(0, id_priv, &ib, &mc->iboe_join.event, mc); queue_work(cma_wq, &mc->iboe_join.work); return 0; } int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, u8 join_state, void *context) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct cma_multicast *mc; int ret; /* Not supported for kernel QPs */ if (WARN_ON(id->qp)) return -EINVAL; /* ULP is calling this wrong. */ if (!id->device || (READ_ONCE(id_priv->state) != RDMA_CM_ADDR_BOUND && READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; if (id_priv->id.qp_type != IB_QPT_UD) return -EINVAL; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; memcpy(&mc->addr, addr, rdma_addr_size(addr)); mc->context = context; mc->id_priv = id_priv; mc->join_state = join_state; if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_iboe_join_multicast(id_priv, mc); if (ret) goto out_err; } else if (rdma_cap_ib_mcast(id->device, id->port_num)) { ret = cma_join_ib_multicast(id_priv, mc); if (ret) goto out_err; } else { ret = -ENOSYS; goto out_err; } spin_lock(&id_priv->lock); list_add(&mc->list, &id_priv->mc_list); spin_unlock(&id_priv->lock); return 0; out_err: kfree(mc); return ret; } EXPORT_SYMBOL(rdma_join_multicast); void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; struct cma_multicast *mc; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) continue; list_del(&mc->list); spin_unlock_irq(&id_priv->lock); WARN_ON(id_priv->cma_dev->device != id->device); destroy_mc(id_priv, mc); return; } spin_unlock_irq(&id_priv->lock); } EXPORT_SYMBOL(rdma_leave_multicast); static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr; struct cma_work *work; dev_addr = &id_priv->id.route.addr.dev_addr; if ((dev_addr->bound_dev_if == ndev->ifindex) && (net_eq(dev_net(ndev), dev_addr->net)) && memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) { pr_info("RDMA CM addr change for ndev %s used by id %p\n", ndev->name, &id_priv->id); work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; INIT_WORK(&work->work, cma_work_handler); work->id = id_priv; work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; cma_id_get(id_priv); queue_work(cma_wq, &work->work); } return 0; } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; if (event != NETDEV_BONDING_FAILOVER) return NOTIFY_DONE; if (!netif_is_bond_master(ndev)) return NOTIFY_DONE; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) list_for_each_entry(id_priv, &cma_dev->id_list, device_item) { ret = cma_netdev_change(ndev, id_priv); if (ret) goto out; } out: mutex_unlock(&lock); return ret; } static void cma_netevent_work_handler(struct work_struct *_work) { struct rdma_id_private *id_priv = container_of(_work, struct rdma_id_private, id.net_work); struct rdma_cm_event event = {}; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; if (cma_cm_event_handler(id_priv, &event)) { __acquire(&id_priv->handler_mutex); id_priv->cm_id.ib = NULL; cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); return; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); } static int cma_netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { struct id_table_entry *ips_node = NULL; struct rdma_id_private *current_id; struct neighbour *neigh = ctx; unsigned long flags; if (event != NETEVENT_NEIGH_UPDATE) return NOTIFY_DONE; spin_lock_irqsave(&id_table_lock, flags); if (neigh->tbl->family == AF_INET6) { struct sockaddr_in6 neigh_sock_6; neigh_sock_6.sin6_family = AF_INET6; neigh_sock_6.sin6_addr = *(struct in6_addr *)neigh->primary_key; ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_6); } else if (neigh->tbl->family == AF_INET) { struct sockaddr_in neigh_sock_4; neigh_sock_4.sin_family = AF_INET; neigh_sock_4.sin_addr.s_addr = *(__be32 *)(neigh->primary_key); ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_4); } else goto out; if (!ips_node) goto out; list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) { if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr, neigh->ha, ETH_ALEN)) continue; INIT_WORK(¤t_id->id.net_work, cma_netevent_work_handler); cma_id_get(current_id); queue_work(cma_wq, ¤t_id->id.net_work); } out: spin_unlock_irqrestore(&id_table_lock, flags); return NOTIFY_DONE; } static struct notifier_block cma_nb = { .notifier_call = cma_netdev_callback }; static struct notifier_block cma_netevent_cb = { .notifier_call = cma_netevent_callback }; static void cma_send_device_removal_put(struct rdma_id_private *id_priv) { struct rdma_cm_event event = { .event = RDMA_CM_EVENT_DEVICE_REMOVAL }; enum rdma_cm_state state; unsigned long flags; mutex_lock(&id_priv->handler_mutex); /* Record that we want to remove the device */ spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; if (state == RDMA_CM_DESTROYING || state == RDMA_CM_DEVICE_REMOVAL) { spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); return; } id_priv->state = RDMA_CM_DEVICE_REMOVAL; spin_unlock_irqrestore(&id_priv->lock, flags); if (cma_cm_event_handler(id_priv, &event)) { /* * At this point the ULP promises it won't call * rdma_destroy_id() concurrently */ cma_id_put(id_priv); mutex_unlock(&id_priv->handler_mutex); trace_cm_id_destroy(id_priv); _destroy_id(id_priv, state); return; } mutex_unlock(&id_priv->handler_mutex); /* * If this races with destroy then the thread that first assigns state * to a destroying does the cancel. */ cma_cancel_operation(id_priv, state); cma_id_put(id_priv); } static void cma_process_remove(struct cma_device *cma_dev) { mutex_lock(&lock); while (!list_empty(&cma_dev->id_list)) { struct rdma_id_private *id_priv = list_first_entry( &cma_dev->id_list, struct rdma_id_private, device_item); list_del_init(&id_priv->listen_item); list_del_init(&id_priv->device_item); cma_id_get(id_priv); mutex_unlock(&lock); cma_send_device_removal_put(id_priv); mutex_lock(&lock); } mutex_unlock(&lock); cma_dev_put(cma_dev); wait_for_completion(&cma_dev->comp); } static bool cma_supported(struct ib_device *device) { u32 i; rdma_for_each_port(device, i) { if (rdma_cap_ib_cm(device, i) || rdma_cap_iw_cm(device, i)) return true; } return false; } static int cma_add_one(struct ib_device *device) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; struct rdma_id_private *id_priv; unsigned long supported_gids = 0; int ret; u32 i; if (!cma_supported(device)) return -EOPNOTSUPP; cma_dev = kmalloc(sizeof(*cma_dev), GFP_KERNEL); if (!cma_dev) return -ENOMEM; cma_dev->device = device; cma_dev->default_gid_type = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_gid_type), GFP_KERNEL); if (!cma_dev->default_gid_type) { ret = -ENOMEM; goto free_cma_dev; } cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_roce_tos), GFP_KERNEL); if (!cma_dev->default_roce_tos) { ret = -ENOMEM; goto free_gid_type; } rdma_for_each_port (device, i) { supported_gids = roce_gid_type_mask_support(device, i); WARN_ON(!supported_gids); if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE)) cma_dev->default_gid_type[i - rdma_start_port(device)] = CMA_PREFERRED_ROCE_GID_TYPE; else cma_dev->default_gid_type[i - rdma_start_port(device)] = find_first_bit(&supported_gids, BITS_PER_LONG); cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0; } init_completion(&cma_dev->comp); refcount_set(&cma_dev->refcount, 1); INIT_LIST_HEAD(&cma_dev->id_list); ib_set_client_data(device, &cma_client, cma_dev); mutex_lock(&lock); list_add_tail(&cma_dev->list, &dev_list); list_for_each_entry(id_priv, &listen_any_list, listen_any_item) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) goto free_listen; } mutex_unlock(&lock); trace_cm_add_one(device); return 0; free_listen: list_del(&cma_dev->list); mutex_unlock(&lock); /* cma_process_remove() will delete to_destroy */ cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); free_gid_type: kfree(cma_dev->default_gid_type); free_cma_dev: kfree(cma_dev); return ret; } static void cma_remove_one(struct ib_device *device, void *client_data) { struct cma_device *cma_dev = client_data; trace_cm_remove_one(device); mutex_lock(&lock); list_del(&cma_dev->list); mutex_unlock(&lock); cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); kfree(cma_dev->default_gid_type); kfree(cma_dev); } static int cma_init_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); xa_init(&pernet->tcp_ps); xa_init(&pernet->udp_ps); xa_init(&pernet->ipoib_ps); xa_init(&pernet->ib_ps); return 0; } static void cma_exit_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); WARN_ON(!xa_empty(&pernet->tcp_ps)); WARN_ON(!xa_empty(&pernet->udp_ps)); WARN_ON(!xa_empty(&pernet->ipoib_ps)); WARN_ON(!xa_empty(&pernet->ib_ps)); } static struct pernet_operations cma_pernet_operations = { .init = cma_init_net, .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), }; static int __init cma_init(void) { int ret; /* * There is a rare lock ordering dependency in cma_netdev_callback() * that only happens when bonding is enabled. Teach lockdep that rtnl * must never be nested under lock so it can find these without having * to test with bonding. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { rtnl_lock(); mutex_lock(&lock); mutex_unlock(&lock); rtnl_unlock(); } cma_wq = alloc_ordered_workqueue("rdma_cm", WQ_MEM_RECLAIM); if (!cma_wq) return -ENOMEM; ret = register_pernet_subsys(&cma_pernet_operations); if (ret) goto err_wq; ib_sa_register_client(&sa_client); register_netdevice_notifier(&cma_nb); register_netevent_notifier(&cma_netevent_cb); ret = ib_register_client(&cma_client); if (ret) goto err; ret = cma_configfs_init(); if (ret) goto err_ib; return 0; err_ib: ib_unregister_client(&cma_client); err: unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret; } static void __exit cma_cleanup(void) { cma_configfs_exit(); ib_unregister_client(&cma_client); unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); destroy_workqueue(cma_wq); } module_init(cma_init); module_exit(cma_cleanup); |
| 87 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_ENTRYKVM_H #define __LINUX_ENTRYKVM_H #include <linux/static_call_types.h> #include <linux/resume_user_mode.h> #include <linux/syscalls.h> #include <linux/seccomp.h> #include <linux/sched.h> #include <linux/tick.h> /* Transfer to guest mode work */ #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK #ifndef ARCH_XFER_TO_GUEST_MODE_WORK # define ARCH_XFER_TO_GUEST_MODE_WORK (0) #endif #define XFER_TO_GUEST_MODE_WORK \ (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \ _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME | \ ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; /** * arch_xfer_to_guest_mode_handle_work - Architecture specific xfer to guest * mode work handling function. * @vcpu: Pointer to current's VCPU data * @ti_work: Cached TIF flags gathered in xfer_to_guest_mode_handle_work() * * Invoked from xfer_to_guest_mode_handle_work(). Defaults to NOOP. Can be * replaced by architecture specific code. */ static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, unsigned long ti_work); #ifndef arch_xfer_to_guest_mode_work static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, unsigned long ti_work) { return 0; } #endif /** * xfer_to_guest_mode_handle_work - Check and handle pending work which needs * to be handled before going to guest mode * @vcpu: Pointer to current's VCPU data * * Returns: 0 or an error code */ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu); /** * xfer_to_guest_mode_prepare - Perform last minute preparation work that * need to be handled while IRQs are disabled * upon entering to guest. * * Has to be invoked with interrupts disabled before the last call * to xfer_to_guest_mode_work_pending(). */ static inline void xfer_to_guest_mode_prepare(void) { lockdep_assert_irqs_disabled(); tick_nohz_user_enter_prepare(); } /** * __xfer_to_guest_mode_work_pending - Check if work is pending * * Returns: True if work pending, False otherwise. * * Bare variant of xfer_to_guest_mode_work_pending(). Can be called from * interrupt enabled code for racy quick checks with care. */ static inline bool __xfer_to_guest_mode_work_pending(void) { unsigned long ti_work = read_thread_flags(); return !!(ti_work & XFER_TO_GUEST_MODE_WORK); } /** * xfer_to_guest_mode_work_pending - Check if work is pending which needs to be * handled before returning to guest mode * * Returns: True if work pending, False otherwise. * * Has to be invoked with interrupts disabled before the transition to * guest mode. */ static inline bool xfer_to_guest_mode_work_pending(void) { lockdep_assert_irqs_disabled(); return __xfer_to_guest_mode_work_pending(); } #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */ #endif |
| 185 79 50 50 | 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: GPL-2.0 */ /* * include/linux/writeback.h */ #ifndef WRITEBACK_H #define WRITEBACK_H #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/fs.h> #include <linux/flex_proportions.h> #include <linux/backing-dev-defs.h> #include <linux/blk_types.h> #include <linux/pagevec.h> struct bio; DECLARE_PER_CPU(int, dirty_throttle_leaks); /* * The global dirty threshold is normally equal to the global dirty limit, * except when the system suddenly allocates a lot of anonymous memory and * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ #define DIRTY_SCOPE 8 struct backing_dev_info; /* * fs/fs-writeback.c */ enum writeback_sync_modes { WB_SYNC_NONE, /* Don't wait on anything */ WB_SYNC_ALL, /* Wait on every mapping */ }; /* * A control structure which tells the writeback code what to do. These are * always on the stack, and hence need no locking. They are always initialised * in a manner such that unspecified fields are set to zero. */ struct writeback_control { /* public fields that can be set and/or consumed by the caller: */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ /* * For a_ops->writepages(): if start or end are non-zero then this is * a hint that the filesystem need only write out the pages inside that * byterange. The byte at `end' is included in the writeout request. */ loff_t range_start; loff_t range_end; enum writeback_sync_modes sync_mode; unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_background:1; /* A background writeback */ unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */ unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned unpinned_netfs_wb:1; /* Cleared I_PINNING_NETFS_WB */ /* * When writeback IOs are bounced through async layers, only the * initial synchronous phase should be accounted towards inode * cgroup ownership arbitration to avoid confusion. Later stages * can set the following flag to disable the accounting. */ unsigned no_cgroup_owner:1; /* To enable batching of swap writes to non-block-device backends, * "plug" can be set point to a 'struct swap_iocb *'. When all swap * writes have been submitted, if with swap_iocb is not NULL, * swap_write_unplug() should be called. */ struct swap_iocb **swap_plug; /* Target list for splitting a large folio */ struct list_head *list; /* internal fields used by the ->writepages implementation: */ struct folio_batch fbatch; pgoff_t index; int saved_err; #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ /* foreign inode detection, see wbc_detach_inode() */ int wb_id; /* current wb id */ int wb_lcand_id; /* last foreign candidate wb id */ int wb_tcand_id; /* this foreign candidate wb id */ size_t wb_bytes; /* bytes written by current wb */ size_t wb_lcand_bytes; /* bytes written by last candidate */ size_t wb_tcand_bytes; /* bytes written by this candidate */ #endif }; static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc) { blk_opf_t flags = 0; if (wbc->sync_mode == WB_SYNC_ALL) flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) flags |= REQ_BACKGROUND; return flags; } #ifdef CONFIG_CGROUP_WRITEBACK #define wbc_blkcg_css(wbc) \ ((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css) #else #define wbc_blkcg_css(wbc) (blkcg_root_css) #endif /* CONFIG_CGROUP_WRITEBACK */ /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global * domain, global_wb_domain, that every wb in the system is a member of. * This allows measuring the relative bandwidth of each wb to distribute * dirtyable memory accordingly. */ struct wb_domain { spinlock_t lock; /* * Scale the writeback cache size proportional to the relative * writeout speed. * * We do this by keeping a floating proportion between BDIs, based * on page writeback completions [end_page_writeback()]. Those * devices that write out pages fastest will get the larger share, * while the slower will get a smaller share. * * We use page writeout completions because we are interested in * getting rid of dirty pages. Having them written out is the * primary goal. * * We introduce a concept of time, a period over which we measure * these events, because demand can/will vary over time. The length * of this period itself is measured in page writeback completions. */ struct fprop_global completions; struct timer_list period_timer; /* timer for aging of completions */ unsigned long period_time; /* * The dirtyable memory and dirty threshold could be suddenly * knocked down by a large amount (eg. on the startup of KVM in a * swapless system). This may throw the system into deep dirty * exceeded state and throttle heavy/light dirtiers alike. To * retain good responsiveness, maintain global_dirty_limit for * tracking slowly down to the knocked down dirty threshold. * * Both fields are protected by ->lock. */ unsigned long dirty_limit_tstamp; unsigned long dirty_limit; }; /** * wb_domain_size_changed - memory available to a wb_domain has changed * @dom: wb_domain of interest * * This function should be called when the amount of memory available to * @dom has changed. It resets @dom's dirty limit parameters to prevent * the past values which don't match the current configuration from skewing * dirty throttling. Without this, when memory size of a wb_domain is * greatly reduced, the dirty throttling logic may allow too many pages to * be dirtied leading to consecutive unnecessary OOMs and may get stuck in * that situation. */ static inline void wb_domain_size_changed(struct wb_domain *dom) { spin_lock(&dom->lock); dom->dirty_limit_tstamp = jiffies; dom->dirty_limit = 0; spin_unlock(&dom->lock); } /* * fs/fs-writeback.c */ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(enum wb_reason reason); void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) { wait_var_event(inode_state_wait_address(inode, __I_NEW), !(READ_ONCE(inode->i_state) & I_NEW)); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/cgroup.h> #include <linux/bio.h> void __inode_attach_wb(struct inode *inode, struct folio *folio); void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(struct super_block *sb); bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** * inode_attach_wb - associate an inode with its wb * @inode: inode of interest * @folio: folio being dirtied (may be NULL) * * If @inode doesn't have its wb, associate it with the wb matching the * memcg of @folio or, if @folio is NULL, %current. May be called w/ or w/o * @inode->i_lock. */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { if (!inode->i_wb) __inode_attach_wb(inode, folio); } /** * inode_detach_wb - disassociate an inode from its wb * @inode: inode of interest * * @inode is being freed. Detach from its wb. */ static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } } void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode); /** * wbc_init_bio - writeback specific initializtion of bio * @wbc: writeback_control for the writeback in progress * @bio: bio to be initialized * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup * writeback context. Must be called after the bio has been associated with * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (wbc->wb) bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { } static inline void inode_detach_wb(struct inode *inode) { } static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { } static inline void wbc_detach_inode(struct writeback_control *wbc) { } static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { } static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes) { } static inline void cgroup_writeback_umount(struct super_block *sb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * mm/page-writeback.c */ void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); void laptop_mode_timer_fn(struct timer_list *t); bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom); #endif extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int laptop_mode; int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); void wb_update_bandwidth(struct bdi_writeback *wb); /* Invoke balance dirty pages in async mode. */ #define BDP_ASYNC 0x0001 void balance_dirty_pages_ratelimited(struct address_space *mapping); int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags); bool wb_over_bg_thresh(struct bdi_writeback *wb); struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error); typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, void *data); int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio); bool folio_redirty_for_writepage(struct writeback_control *, struct folio *); bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); #endif /* WRITEBACK_H */ |
| 105 503 388 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 33 33 9 5 224 224 224 224 224 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RMAP_H #define _LINUX_RMAP_H /* * Declarations for Reverse Mapping functions in mm/rmap.c */ #include <linux/list.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/rwsem.h> #include <linux/memcontrol.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> /* * The anon_vma heads a list of private "related" vmas, to scan if * an anonymous page pointing to this anon_vma needs to be unmapped: * the vmas on the list will be related by forking, or by splitting. * * Since vmas come and go as they are split and merged (particularly * in mprotect), the mapping field of an anonymous page cannot point * directly to a vma: instead it points to an anon_vma, on whose list * the related vmas can be easily linked or unlinked. * * After unlinking the last vma on the list, we must garbage collect * the anon_vma object itself: we're guaranteed no page can be * pointing to this anon_vma once its vma list is empty. */ struct anon_vma { struct anon_vma *root; /* Root of this anon_vma tree */ struct rw_semaphore rwsem; /* W: modification, R: walking the list */ /* * The refcount is taken on an anon_vma when there is no * guarantee that the vma of page tables will exist for * the duration of the operation. A caller that takes * the reference is responsible for clearing up the * anon_vma if they are the last user on release */ atomic_t refcount; /* * Count of child anon_vmas. Equals to the count of all anon_vmas that * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ unsigned long num_children; /* Count of VMAs whose ->anon_vma pointer points to this object. */ unsigned long num_active_vmas; struct anon_vma *parent; /* Parent of this anon_vma */ /* * NOTE: the LSB of the rb_root.rb_node is set by * mm_take_all_locks() _after_ taking the above lock. So the * rb_root must only be read/written after taking the above lock * to be sure to see a valid next pointer. The LSB bit itself * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ /* Interval tree of private "related" vmas */ struct rb_root_cached rb_root; }; /* * The copy-on-write semantics of fork mean that an anon_vma * can become associated with multiple processes. Furthermore, * each child process will have its own anon_vma, where new * pages for that process are instantiated. * * This structure allows us to find the anon_vmas associated * with a VMA, or the VMAs associated with an anon_vma. * The "same_vma" list contains the anon_vma_chains linking * all the anon_vmas associated with this VMA. * The "rb" field indexes on an interval tree the anon_vma_chains * which link all the VMAs associated with this anon_vma. */ struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB unsigned long cached_vma_start, cached_vma_last; #endif }; enum ttu_flags { TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ TTU_HWPOISON = 0x20, /* do convert pte to hwpoison entry */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ }; #ifdef CONFIG_MMU static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); } void __put_anon_vma(struct anon_vma *anon_vma); static inline void put_anon_vma(struct anon_vma *anon_vma) { if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma); } static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_write(struct anon_vma *anon_vma) { return down_write_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } static inline void anon_vma_lock_read(struct anon_vma *anon_vma) { down_read(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) { return down_read_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); } /* * anon_vma helper functions. */ void anon_vma_init(void); /* create anon_vma_cachep */ int __anon_vma_prepare(struct vm_area_struct *); void unlink_anon_vmas(struct vm_area_struct *); int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); static inline int anon_vma_prepare(struct vm_area_struct *vma) { if (likely(vma->anon_vma)) return 0; return __anon_vma_prepare(vma); } static inline void anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) { VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma); unlink_anon_vmas(next); } struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; /* * No special request: A mapped anonymous (sub)page is possibly shared between * processes. */ #define RMAP_NONE ((__force rmap_t)0) /* The anonymous (sub)page is exclusive to a single process. */ #define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) /* * Internally, we're using an enum to specify the granularity. We make the * compiler emit specialized code for each granularity. */ enum rmap_level { RMAP_LEVEL_PTE = 0, RMAP_LEVEL_PMD, }; static inline void __folio_rmap_sanity_checks(const struct folio *folio, const struct page *page, int nr_pages, enum rmap_level level) { /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); /* When (un)mapping zeropages, we should never touch ref+mapcount. */ VM_WARN_ON_FOLIO(is_zero_folio(folio), folio); /* * TODO: we get driver-allocated folios that have nothing to do with * the rmap using vm_insert_page(); therefore, we cannot assume that * folio_test_large_rmappable() holds for large folios. We should * handle any desired mapcount+stats accounting for these folios in * VM_MIXEDMAP VMAs separately, and then sanity-check here that * we really only get rmappable folios. */ VM_WARN_ON_ONCE(nr_pages <= 0); VM_WARN_ON_FOLIO(page_folio(page) != folio, folio); VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio); switch (level) { case RMAP_LEVEL_PTE: break; case RMAP_LEVEL_PMD: /* * We don't support folios larger than a single PMD yet. So * when RMAP_LEVEL_PMD is set, we assume that we are creating * a single "entire" mapping of the folio. */ VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio); VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio); break; default: VM_WARN_ON_ONCE(true); } } /* * rmap interfaces called when adding or removing pte of page */ void folio_move_anon_rmap(struct folio *, struct vm_area_struct *); void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *, unsigned long address, rmap_t flags); #define folio_add_anon_rmap_pte(folio, page, vma, address, flags) \ folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags) void folio_add_anon_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_add_file_rmap_pte(folio, page, vma) \ folio_add_file_rmap_ptes(folio, page, 1, vma) void folio_add_file_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_remove_rmap_pte(folio, page, vma) \ folio_remove_rmap_ptes(folio, page, 1, vma) void folio_remove_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); /* See folio_try_dup_anon_rmap_*() */ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); if (PageAnonExclusive(&folio->page)) { if (unlikely(folio_needs_cow_for_dma(vma, folio))) return -EBUSY; ClearPageAnonExclusive(&folio->page); } atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); return 0; } /* See folio_try_share_anon_rmap_*() */ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); /* Paired with the memory barrier in try_grab_folio(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) return -EBUSY; ClearPageAnonExclusive(&folio->page); /* * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } static inline void hugetlb_add_file_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); } static inline void hugetlb_remove_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); atomic_dec(&folio->_entire_mapcount); atomic_dec(&folio->_large_mapcount); } static __always_inline void __folio_dup_file_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { const int orig_nr_pages = nr_pages; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { atomic_inc(&folio->_mapcount); break; } do { atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); break; } } /** * folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio * @folio: The folio to duplicate the mappings of * @page: The first page to duplicate the mappings of * @nr_pages: The number of pages of which the mapping will be duplicated * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ static inline void folio_dup_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages) { __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); } static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, struct page *page) { __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE); } /** * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio * @folio: The folio to duplicate the mapping of * @page: The first page to duplicate the mapping of * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ static inline void folio_dup_file_rmap_pmd(struct folio *folio, struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PTE); #else WARN_ON_ONCE(true); #endif } static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma, enum rmap_level level) { const int orig_nr_pages = nr_pages; bool maybe_pinned; int i; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); __folio_rmap_sanity_checks(folio, page, nr_pages, level); /* * If this folio may have been pinned by the parent process, * don't allow to duplicate the mappings but instead require to e.g., * copy the subpage immediately for the child so that we'll always * guarantee the pinned folio won't be randomly replaced in the * future on write faults. */ maybe_pinned = likely(!folio_is_device_private(folio)) && unlikely(folio_needs_cow_for_dma(src_vma, folio)); /* * No need to check+clear for already shared PTEs/PMDs of the * folio. But if any page is PageAnonExclusive, we must fallback to * copying if the folio maybe pinned. */ switch (level) { case RMAP_LEVEL_PTE: if (unlikely(maybe_pinned)) { for (i = 0; i < nr_pages; i++) if (PageAnonExclusive(page + i)) return -EBUSY; } if (!folio_test_large(folio)) { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&folio->_mapcount); break; } do { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: if (PageAnonExclusive(page)) { if (unlikely(maybe_pinned)) return -EBUSY; ClearPageAnonExclusive(page); } atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); break; } return 0; } /** * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range * of a folio * @folio: The folio to duplicate the mappings of * @page: The first page to duplicate the mappings of * @nr_pages: The number of pages of which the mapping will be duplicated * @src_vma: The vm area from which the mappings are duplicated * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock and the * vma->vma_mm->write_protect_seq. * * Duplicating the mappings can only fail if the folio may be pinned; device * private folios cannot get pinned and consequently this function cannot fail * for them. * * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in * the parent and the child. They must *not* be writable after this call * succeeded. * * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise. */ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma) { return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, RMAP_LEVEL_PTE); } static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, struct page *page, struct vm_area_struct *src_vma) { return __folio_try_dup_anon_rmap(folio, page, 1, src_vma, RMAP_LEVEL_PTE); } /** * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range * of a folio * @folio: The folio to duplicate the mapping of * @page: The first page to duplicate the mapping of * @src_vma: The vm area from which the mapping is duplicated * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock and the * vma->vma_mm->write_protect_seq. * * Duplicating the mapping can only fail if the folio may be pinned; device * private folios cannot get pinned and consequently this function cannot fail * for them. * * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in * the parent and the child. They must *not* be writable after this call * succeeded. * * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. */ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *src_vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; #endif } static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio); __folio_rmap_sanity_checks(folio, page, nr_pages, level); /* device private folios cannot get pinned via GUP. */ if (unlikely(folio_is_device_private(folio))) { ClearPageAnonExclusive(page); return 0; } /* * We have to make sure that when we clear PageAnonExclusive, that * the page is not pinned and that concurrent GUP-fast won't succeed in * concurrently pinning the page. * * Conceptually, PageAnonExclusive clearing consists of: * (A1) Clear PTE * (A2) Check if the page is pinned; back off if so. * (A3) Clear PageAnonExclusive * (A4) Restore PTE (optional, but certainly not writable) * * When clearing PageAnonExclusive, we cannot possibly map the page * writable again, because anon pages that may be shared must never * be writable. So in any case, if the PTE was writable it cannot * be writable anymore afterwards and there would be a PTE change. Only * if the PTE wasn't writable, there might not be a PTE change. * * Conceptually, GUP-fast pinning of an anon page consists of: * (B1) Read the PTE * (B2) FOLL_WRITE: check if the PTE is not writable; back off if so. * (B3) Pin the mapped page * (B4) Check if the PTE changed by re-reading it; back off if so. * (B5) If the original PTE is not writable, check if * PageAnonExclusive is not set; back off if so. * * If the PTE was writable, we only have to make sure that GUP-fast * observes a PTE change and properly backs off. * * If the PTE was not writable, we have to make sure that GUP-fast either * detects a (temporary) PTE change or that PageAnonExclusive is cleared * and properly backs off. * * Consequently, when clearing PageAnonExclusive(), we have to make * sure that (A1), (A2)/(A3) and (A4) happen in the right memory * order. In GUP-fast pinning code, we have to make sure that (B3),(B4) * and (B5) happen in the right memory order. * * We assume that there might not be a memory barrier after * clearing/invalidating the PTE (A1) and before restoring the PTE (A4), * so we use explicit ones here. */ /* Paired with the memory barrier in try_grab_folio(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) return -EBUSY; ClearPageAnonExclusive(page); /* * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } /** * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page * mapped by a PTE possibly shared to prepare * for KSM or temporary unmapping * @folio: The folio to share a mapping of * @page: The mapped exclusive page * * The caller needs to hold the page table lock and has to have the page table * entries cleared/invalidated. * * This is similar to folio_try_dup_anon_rmap_pte(), however, not used during * fork() to duplicate mappings, but instead to prepare for KSM or temporarily * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte(). * * Marking the mapped page shared can only fail if the folio maybe pinned; * device private folios cannot get pinned and consequently this function cannot * fail. * * Returns 0 if marking the mapped page possibly shared succeeded. Returns * -EBUSY otherwise. */ static inline int folio_try_share_anon_rmap_pte(struct folio *folio, struct page *page) { return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE); } /** * folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page * range mapped by a PMD possibly shared to * prepare for temporary unmapping * @folio: The folio to share the mapping of * @page: The first page to share the mapping of * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock and has to have the page table * entries cleared/invalidated. * * This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during * fork() to duplicate a mapping, but instead to prepare for temporarily * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd(). * * Marking the mapped pages shared can only fail if the folio maybe pinned; * device private folios cannot get pinned and consequently this function cannot * fail. * * Returns 0 if marking the mapped pages possibly shared succeeded. Returns * -EBUSY otherwise. */ static inline int folio_try_share_anon_rmap_pmd(struct folio *folio, struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); return -EBUSY; #endif } /* * Called from mm/vmscan.c to handle paging out */ int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); void try_to_migrate(struct folio *folio, enum ttu_flags flags); void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *arg); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) /* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { unsigned long pfn; unsigned long nr_pages; pgoff_t pgoff; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; unsigned int flags; }; #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ .pfn = folio_pfn(_folio), \ .nr_pages = folio_nr_pages(_folio), \ .pgoff = folio_pgoff(_folio), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ } static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); } /** * page_vma_mapped_walk_restart - Restart the page table walk. * @pvmw: Pointer to struct page_vma_mapped_walk. * * It restarts the page table walk when changes occur in the page * table, such as splitting a PMD. Ensures that the PTL held during * the previous walk is released and resets the state to allow for * a new walk starting at the current address stored in pvmw->address. */ static inline void page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) { WARN_ON_ONCE(!pvmw->pmd && !pvmw->pte); if (likely(pvmw->ptl)) spin_unlock(pvmw->ptl); else WARN_ON_ONCE(1); pvmw->ptl = NULL; pvmw->pmd = NULL; pvmw->pte = NULL; } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); unsigned long page_address_in_vma(const struct folio *folio, const struct page *, const struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. * (and since clean PTEs should also be readonly, write protects them too) * * returns the number of cleaned PTEs. */ int folio_mkclean(struct folio *); int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); enum rmp_flags { RMP_LOCKED = 1 << 0, RMP_USE_SHARED_ZEROPAGE = 1 << 1, }; void remove_migration_ptes(struct folio *src, struct folio *dst, int flags); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() * try_lock: bail out if the rmap lock is contended * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ struct rmap_walk_control { void *arg; bool try_lock; bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); struct anon_vma *(*anon_lock)(const struct folio *folio, struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) #define anon_vma_prepare(vma) (0) static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { *vm_flags = 0; return 0; } static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags) { } static inline int folio_mkclean(struct folio *folio) { return 0; } #endif /* CONFIG_MMU */ #endif /* _LINUX_RMAP_H */ |
| 43 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU #ifdef CONFIG_SWAP #include <linux/swapfile.h> #endif /* CONFIG_SWAP */ /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS #define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ #define SWP_PFN_BITS min_t(int, \ sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ #define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: * * |----------+--------------------| * | swp_type | swp_offset | * |----------+--------+-+-+-------| * | | resv |D|A| PFN | * |----------+--------+-+-+-------| * * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) * * Note: A/D bits will be stored in migration entries iff there're enough * free bits in arch specific swp offset. By default we'll ignore A/D bits * when migrating a page. Please refer to migration_entry_supports_ad() * for more information. If there're more bits besides PFN and A/D bits, * they should be reserved and always be zeros. */ #define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) #define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) #define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) #define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) #define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) static inline bool is_pfn_swap_entry(swp_entry_t entry); /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { if (pte_swp_exclusive(pte)) pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) pte = pte_swp_clear_uffd_wp(pte); return pte; } /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* * This should only be called upon a pfn swap entry to get the PFN stored * in the swap entry. Please refers to is_pfn_swap_entry() for definition * of pfn swap entry. */ static inline unsigned long swp_offset_pfn(swp_entry_t entry) { VM_BUG_ON(!is_pfn_swap_entry(entry)); return swp_offset(entry) & SWP_PFN_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_READ, offset); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_readable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ); } static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); } static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); } /* * Returns whether the host has large enough swap offset field to support * carrying over pgtable A/D bits for page migrations. The result is * pretty much arch specific. */ static inline bool migration_entry_supports_ad(void) { #ifdef CONFIG_SWAP return swap_migration_ad_supported; #else /* CONFIG_SWAP */ return false; #endif /* CONFIG_SWAP */ } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_YOUNG); return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_YOUNG; /* Keep the old behavior of aging page after migration */ return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_DIRTY); return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_DIRTY; /* Keep the old behavior of clean page after migration */ return false; } extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } static inline int is_readable_migration_entry(swp_entry_t entry) { return 0; } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { return false; } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } #endif typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) /* * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. * * Note that, when encountered by the faulting logic, PTEs with this marker will * result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error * logic. */ #define PTE_MARKER_POISONED BIT(1) /* * Indicates that, on fault, this PTE will case a SIGSEGV signal to be * sent. This means guard markers behave in effect as if the region were mapped * PROT_NONE, rather than if they were a memory hole or equivalent. */ #define PTE_MARKER_GUARD BIT(2) #define PTE_MARKER_MASK (BIT(3) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { return swp_entry(SWP_PTE_MARKER, marker); } static inline bool is_pte_marker_entry(swp_entry_t entry) { return swp_type(entry) == SWP_PTE_MARKER; } static inline pte_marker pte_marker_get(swp_entry_t entry) { return swp_offset(entry) & PTE_MARKER_MASK; } static inline bool is_pte_marker(pte_t pte) { return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); } static inline pte_t make_pte_marker(pte_marker marker) { return swp_entry_to_pte(make_pte_marker_entry(marker)); } static inline swp_entry_t make_poisoned_swp_entry(void) { return make_pte_marker_entry(PTE_MARKER_POISONED); } static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); } static inline swp_entry_t make_guard_swp_entry(void) { return make_pte_marker_entry(PTE_MARKER_GUARD); } static inline int is_guard_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_GUARD); } /* * This is a special version to check pte_none() just to cover the case when * the pte is a pte marker. It existed because in many cases the pte marker * should be seen as a none pte; it's just that we have stored some information * onto the none pte so it becomes not-none any more. * * It should be used when the pte is file-backed, ram-based and backing * userspace pages, like shmem. It is not needed upon pgtables that do not * support pte markers at all. For example, it's not needed on anonymous * memory, kernel-only memory (including when the system is during-boot), * non-ram based generic file-system. It's fine to be used even there, but the * extra pte marker check will be pure overhead. */ static inline int pte_none_mostly(pte_t pte) { return pte_none(pte) || is_pte_marker(pte); } static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(is_migration_entry(entry) && !PageLocked(p)); return p; } static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) { struct folio *folio = pfn_folio(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding folio is locked */ BUG_ON(is_migration_entry(entry) && !folio_test_locked(folio)); return folio; } /* * A pfn swap entry is a special type of swap entry that always has a pfn stored * in the swap offset. They can either be used to represent unaddressable device * memory, to restrict access to a page undergoing migration or to represent a * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { /* Make sure the swp offset can always store the needed fields */ BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |
| 226 226 226 226 226 226 226 226 226 226 226 226 226 226 225 226 226 226 226 226 226 226 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * kernel userspace event delivery * * Copyright (C) 2004 Red Hat, Inc. All rights reserved. * Copyright (C) 2004 Novell, Inc. All rights reserved. * Copyright (C) 2004 IBM, Inc. All rights reserved. * * Authors: * Robert Love <rml@novell.com> * Kay Sievers <kay.sievers@vrfy.org> * Arjan van de Ven <arjanv@redhat.com> * Greg Kroah-Hartman <greg@kroah.com> */ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/kobject.h> #include <linux/export.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/uidgid.h> #include <linux/uuid.h> #include <linux/ctype.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> atomic64_t uevent_seqnum; #ifdef CONFIG_UEVENT_HELPER char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH; #endif struct uevent_sock { struct list_head list; struct sock *sk; }; #ifdef CONFIG_NET static LIST_HEAD(uevent_sock_list); /* This lock protects uevent_sock_list */ static DEFINE_MUTEX(uevent_sock_mutex); #endif /* the strings here must match the enum in include/linux/kobject.h */ static const char *kobject_actions[] = { [KOBJ_ADD] = "add", [KOBJ_REMOVE] = "remove", [KOBJ_CHANGE] = "change", [KOBJ_MOVE] = "move", [KOBJ_ONLINE] = "online", [KOBJ_OFFLINE] = "offline", [KOBJ_BIND] = "bind", [KOBJ_UNBIND] = "unbind", }; static int kobject_action_type(const char *buf, size_t count, enum kobject_action *type, const char **args) { enum kobject_action action; size_t count_first; const char *args_start; int ret = -EINVAL; if (count && (buf[count-1] == '\n' || buf[count-1] == '\0')) count--; if (!count) goto out; args_start = strnchr(buf, count, ' '); if (args_start) { count_first = args_start - buf; args_start = args_start + 1; } else count_first = count; for (action = 0; action < ARRAY_SIZE(kobject_actions); action++) { if (strncmp(kobject_actions[action], buf, count_first) != 0) continue; if (kobject_actions[action][count_first] != '\0') continue; if (args) *args = args_start; *type = action; ret = 0; break; } out: return ret; } static const char *action_arg_word_end(const char *buf, const char *buf_end, char delim) { const char *next = buf; while (next <= buf_end && *next != delim) if (!isalnum(*next++)) return NULL; if (next == buf) return NULL; return next; } static int kobject_action_args(const char *buf, size_t count, struct kobj_uevent_env **ret_env) { struct kobj_uevent_env *env = NULL; const char *next, *buf_end, *key; int key_len; int r = -EINVAL; if (count && (buf[count - 1] == '\n' || buf[count - 1] == '\0')) count--; if (!count) return -EINVAL; env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return -ENOMEM; /* first arg is UUID */ if (count < UUID_STRING_LEN || !uuid_is_valid(buf) || add_uevent_var(env, "SYNTH_UUID=%.*s", UUID_STRING_LEN, buf)) goto out; /* * the rest are custom environment variables in KEY=VALUE * format with ' ' delimiter between each KEY=VALUE pair */ next = buf + UUID_STRING_LEN; buf_end = buf + count - 1; while (next <= buf_end) { if (*next != ' ') goto out; /* skip the ' ', key must follow */ key = ++next; if (key > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, '='); if (!next || next > buf_end || *next != '=') goto out; key_len = next - buf; /* skip the '=', value must follow */ if (++next > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, ' '); if (!next) goto out; if (add_uevent_var(env, "SYNTH_ARG_%.*s=%.*s", key_len, key, (int) (next - buf), buf)) goto out; } r = 0; out: if (r) kfree(env); else *ret_env = env; return r; } /** * kobject_synth_uevent - send synthetic uevent with arguments * * @kobj: struct kobject for which synthetic uevent is to be generated * @buf: buffer containing action type and action args, newline is ignored * @count: length of buffer * * Returns 0 if kobject_synthetic_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) { char *no_uuid_envp[] = { "SYNTH_UUID=0", NULL }; enum kobject_action action; const char *action_args; struct kobj_uevent_env *env; const char *msg = NULL, *devpath; int r; r = kobject_action_type(buf, count, &action, &action_args); if (r) { msg = "unknown uevent action string"; goto out; } if (!action_args) { r = kobject_uevent_env(kobj, action, no_uuid_envp); goto out; } r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { msg = "incorrect uevent action arguments"; goto out; } if (r) goto out; r = kobject_uevent_env(kobj, action, env->envp); kfree(env); out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); } return r; } #ifdef CONFIG_UEVENT_HELPER static int kobj_usermode_filter(struct kobject *kobj) { const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); return ns != init_ns; } return 0; } static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem) { int buffer_size = sizeof(env->buf) - env->buflen; int len; len = strscpy(&env->buf[env->buflen], subsystem, buffer_size); if (len < 0) { pr_warn("%s: insufficient buffer space (%u left) for %s\n", __func__, buffer_size, subsystem); return -ENOMEM; } env->argv[0] = uevent_helper; env->argv[1] = &env->buf[env->buflen]; env->argv[2] = NULL; env->buflen += len + 1; return 0; } static void cleanup_uevent_env(struct subprocess_info *info) { kfree(info->data); } #endif #ifdef CONFIG_NET static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct netlink_skb_parms *parms; struct sk_buff *skb = NULL; char *scratch; size_t len; /* allocate message with maximum possible size */ len = strlen(action_string) + strlen(devpath) + 2; skb = alloc_skb(len + env->buflen, GFP_KERNEL); if (!skb) return NULL; /* add header */ scratch = skb_put(skb, len); sprintf(scratch, "%s@%s", action_string, devpath); skb_put_data(skb, env->buf, env->buflen); parms = &NETLINK_CB(skb); parms->creds.uid = GLOBAL_ROOT_UID; parms->creds.gid = GLOBAL_ROOT_GID; parms->dst_group = 1; parms->portid = 0; return skb; } static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct sk_buff *skb = NULL; struct uevent_sock *ue_sk; int retval = 0; /* send netlink message */ mutex_lock(&uevent_sock_mutex); list_for_each_entry(ue_sk, &uevent_sock_list, list) { struct sock *uevent_sock = ue_sk->sk; if (!netlink_has_listeners(uevent_sock, 1)) continue; if (!skb) { retval = -ENOMEM; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) continue; } retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } mutex_unlock(&uevent_sock_mutex); consume_skb(skb); return retval; } static int uevent_net_broadcast_tagged(struct sock *usk, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct user_namespace *owning_user_ns = sock_net(usk)->user_ns; struct sk_buff *skb = NULL; int ret = 0; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) return -ENOMEM; /* fix credentials */ if (owning_user_ns != &init_user_ns) { struct netlink_skb_parms *parms = &NETLINK_CB(skb); kuid_t root_uid; kgid_t root_gid; /* fix uid */ root_uid = make_kuid(owning_user_ns, 0); if (uid_valid(root_uid)) parms->creds.uid = root_uid; /* fix gid */ root_gid = make_kgid(owning_user_ns, 0); if (gid_valid(root_gid)) parms->creds.gid = root_gid; } ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } #endif static int kobject_uevent_net_broadcast(struct kobject *kobj, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { int ret = 0; #ifdef CONFIG_NET const struct kobj_ns_type_operations *ops; const struct net *net = NULL; ops = kobj_ns_ops(kobj); if (!ops && kobj->kset) { struct kobject *ksobj = &kobj->kset->kobj; if (ksobj->parent != NULL) ops = kobj_ns_ops(ksobj->parent); } /* kobjects currently only carry network namespace tags and they * are the only tag relevant here since we want to decide which * network namespaces to broadcast the uevent into. */ if (ops && ops->netlink_ns && kobj->ktype->namespace) if (ops->type == KOBJ_NS_TYPE_NET) net = kobj->ktype->namespace(kobj); if (!net) ret = uevent_net_broadcast_untagged(env, action_string, devpath); else ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, action_string, devpath); #endif return ret; } static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; size_t len; int i, j; for (i = 0; i < env->envp_idx;) { if (strncmp(env->envp[i], modalias_prefix, sizeof(modalias_prefix) - 1)) { i++; continue; } len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { /* @env->envp[] contains pointers to @env->buf[] * with @env->buflen chars, and we are removing * variable MODALIAS here pointed by @env->envp[i] * with length @len as shown below: * * 0 @env->buf[] @env->buflen * --------------------------------------------- * ^ ^ ^ ^ * | |-> @len <-| target block | * @env->envp[0] @env->envp[i] @env->envp[i + 1] * * so the "target block" indicated above is moved * backward by @len, and its right size is * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). */ memmove(env->envp[i], env->envp[i + 1], env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; } env->envp_idx--; env->buflen -= len; } } /** * kobject_uevent_env - send an uevent with environmental data * * @kobj: struct kobject that the action is happening to * @action: action that is happening * @envp_ext: pointer to environmental data * * Returns 0 if kobject_uevent_env() is completed with success or the * corresponding error when it fails. */ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp_ext[]) { struct kobj_uevent_env *env; const char *action_string = kobject_actions[action]; const char *devpath = NULL; const char *subsystem; struct kobject *top_kobj; struct kset *kset; const struct kset_uevent_ops *uevent_ops; int i = 0; int retval = 0; /* * Mark "remove" event done regardless of result, for some subsystems * do not want to re-trigger "remove" event via automatic cleanup. */ if (action == KOBJ_REMOVE) kobj->state_remove_uevent_sent = 1; pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); /* search the kset we belong to */ top_kobj = kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) { pr_debug("kobject: '%s' (%p): %s: attempted to send uevent " "without kset!\n", kobject_name(kobj), kobj, __func__); return -EINVAL; } kset = top_kobj->kset; uevent_ops = kset->uevent_ops; /* skip the event, if uevent_suppress is set*/ if (kobj->uevent_suppress) { pr_debug("kobject: '%s' (%p): %s: uevent_suppress " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* originating subsystem */ if (uevent_ops && uevent_ops->name) subsystem = uevent_ops->name(kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the " "event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* environment buffer */ env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* complete object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { retval = -ENOENT; goto exit; } /* default keys */ retval = add_uevent_var(env, "ACTION=%s", action_string); if (retval) goto exit; retval = add_uevent_var(env, "DEVPATH=%s", devpath); if (retval) goto exit; retval = add_uevent_var(env, "SUBSYSTEM=%s", subsystem); if (retval) goto exit; /* keys passed in from the caller */ if (envp_ext) { for (i = 0; envp_ext[i]; i++) { retval = add_uevent_var(env, "%s", envp_ext[i]); if (retval) goto exit; } } /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { retval = uevent_ops->uevent(kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, __func__, retval); goto exit; } } switch (action) { case KOBJ_ADD: /* * Mark "add" event so we can make sure we deliver "remove" * event to userspace during automatic cleanup. If * the object did send an "add" event, "remove" will * automatically generated by the core, if not already done * by the caller. */ kobj->state_add_uevent_sent = 1; break; case KOBJ_UNBIND: zap_modalias_env(env); break; default: break; } /* we will send an event, so request a new sequence number */ retval = add_uevent_var(env, "SEQNUM=%llu", atomic64_inc_return(&uevent_seqnum)); if (retval) goto exit; retval = kobject_uevent_net_broadcast(kobj, env, action_string, devpath); #ifdef CONFIG_UEVENT_HELPER /* call uevent_helper, usually only enabled during early boot */ if (uevent_helper[0] && !kobj_usermode_filter(kobj)) { struct subprocess_info *info; retval = add_uevent_var(env, "HOME=/"); if (retval) goto exit; retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin"); if (retval) goto exit; retval = init_uevent_argv(env, subsystem); if (retval) goto exit; retval = -ENOMEM; info = call_usermodehelper_setup(env->argv[0], env->argv, env->envp, GFP_KERNEL, NULL, cleanup_uevent_env, env); if (info) { retval = call_usermodehelper_exec(info, UMH_NO_WAIT); env = NULL; /* freed by cleanup_uevent_env */ } } #endif exit: kfree(devpath); kfree(env); return retval; } EXPORT_SYMBOL_GPL(kobject_uevent_env); /** * kobject_uevent - notify userspace by sending an uevent * * @kobj: struct kobject that the action is happening to * @action: action that is happening * * Returns 0 if kobject_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_uevent(struct kobject *kobj, enum kobject_action action) { return kobject_uevent_env(kobj, action, NULL); } EXPORT_SYMBOL_GPL(kobject_uevent); /** * add_uevent_var - add key value string to the environment buffer * @env: environment buffer structure * @format: printf format for the key=value pair * * Returns 0 if environment variable was added successfully or -ENOMEM * if no space was available. */ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { va_list args; int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } va_start(args, format); len = vsnprintf(&env->buf[env->buflen], sizeof(env->buf) - env->buflen, format, args); va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } env->envp[env->envp_idx++] = &env->buf[env->buflen]; env->buflen += len + 1; return 0; } EXPORT_SYMBOL_GPL(add_uevent_var); #if defined(CONFIG_NET) static int uevent_net_broadcast(struct sock *usk, struct sk_buff *skb, struct netlink_ext_ack *extack) { /* u64 to chars: 2^64 - 1 = 21 chars */ char buf[sizeof("SEQNUM=") + 21]; struct sk_buff *skbc; int ret; /* bump and prepare sequence number */ ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", atomic64_inc_return(&uevent_seqnum)); if (ret < 0 || (size_t)ret >= sizeof(buf)) return -ENOMEM; ret++; /* verify message does not overflow */ if ((skb->len + ret) > UEVENT_BUFFER_SIZE) { NL_SET_ERR_MSG(extack, "uevent message too big"); return -EINVAL; } /* copy skb and extend to accommodate sequence number */ skbc = skb_copy_expand(skb, 0, ret, GFP_KERNEL); if (!skbc) return -ENOMEM; /* append sequence number */ skb_put_data(skbc, buf, ret); /* remove msg header */ skb_pull(skbc, NLMSG_HDRLEN); /* set portid 0 to inform userspace message comes from kernel */ NETLINK_CB(skbc).portid = 0; NETLINK_CB(skbc).dst_group = 1; ret = netlink_broadcast(usk, skbc, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } static int uevent_net_rcv_skb(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net; int ret; if (!nlmsg_data(nlh)) return -EINVAL; /* * Verify that we are allowed to send messages to the target * network namespace. The caller must have CAP_SYS_ADMIN in the * owning user namespace of the target network namespace. */ net = sock_net(NETLINK_CB(skb).sk); if (!netlink_ns_capable(skb, net->user_ns, CAP_SYS_ADMIN)) { NL_SET_ERR_MSG(extack, "missing CAP_SYS_ADMIN capability"); return -EPERM; } ret = uevent_net_broadcast(net->uevent_sock->sk, skb, extack); return ret; } static void uevent_net_rcv(struct sk_buff *skb) { netlink_rcv_skb(skb, &uevent_net_rcv_skb); } static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; struct netlink_kernel_cfg cfg = { .groups = 1, .input = uevent_net_rcv, .flags = NL_CFG_F_NONROOT_RECV }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } net->uevent_sock = ue_sk; /* Restrict uevents to initial user namespace. */ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_add_tail(&ue_sk->list, &uevent_sock_list); mutex_unlock(&uevent_sock_mutex); } return 0; } static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk = net->uevent_sock; if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_del(&ue_sk->list); mutex_unlock(&uevent_sock_mutex); } netlink_kernel_release(ue_sk->sk); kfree(ue_sk); } static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, }; static int __init kobject_uevent_init(void) { return register_pernet_subsys(&uevent_net_ops); } postcore_initcall(kobject_uevent_init); #endif |
| 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * FIB front-end. * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ /* Changes: * * YOSHIFUJI Hideaki @USAGI * reworked default router selection. * - respect outgoing interface * - select from (probably) reachable routers (i.e. * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. * Ville Nuorvala * Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/capability.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/mroute6.h> #include <linux/init.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> #include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/tcp.h> #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> #include <net/ip.h> #include <linux/uaccess.h> #include <linux/btf_ids.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static int ip6_rt_type_to_error(u8 fib6_type); #define CREATE_TRACE_POINTS #include <trace/events/fib6.h> EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); #undef CREATE_TRACE_POINTS enum rt6_nud_state { RT6_NUD_FAIL_HARD = -3, RT6_NUD_FAIL_PROBE = -2, RT6_NUD_FAIL_DO_RR = -1, RT6_NUD_SUCCEED = 1 }; INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict); static size_t rt6_nlmsg_size(struct fib6_info *f6i); static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); #endif struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->dst.rt_uncached)) { struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void rt6_uncached_list_flush_dev(struct net_device *dev) { int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt, *safe; if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; bool handled = false; if (rt_idev && rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); handled = true; } if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; netdev_ref_replace(rt_dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); handled = true; } if (handled) list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) return &ipv6_hdr(skb)->daddr; return daddr; } struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr) { struct neighbour *n; daddr = choose_neigh_daddr(gw, skb, daddr); n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; n = neigh_create(&nd_tbl, daddr, dev); return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst->dev, skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst->dev; daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) return; if (ipv6_addr_is_multicast((const struct in6_addr *)daddr)) return; __ipv6_confirm_neigh(dev, daddr); } static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .default_advmss = ip6_default_advmss, .neigh_lookup = ip6_dst_neigh_lookup, .check = ip6_dst_check, .destroy = ip6_dst_destroy, .cow_metrics = dst_cow_metrics_generic, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; static const struct fib6_info fib6_null_entry_template = { .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), .fib6_protocol = RTPROT_KERNEL, .fib6_metric = ~(u32)0, .fib6_ref = REFCOUNT_INIT(1), .fib6_type = RTN_UNREACHABLE, .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, }; static const struct rt6_info ip6_null_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #endif static void rt6_info_init(struct rt6_info *rt) { memset_after(rt, 0, dst); } /* allocate dst with ip6_dst_ops */ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); } return rt; } EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; ip_dst_metrics_put(dst); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; struct fib6_info *from; if (idev && idev->dev != blackhole_netdev) { struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); if (blackhole_idev) { rt->rt6i_idev = blackhole_idev; in6_dev_put(idev); } } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static bool __rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) return time_after(jiffies, rt->dst.expires); else return false; } static bool rt6_check_expired(const struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, rt->dst.expires)) return true; } else if (from) { return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || fib6_check_expired(from); } return false; } void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { struct fib6_info *match = res->f6i; struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; if (match->nh && have_oif_match && res->nh) return; if (skb) IP6CB(skb)->flags |= IP6SKB_MULTIPATH; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash && (!match->nh || nexthop_is_multipath(match->nh))) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (unlikely(match->nh)) { nexthop_path_fib6_result(res, fl6->mp_hash); return; } if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; list_for_each_entry_rcu(sibling, &match->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); if (fl6->mp_hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; match = sibling; break; } out: res->f6i = match; res->nh = match->fib6_nh; } /* * Route lookup. rcu_read_lock() should be held. */ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh, const struct in6_addr *saddr, int oif, int flags) { const struct net_device *dev; if (nh->fib_nh_flags & RTNH_F_DEAD) return false; dev = nh->fib_nh_dev; if (oif) { if (dev->ifindex == oif) return true; } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) return true; } return false; } struct fib6_nh_dm_arg { struct net *net; const struct in6_addr *saddr; int oif; int flags; struct fib6_nh *nh; }; static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_dm_arg *arg = _arg; arg->nh = nh; return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif, arg->flags); } /* returns fib6_nh from nexthop or NULL */ static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_nh_dm_arg arg = { .net = net, .saddr = saddr, .oif = oif, .flags = flags, }; if (nexthop_is_blackhole(nh)) return NULL; if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg)) return arg.nh; return NULL; } static void rt6_device_match(struct net *net, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_info *f6i = res->f6i; struct fib6_info *spf6i; struct fib6_nh *nh; if (!oif && ipv6_addr_any(saddr)) { if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (!(nh->fib_nh_flags & RTNH_F_DEAD)) goto out; } for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) { bool matched = false; if (unlikely(spf6i->nh)) { nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr, oif, flags); if (nh) matched = true; } else { nh = spf6i->fib6_nh; if (__rt6_device_match(net, nh, saddr, oif, flags)) matched = true; } if (matched) { res->f6i = spf6i; goto out; } } if (oif && flags & RT6_LOOKUP_F_IFACE) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; goto out; } if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (nh->fib_nh_flags & RTNH_F_DEAD) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; } out: res->nh = nh; res->fib6_type = res->f6i->fib6_type; res->fib6_flags = res->f6i->fib6_flags; return; out_blackhole: res->fib6_flags |= RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->nh = nh; } #ifdef CONFIG_IPV6_ROUTER_PREF struct __rt6_probe_work { struct work_struct work; struct in6_addr target; struct net_device *dev; netdevice_tracker dev_tracker; }; static void rt6_probe_deferred(struct work_struct *w) { struct in6_addr mcaddr; struct __rt6_probe_work *work = container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); netdev_put(work->dev, &work->dev_tracker); kfree(work); } static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it * is really so; aka Router Reachability Probing. * * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); if (!idev) goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } if (!work || cmpxchg(&fib6_nh->last_probe, last_probe, jiffies) != last_probe) { kfree(work); } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } out: rcu_read_unlock(); } #else static inline void rt6_probe(struct fib6_nh *fib6_nh) { } #endif /* * Default Router Selection (RFC 2461 6.3.6) */ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) { enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; struct neighbour *neigh; rcu_read_lock(); neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { u8 nud_state = READ_ONCE(neigh->nud_state); if (nud_state & NUD_VALID) ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; else ret = RT6_NUD_FAIL_PROBE; #endif } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } rcu_read_unlock(); return ret; } static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict) { int m = 0; if (!oif || nh->fib_nh_dev->ifindex == oif) m = 2; if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2; #endif if ((strict & RT6_LOOKUP_F_REACHABLE) && !(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) { int n = rt6_check_neigh(nh); if (n < 0) return n; } return m; } static bool find_match(struct fib6_nh *nh, u32 fib6_flags, int oif, int strict, int *mpri, bool *do_rr) { bool match_do_rr = false; bool rc = false; int m; if (nh->fib_nh_flags & RTNH_F_DEAD) goto out; if (ip6_ignore_linkdown(nh->fib_nh_dev) && nh->fib_nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; m = rt6_score_route(nh, fib6_flags, oif, strict); if (m == RT6_NUD_FAIL_DO_RR) { match_do_rr = true; m = 0; /* lowest valid score */ } else if (m == RT6_NUD_FAIL_HARD) { goto out; } if (strict & RT6_LOOKUP_F_REACHABLE) rt6_probe(nh); /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { *do_rr = match_do_rr; *mpri = m; rc = true; } out: return rc; } struct fib6_nh_frl_arg { u32 flags; int oif; int strict; int *mpri; bool *do_rr; struct fib6_nh *nh; }; static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_frl_arg *arg = _arg; arg->nh = nh; return find_match(nh, arg->flags, arg->oif, arg->strict, arg->mpri, arg->do_rr); } static void __find_rr_leaf(struct fib6_info *f6i_start, struct fib6_info *nomatch, u32 metric, struct fib6_result *res, struct fib6_info **cont, int oif, int strict, bool *do_rr, int *mpri) { struct fib6_info *f6i; for (f6i = f6i_start; f6i && f6i != nomatch; f6i = rcu_dereference(f6i->fib6_next)) { bool matched = false; struct fib6_nh *nh; if (cont && f6i->fib6_metric != metric) { *cont = f6i; return; } if (fib6_check_expired(f6i)) continue; if (unlikely(f6i->nh)) { struct fib6_nh_frl_arg arg = { .flags = f6i->fib6_flags, .oif = oif, .strict = strict, .mpri = mpri, .do_rr = do_rr }; if (nexthop_is_blackhole(f6i->nh)) { res->fib6_flags = RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->f6i = f6i; res->nh = nexthop_fib6_nh(f6i->nh); return; } if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match, &arg)) { matched = true; nh = arg.nh; } } else { nh = f6i->fib6_nh; if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) matched = true; } if (matched) { res->f6i = f6i; res->nh = nh; res->fib6_flags = f6i->fib6_flags; res->fib6_type = f6i->fib6_type; } } } static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf, struct fib6_info *rr_head, int oif, int strict, bool *do_rr, struct fib6_result *res) { u32 metric = rr_head->fib6_metric; struct fib6_info *cont = NULL; int mpri = -1; __find_rr_leaf(rr_head, NULL, metric, res, &cont, oif, strict, do_rr, &mpri); __find_rr_leaf(leaf, rr_head, metric, res, &cont, oif, strict, do_rr, &mpri); if (res->f6i || !cont) return; __find_rr_leaf(cont, NULL, metric, res, NULL, oif, strict, do_rr, &mpri); } static void rt6_select(struct net *net, struct fib6_node *fn, int oif, struct fib6_result *res, int strict) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct fib6_info *rt0; bool do_rr = false; int key_plen; /* make sure this function or its helpers sets f6i */ res->f6i = NULL; if (!leaf || leaf == net->ipv6.fib6_null_entry) goto out; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) rt0 = leaf; /* Double check to make sure fn is not an intermediate node * and fn->leaf does not points to its child's leaf * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES if (rt0->fib6_src.plen) key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) goto out; find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res); if (do_rr) { struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } out: if (!res->f6i) { res->f6i = net->ipv6.fib6_null_entry; res->nh = res->f6i->fib6_nh; res->fib6_flags = res->f6i->fib6_flags; res->fib6_type = res->f6i->fib6_type; } } static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res) { return (res->f6i->fib6_flags & RTF_NONEXTHOP) || res->nh->fib_nh_gw_family; } #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) { struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; } /* Sanity check for prefix_len and length */ if (rinfo->length > 3) { return -EINVAL; } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { if (rinfo->length < 2) { return -EINVAL; } } else if (rinfo->prefix_len > 0) { if (rinfo->length < 1) { return -EINVAL; } } pref = rinfo->route_pref; if (pref == ICMPV6_ROUTER_PREF_INVALID) return -EINVAL; lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; else { /* this function is safe */ ipv6_addr_prefix(&prefix_buf, (struct in6_addr *)rinfo->prefix, rinfo->prefix_len); prefix = &prefix_buf; } if (rinfo->prefix_len == 0) rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { ip6_del_rt(net, rt, false); rt = NULL; } if (!rt && lifetime) rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) rt->fib6_flags = RTF_ROUTEINFO | (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); fib6_remove_gc_list(rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); } spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } return 0; } #endif /* * Misc support functions */ /* called with rcu_lock held */ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { /* for copies of local routes, dst->dev needs to be the * device if it is a master device, the master device if * device is enslaved, and the loopback as the default */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) dev = l3mdev_master_dev_rcu(dev); else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which * case we want dev returned to be dev */ } return dev; } static const int fib6_prop[RTN_MAX + 1] = { [RTN_UNSPEC] = 0, [RTN_UNICAST] = 0, [RTN_LOCAL] = 0, [RTN_BROADCAST] = 0, [RTN_ANYCAST] = 0, [RTN_MULTICAST] = 0, [RTN_BLACKHOLE] = -EINVAL, [RTN_UNREACHABLE] = -EHOSTUNREACH, [RTN_PROHIBIT] = -EACCES, [RTN_THROW] = -EAGAIN, [RTN_NAT] = -EINVAL, [RTN_XRESOLVE] = -EINVAL, }; static int ip6_rt_type_to_error(u8 fib6_type) { return fib6_prop[fib6_type]; } static unsigned short fib6_info_dst_flags(struct fib6_info *rt) { unsigned short flags = 0; if (rt->dst_nocount) flags |= DST_NOCOUNT; if (rt->dst_nopolicy) flags |= DST_NOPOLICY; return flags; } static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type) { rt->dst.error = ip6_rt_type_to_error(fib6_type); switch (fib6_type) { case RTN_BLACKHOLE: rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.output = ip6_pkt_prohibit_out; rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: case RTN_UNREACHABLE: default: rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; } } static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; if (res->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, res->fib6_type); return; } rt->dst.error = 0; rt->dst.output = ip6_output; if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; } else { rt->dst.input = ip6_forward; } if (res->nh->fib_nh_lws) { rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws); lwtunnel_set_redirect(&rt->dst); } rt->dst.lastuse = jiffies; } /* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); ip_dst_init_metrics(&rt->dst, from->fib6_metrics); } /* Caller must already hold reference to f6i in result */ static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; const struct net_device *dev = nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; ip6_rt_init_dst(rt, res); rt->rt6i_dst = f6i->fib6_dst; rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; rt->rt6i_flags = res->fib6_flags; if (nh->fib_nh_gw_family) { rt->rt6i_gateway = nh->fib_nh_gw6; rt->rt6i_flags |= RTF_GATEWAY; } rt6_set_from(rt, f6i); #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = f6i->fib6_src; #endif } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; pn = rcu_dereference(fn->parent); sn = FIB6_SUBTREE(pn); if (sn && sn != fn) fn = fib6_node_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) return fn; } } static bool ip6_hold_safe(struct net *net, struct rt6_info **prt) { struct rt6_info *rt = *prt; if (dst_hold_safe(&rt->dst)) return true; if (net) { rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); } else { rt = NULL; } *prt = rt; return false; } /* called with rcu_lock held */ static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; unsigned short flags; struct rt6_info *nrt; if (!fib6_info_hold_safe(f6i)) goto fallback; flags = fib6_info_dst_flags(f6i); nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (!nrt) { fib6_info_release(f6i); goto fallback; } ip6_rt_copy_init(nrt, res); return nrt; fallback: nrt = dev_net(dev)->ipv6.ip6_null_entry; dst_hold(&nrt->dst); return nrt; } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct fib6_node *fn; struct rt6_info *rt; rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: res.f6i = rcu_dereference(fn->leaf); if (!res.f6i) res.f6i = net->ipv6.fib6_null_entry; else rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif, flags); if (res.f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); goto out; } else if (res.fib6_flags & RTF_REJECT) { goto do_create; } fib6_select_path(net, &res, fl6, fl6->flowi6_oif, fl6->flowi6_oif != 0, skb, flags); /* Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { if (ip6_hold_safe(net, &rt)) dst_use_noref(&rt->dst, jiffies); } else { do_create: rt = ip6_create_rt_rcu(&res); } out: trace_fib6_table_lookup(net, &res, table, fl6); rcu_read_unlock(); return rt; } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, .daddr = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; if (saddr) { memcpy(&fl6.saddr, saddr, sizeof(*saddr)); flags |= RT6_LOOKUP_F_HAS_SADDR; } dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return dst_rt6_info(dst); dst_release(dst); return NULL; } EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. * It takes new route entry, the addition fails by any reason the * route is released. * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } int ip6_ins_rt(struct net *net, struct fib6_info *rt) { struct nl_info info = { .nl_net = net, }; return __ip6_ins_rt(rt, &info, NULL); } static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_info *f6i = res->f6i; struct net_device *dev; struct rt6_info *rt; /* * Clone the route. */ if (!fib6_info_hold_safe(f6i)) return NULL; dev = ip6_rt_get_dev_rcu(res); rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(rt, res); rt->rt6i_flags |= RTF_CACHE; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(res)) { if (f6i->fib6_dst.plen != 128 && ipv6_addr_equal(&f6i->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif } return rt; } static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; unsigned short flags = fib6_info_dst_flags(f6i); struct net_device *dev; struct rt6_info *pcpu_rt; if (!fib6_info_hold_safe(f6i)) return NULL; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(res); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags | DST_NOCOUNT); rcu_read_unlock(); if (!pcpu_rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; if (f6i->nh) pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); return pcpu_rt; } static bool rt6_is_valid(const struct rt6_info *rt6) { return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); } /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { struct rt6_info *pcpu_rt; pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); dst_release(&prev->dst); } pcpu_rt = NULL; } return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct net *net, const struct fib6_result *res) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(res); if (!pcpu_rt) return NULL; p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); if (res->f6i->fib6_destroying) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } return pcpu_rt; } /* exception hash table implementation */ static DEFINE_SPINLOCK(rt6_exception_lock); /* Remove rt6_ex from hash table and free the memory * Caller must hold rt6_exception_lock */ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); net->ipv6.rt6_stats->fib_rt_cache--; /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ dst_dev_put(&rt6_ex->rt6i->dst); hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; } /* Remove oldest rt6_ex in bucket and free the memory * Caller must hold rt6_exception_lock */ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) { struct rt6_exception *rt6_ex, *oldest = NULL; if (!bucket) return; hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) oldest = rt6_ex; } rt6_remove_exception(bucket, oldest); } static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { static siphash_aligned_key_t rt6_exception_key; struct { struct in6_addr dst; struct in6_addr src; } __aligned(SIPHASH_ALIGNMENT) combined = { .dst = *dst, }; u64 val; net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) combined.src = *src; #endif val = siphash(&combined, sizeof(combined), &rt6_exception_key); return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rt6_exception_lock */ static struct rt6_exception * __rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rcu_read_lock() */ static struct rt6_exception * __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; WARN_ON_ONCE(!rcu_read_lock_held()); if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } static unsigned int fib6_mtu(const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; unsigned int mtu; if (res->f6i->fib6_pmtu) { mtu = res->f6i->fib6_pmtu; } else { struct net_device *dev = nh->fib_nh_dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } #define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL /* used when the flushed bit is not relevant, only access to the bucket * (ie., all bucket users except rt6_insert_exception); * * called under rcu lock; sometimes called with rt6_exception_lock held */ static struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; if (lock) bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); else bucket = rcu_dereference(nh->rt6i_exception_bucket); /* remove bucket flushed bit if set */ if (bucket) { unsigned long p = (unsigned long)bucket; p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; } return bucket; } static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket) { unsigned long p = (unsigned long)bucket; return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED); } /* called with rt6_exception_lock held */ static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; unsigned long p; bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); p = (unsigned long)bucket; p |= FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } static int rt6_insert_exception(struct rt6_info *nrt, const struct fib6_result *res) { struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct fib6_info *f6i = res->f6i; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); if (!bucket) { bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), GFP_ATOMIC); if (!bucket) { err = -ENOMEM; goto out; } rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } else if (fib6_nh_excptn_bucket_flushed(bucket)) { err = -EINVAL; goto out; } #ifdef CONFIG_IPV6_SUBTREES /* fib6_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * Otherwise, the exception table is indexed by * a hash of only fib6_dst. */ if (f6i->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* rt6_mtu_change() might lower mtu on f6i. * Only insert this exception route if its mtu * is less than f6i's mtu value. */ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) { err = -EINVAL; goto out; } rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_remove_exception(bucket, rt6_ex); rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); if (!rt6_ex) { err = -ENOMEM; goto out; } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; /* Randomize max depth to avoid some side channels attacks. */ max_depth = FIB6_MAX_DEPTH + get_random_u32_below(FIB6_MAX_DEPTH); while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: spin_unlock_bh(&rt6_exception_lock); /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) goto out; /* Prevent rt6_insert_exception() to recreate the bucket list */ if (!from) fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock); for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { if (!from || rcu_access_pointer(rt6_ex->rt6i->from) == from) rt6_remove_exception(bucket, rt6_ex); } WARN_ON_ONCE(!from && bucket->depth); bucket++; } out: spin_unlock_bh(&rt6_exception_lock); } static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_info *f6i = arg; fib6_nh_flush_exceptions(nh, f6i); return 0; } void rt6_flush_exceptions(struct fib6_info *f6i) { if (f6i->nh) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i); else fib6_nh_flush_exceptions(f6i->fib6_nh, f6i); } /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct rt6_info *ret = NULL; #ifdef CONFIG_IPV6_SUBTREES /* fib6i_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * However, the src addr used to create the hash * might not be exactly the passed in saddr which * is a /128 addr from the flow. * So we need to use f6i->fib6_src to redo lookup * if the passed in saddr does not find anything. * (See the logic in ip6_rt_cache_alloc() on how * rt->rt6i_src is updated.) */ if (res->f6i->fib6_src.plen) src_key = saddr; find_ex: #endif bucket = fib6_nh_get_excptn_bucket(res->nh, NULL); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) ret = rt6_ex->rt6i; #ifdef CONFIG_IPV6_SUBTREES /* Use fib6_src as src_key and redo lookup */ if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) { src_key = &res->f6i->fib6_src.addr; goto find_ex; } #endif return ret; } /* Remove the passed in cached rt from the hash table that contains it */ static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int err; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return -ENOENT; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) { rt6_remove_exception(bucket, rt6_ex); err = 0; } else { err = -ENOENT; } spin_unlock_bh(&rt6_exception_lock); return err; } struct fib6_nh_excptn_arg { struct rt6_info *rt; int plen; }; static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_excptn_arg *arg = _arg; int err; err = fib6_nh_remove_exception(nh, arg->plen, arg->rt); if (err == 0) return 1; return 0; } static int rt6_remove_exception_rt(struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; if (from->nh) { struct fib6_nh_excptn_arg arg = { .rt = rt, .plen = from->fib6_src.plen }; int rc; /* rc = 1 means an entry was found */ rc = nexthop_for_each_fib6_nh(from->nh, rt6_nh_remove_exception_rt, &arg); return rc ? 0 : -ENOENT; } return fib6_nh_remove_exception(from->fib6_nh, from->fib6_src.plen, rt); } /* Find rt6_ex which contains the passed in rt cache and * refresh its stamp */ static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; bucket = fib6_nh_get_excptn_bucket(nh, NULL); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_ex->stamp = jiffies; } struct fib6_nh_match_arg { const struct net_device *dev; const struct in6_addr *gw; struct fib6_nh *match; }; /* determine if fib6_nh has given device and gateway */ static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_match_arg *arg = _arg; if (arg->dev != nh->fib_nh_dev || (arg->gw && !nh->fib_nh_gw_family) || (!arg->gw && nh->fib_nh_gw_family) || (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6))) return 0; arg->match = nh; /* found a match, break the loop */ return 1; } static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct fib6_info *from; struct fib6_nh *fib6_nh; rcu_read_lock(); from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) goto unlock; if (from->nh) { struct fib6_nh_match_arg arg = { .dev = rt->dst.dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; } fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt); unlock: rcu_read_unlock(); } static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { /* If the new MTU is lower than the route PMTU, this new MTU will be the * lowest MTU in the path: always allow updating the route PMTU to * reflect PMTU decreases. * * If the new MTU is higher, and the route PMTU is equal to the local * MTU, this means the old MTU is the lowest in the path, so allow * updating it: if other nodes now have lower MTUs, PMTU discovery will * handle this. */ if (dst_mtu(&rt->dst) >= mtu) return true; if (dst_mtu(&rt->dst) == idev->cnf.mtu6) return true; return false; } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, const struct fib6_nh *nh, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i; bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) return; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected * route), the metrics of its rt->from have already * been updated. */ if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } } #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh, const struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY && ipv6_addr_equal(gateway, &entry->rt6i_gateway)) { rt6_remove_exception(bucket, rt6_ex); } } bucket++; } } spin_unlock_bh(&rt6_exception_lock); } static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_info *rt = rt6_ex->rt6i; /* we are pruning and obsoleting aged-out and non gateway exceptions * even if others have still references to them, so that on next * dst_check() such references can be dropped. * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when * expired, independently from their aging, as per RFC 8201 section 4 */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, rt->dst.expires)) { pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } if (rt->rt6i_flags & RTF_GATEWAY) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { pr_debug("purging route %p via non-router but gateway\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } gc_args->more++; } static void fib6_nh_age_exceptions(const struct fib6_nh *nh, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; rcu_read_lock_bh(); spin_lock(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { rt6_age_examine_exception(bucket, rt6_ex, gc_args, now); } bucket++; } } spin_unlock(&rt6_exception_lock); rcu_read_unlock_bh(); } struct fib6_nh_age_excptn_arg { struct fib6_gc_args *gc_args; unsigned long now; }; static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg) { struct fib6_nh_age_excptn_arg *arg = _arg; fib6_nh_age_exceptions(nh, arg->gc_args, arg->now); return 0; } void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now) { if (f6i->nh) { struct fib6_nh_age_excptn_arg arg = { .gc_args = gc_args, .now = now }; nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions, &arg); } else { fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now); } } /* must be called with rcu lock held */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict) { struct fib6_node *fn, *saved_fn; fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; redo_rt6_select: rt6_select(net, fn, oif, res, strict); if (res->f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; else if (strict & RT6_LOOKUP_F_REACHABLE) { /* also consider unreachable route */ strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; } } trace_fib6_table_lookup(net, res, table, fl6); return 0; } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct rt6_info *rt = NULL; int strict = 0; WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) && !rcu_read_lock_held()); strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); fib6_table_lookup(net, table, oif, fl6, &res, strict); if (res.f6i == net->ipv6.fib6_null_entry) goto out; fib6_select_path(net, &res, fl6, oif, false, skb, strict); /*Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { goto out; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !res.nh->fib_nh_gw_family)) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL); if (rt) { /* 1 refcnt is taken during ip6_rt_cache_alloc(). * As rt6_uncached_list_add() does not consume refcnt, * this refcnt is always returned to the caller even * if caller sets RT6_LOOKUP_F_DST_NOREF flag. */ rt6_uncached_list_add(rt); rcu_read_unlock(); return rt; } } else { /* Get a percpu copy */ local_bh_disable(); rt = rt6_get_pcpu_route(&res); if (!rt) rt = rt6_make_pcpu_route(net, &res); local_bh_enable(); } out: if (!rt) rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) ip6_hold_safe(net, &rt); rcu_read_unlock(); return rt; } EXPORT_SYMBOL_GPL(ip6_pol_route); INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *keys, struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; icmph = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmpv6_is_err(icmph->icmp6_type)) goto out; inner_iph = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(*icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; _flkeys = NULL; out: if (_flkeys) { keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; keys->tags.flow_label = _flkeys->tags.flow_label; keys->basic.ip_proto = _flkeys->basic.ip_proto; } else { keys->addrs.v6addrs.src = key_iph->saddr; keys->addrs.v6addrs.dst = key_iph->daddr; keys->tags.flow_label = ip6_flowlabel(key_iph); keys->basic.ip_proto = key_iph->nexthdr; } } static u32 rt6_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 rt6_multipath_custom_hash_fl6(const struct net *net, const struct flowi6 *fl6) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = fl6->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = fl6->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl6->flowi6_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = fl6->fl6_sport; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } else { hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.ports.src = fl6->fl6_sport; hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { struct flow_keys keys; if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, 0); flkeys = &keys; } /* Inner can be v4 or v6 */ if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; } else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.tags.flow_label = flkeys->tags.flow_label; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = rt6_multipath_custom_hash_skb(net, skb); else mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } return mhash >> 1; } /* Called with rcu held */ void ip6_route_input(struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) flkeys = &_flkeys; if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } static struct dst_entry *ip6_route_output_flags_noref(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { bool any_src; if (ipv6_addr_type(&fl6->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) { struct dst_entry *dst; /* This function does not take refcnt on the dst */ dst = l3mdev_link_scope_lookup(net, fl6); if (dst) return dst; } fl6->flowi6_iif = LOOPBACK_IFINDEX; flags |= RT6_LOOKUP_F_DST_NOREF; any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(READ_ONCE(inet6_sk(sk)->srcprefs)); return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { struct dst_entry *dst; struct rt6_info *rt6; rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; dst_hold(dst); } rcu_read_unlock(); return dst; } EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif } dst_release(dst_orig); return new ? new : ERR_PTR(-ENOMEM); } /* * Destination cache support functions */ static bool fib6_check(struct fib6_info *f6i, u32 cookie) { u32 rt_cookie = 0; if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) return false; if (fib6_check_expired(f6i)) return false; return true; } static struct dst_entry *rt6_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { u32 rt_cookie = 0; if (!from || !fib6_get_cookie_safe(from, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) return NULL; return &rt->dst; } static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { if (!__rt6_check_expired(rt) && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && fib6_check(from, cookie)) return &rt->dst; else return NULL; } INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; struct rt6_info *rt; rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ from = rcu_dereference(rt->from); if (from && (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->dst.rt_uncached)))) dst_ret = rt6_dst_from_check(rt, from, cookie); else dst_ret = rt6_check(rt, from, cookie); rcu_read_unlock(); return dst_ret; } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_CACHE) { rcu_read_lock(); if (rt6_check_expired(rt)) { /* rt/dst can not be destroyed yet, * because of rcu_read_lock() */ sk_dst_reset(sk); rt6_remove_exception_rt(rt); } rcu_read_unlock(); return; } sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { rt6_remove_exception_rt(rt); } else { struct fib6_info *from; struct fib6_node *fn; from = rcu_dereference(rt->from); if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); } } static void rt6_update_expires(struct rt6_info *rt0, int timeout) { if (!(rt0->rt6i_flags & RTF_EXPIRES)) { struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt0->from); if (from) rt0->dst.expires = from->expires; rcu_read_unlock(); } dst_set_expires(&rt0->dst, timeout); rt0->rt6i_flags |= RTF_EXPIRES; } static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. * [see also comment in rt6_mtu_change_route()] */ if (iph) { daddr = &iph->daddr; saddr = &iph->saddr; } else if (sk) { daddr = &sk->sk_v6_daddr; saddr = &inet6_sk(sk)->saddr; } else { daddr = NULL; saddr = NULL; } if (confirm_neigh) dst_confirm_neigh(dst, daddr); if (mtu < IPV6_MIN_MTU) return; if (mtu >= dst_mtu(dst)) return; if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); /* update rt6_ex->stamp for cache */ if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct fib6_result res = {}; struct rt6_info *nrt6; rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); if (!res.f6i) goto out_unlock; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst->dev, .gw = &rt6->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ if (!arg.match) goto out_unlock; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } out_unlock: rcu_read_unlock(); } } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = oif, .flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) { int oif = sk->sk_bound_dev_if; struct dst_entry *dst; if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) return; bh_lock_sock(sk); if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ip6_datagram_dst_update(sk, false); bh_unlock_sock(sk); } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { #ifdef CONFIG_IPV6_SUBTREES struct ipv6_pinfo *np = inet6_sk(sk); #endif ip6_dst_store(sk, dst, ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr) ? &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6->saddr, &np->saddr) ? &np->saddr : #endif NULL); } static bool ip6_redirect_nh_match(const struct fib6_result *res, struct flowi6 *fl6, const struct in6_addr *gw, struct rt6_info **ret) { const struct fib6_nh *nh = res->nh; if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family || fl6->flowi6_oif != nh->fib_nh_dev->ifindex) return false; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) { struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) { *ret = rt_cache; return true; } return false; } return true; } struct fib6_nh_rd_arg { struct fib6_result *res; struct flowi6 *fl6; const struct in6_addr *gw; struct rt6_info **ret; }; static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_rd_arg *arg = _arg; arg->res->nh = nh; return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret); } /* Handle redirects */ struct ip6rd_flowi { struct flowi6 fl6; struct in6_addr gateway; }; INDIRECT_CALLABLE_SCOPE struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; struct rt6_info *ret = NULL; struct fib6_result res = {}; struct fib6_nh_rd_arg arg = { .res = &res, .fl6 = fl6, .gw = &rdfl->gateway, .ret = &ret }; struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and * check if the redirect has come from appropriate router. * * RFC 4861 specifies that redirects should only be * accepted if they come from the nexthop to the target. * Due to the way the routes are chosen, this notion * is a bit fuzzy and one might need to check all possible * routes. */ rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { res.f6i = rt; if (fib6_check_expired(rt)) continue; if (rt->fib6_flags & RTF_REJECT) break; if (unlikely(rt->nh)) { if (nexthop_is_blackhole(rt->nh)) continue; /* on match, res->nh is filled in and potentially ret */ if (nexthop_for_each_fib6_nh(rt->nh, fib6_nh_redirect_match, &arg)) goto out; } else { res.nh = rt->fib6_nh; if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret)) goto out; } } if (!rt) rt = net->ipv6.fib6_null_entry; else if (rt->fib6_flags & RTF_REJECT) { ret = net->ipv6.ip6_null_entry; goto out; } if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } res.f6i = rt; res.nh = rt->fib6_nh; out: if (ret) { ip6_hold_safe(net, &ret); } else { res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; ret = ip6_create_rt_rcu(&res); } rcu_read_unlock(); trace_fib6_table_lookup(net, &res, table, fl6); return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; rdfl.fl6 = *fl6; rdfl.gateway = *gateway; return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .flowi6_mark = mark, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .daddr = msg->dest, .saddr = iph->daddr, .flowi6_uid = sock_net_uid(net, NULL), }; dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; unsigned int mtu = dst_mtu(dst); struct net *net = dev_net(dev); mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) mtu = net->ipv6.sysctl.ip6_rt_min_advmss; /* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) mtu = IPV6_MAXPLEN; return mtu; } INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { return ip6_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device * * based on ip6_dst_mtu_forward and exception logic of * rt6_find_cached_rt; called with rcu_read_lock */ u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct fib6_nh *nh = res->nh; struct fib6_info *f6i = res->f6i; struct inet6_dev *idev; struct rt6_info *rt; u32 mtu = 0; if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { mtu = f6i->fib6_pmtu; if (mtu) goto out; } rt = rt6_find_cached_rt(res, daddr, saddr); if (unlikely(rt)) { mtu = dst_metric_raw(&rt->dst, RTAX_MTU); } else { struct net_device *dev = nh->fib_nh_dev; mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); if (idev) mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); out: return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { struct dst_entry *dst; struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); struct net *net = dev_net(dev); if (unlikely(!idev)) return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(net, dev, 0); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); goto out; } rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); /* Add this dst into uncached_list so that rt6_disable_ip() can * do proper release of the net_device */ rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); out: return dst; } static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; unsigned int val; int entries; if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, const struct in6_addr *gw_addr, u32 tbid, int flags, struct fib6_result *res) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, .saddr = cfg->fc_prefsrc, }; struct fib6_table *table; int err; table = fib6_get_table(net, tbid); if (!table) return -EINVAL; if (!ipv6_addr_any(&cfg->fc_prefsrc)) flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; err = fib6_table_lookup(net, table, cfg->fc_ifindex, &fl6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) fib6_select_path(net, res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); return err; } static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; struct fib6_result res = {}; int err; err = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0, &res); if (!err && !(res.fib6_flags & RTF_REJECT) && /* ignore match if it is the default route */ !ipv6_addr_any(&res.f6i->fib6_dst.addr) && (res.fib6_type != RTN_UNICAST || dev != res.nh->fib_nh_dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } return err; } static int ip6_route_check_nh(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev) { const struct in6_addr *gw_addr = &cfg->fc_gateway; struct net_device *dev = _dev ? *_dev : NULL; int flags = RT6_LOOKUP_F_IFACE; struct fib6_result res = {}; int err = -EHOSTUNREACH; if (cfg->fc_table) { err = ip6_nh_lookup_table(net, cfg, gw_addr, cfg->fc_table, flags, &res); /* gw_addr can not require a gateway or resolve to a reject * route. If a device is given, it must match the result. */ if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family || (dev && dev != res.nh->fib_nh_dev)) err = -EHOSTUNREACH; } if (err < 0) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, }; err = fib6_lookup(net, cfg->fc_ifindex, &fl6, &res, flags); if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family) err = -EHOSTUNREACH; if (err) return err; fib6_select_path(net, &res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); } err = 0; if (dev) { if (dev != res.nh->fib_nh_dev) err = -EHOSTUNREACH; } else { *_dev = dev = res.nh->fib_nh_dev; netdev_hold(dev, dev_tracker, GFP_ATOMIC); *idev = in6_dev_get(dev); } return err; } static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev, struct netlink_ext_ack *extack) { const struct in6_addr *gw_addr = &cfg->fc_gateway; int gwa_type = ipv6_addr_type(gw_addr); bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; const struct net_device *dev = *_dev; bool need_addr_check = !dev; int err = -EINVAL; /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() * will return already-added prefix route via interface that * prefix route was assigned to, which might be non-loopback. */ if (dev && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { /* IPv6 strictly inhibits using not link-local * addresses as nexthop address. * Otherwise, router will not able to send redirects. * It is very good, but in some (rare!) circumstances * (SIT, PtP, NBMA NOARP links) it is handy to allow * some exceptions. --ANK * We allow IPv4-mapped nexthops to support RFC4798-type * addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; } rcu_read_lock(); if (cfg->fc_flags & RTNH_F_ONLINK) err = ip6_route_check_nh_onlink(net, cfg, dev, extack); else err = ip6_route_check_nh(net, cfg, _dev, dev_tracker, idev); rcu_read_unlock(); if (err) goto out; } /* reload in case device was changed */ dev = *_dev; err = -EINVAL; if (!dev) { NL_SET_ERR_MSG(extack, "Egress device not specified"); goto out; } else if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Egress device can not be loopback device for this route"); goto out; } /* if we did not check gw_addr above, do so now that the * egress device has been resolved. */ if (need_addr_check && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } err = 0; out: return err; } static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) { if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; #ifdef CONFIG_IPV6_ROUTER_PREF fib6_nh->last_probe = jiffies; #endif if (cfg->fc_is_fdb) { fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; return 0; } err = -ENODEV; if (cfg->fc_ifindex) { dev = netdev_get_by_index(net, cfg->fc_ifindex, dev_tracker, gfp_flags); if (!dev) goto out; idev = in6_dev_get(dev); if (!idev) goto out; } if (cfg->fc_flags & RTNH_F_ONLINK) { if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); goto out; } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } fib6_nh->fib_nh_flags |= RTNH_F_ONLINK; } fib6_nh->fib_nh_weight = 1; /* We cannot add true routes via loopback here, * they would result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { netdev_put(dev, dev_tracker); in6_dev_put(idev); } dev = net->loopback_dev; netdev_hold(dev, dev_tracker, gfp_flags); idev = in6_dev_get(dev); if (!idev) { err = -ENODEV; goto out; } } goto pcpu_alloc; } if (cfg->fc_flags & RTF_GATEWAY) { err = ip6_validate_gw(net, cfg, &dev, dev_tracker, &idev, extack); if (err) goto out; fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; } err = -ENODEV; if (!dev) goto out; if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; } if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = fib_nh_common_init(net, &fib6_nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; pcpu_alloc: fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); if (!fib6_nh->rt6i_pcpu) { err = -ENOMEM; goto out; } fib6_nh->fib_nh_dev = dev; fib6_nh->fib_nh_oif = dev->ifindex; err = 0; out: if (idev) in6_dev_put(idev); if (err) { lwtstate_put(fib6_nh->fib_nh_lws); fib6_nh->fib_nh_lws = NULL; netdev_put(dev, dev_tracker); } return err; } void fib6_nh_release(struct fib6_nh *fib6_nh) { struct rt6_exception_bucket *bucket; rcu_read_lock(); fib6_nh_flush_exceptions(fib6_nh, NULL); bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL); if (bucket) { rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL); kfree(bucket); } rcu_read_unlock(); fib6_nh_release_dsts(fib6_nh); free_percpu(fib6_nh->rt6i_pcpu); fib_nh_common_release(&fib6_nh->nh_common); } void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) { int cpu; if (!fib6_nh->rt6i_pcpu) return; for_each_possible_cpu(cpu) { struct rt6_info *pcpu_rt, **ppcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); pcpu_rt = xchg(ppcpu_rt, NULL); if (pcpu_rt) { dst_dev_put(&pcpu_rt->dst); dst_release(&pcpu_rt->dst); } } } static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_info *rt = NULL; struct nexthop *nh = NULL; struct fib6_table *table; struct fib6_nh *fib6_nh; int err = -EINVAL; int addr_type; /* RTF_PCPU is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_PCPU) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto out; } /* RTF_CACHE is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_CACHE) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); goto out; } if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); goto out; } if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; } if (cfg->fc_src_len > 128) { NL_SET_ERR_MSG(extack, "Invalid source address length"); goto out; } #ifndef CONFIG_IPV6_SUBTREES if (cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Specifying source address requires IPV6_SUBTREES to be enabled"); goto out; } #endif if (cfg->fc_nh_id) { nh = nexthop_find_by_id(net, cfg->fc_nh_id); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto out; } err = fib6_check_nexthop(nh, cfg, extack); if (err) goto out; } err = -ENOBUFS; if (cfg->fc_nlinfo.nlh && !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { table = fib6_get_table(net, cfg->fc_table); if (!table) { pr_warn("NLM_F_CREATE should be specified when creating new route\n"); table = fib6_new_table(net, cfg->fc_table); } } else { table = fib6_new_table(net, cfg->fc_table); } if (!table) goto out; err = -ENOMEM; rt = fib6_info_alloc(gfp_flags, !nh); if (!rt) goto out; rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(rt->fib6_metrics)) { err = PTR_ERR(rt->fib6_metrics); /* Do not leave garbage there. */ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; goto out_free; } if (cfg->fc_flags & RTF_ADDRCONF) rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; rt->fib6_protocol = cfg->fc_protocol; rt->fib6_table = table; rt->fib6_metric = cfg->fc_metric; rt->fib6_type = cfg->fc_type ? : RTN_UNICAST; rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY; ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->fib6_dst.plen = cfg->fc_dst_len; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack); if (err) goto out; fib6_nh = rt->fib6_nh; /* We cannot add true routes via loopback here, they would * result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev, addr_type)) rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; } if (!ipv6_addr_any(&cfg->fc_prefsrc)) { struct net_device *dev = fib6_nh->fib_nh_dev; if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out; } rt->fib6_prefsrc.addr = cfg->fc_prefsrc; rt->fib6_prefsrc.plen = 128; } else rt->fib6_prefsrc.plen = 0; return rt; out: fib6_info_release(rt); return ERR_PTR(err); out_free: ip_fib_metrics_put(rt->fib6_metrics); kfree(rt); return ERR_PTR(err); } int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_info *rt; int err; rt = ip6_route_info_create(cfg, gfp_flags, extack); if (IS_ERR(rt)) return PTR_ERR(rt); err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); fib6_info_release(rt); return err; } static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_table *table; int err; if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: fib6_info_release(rt); return err; } int ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { struct nl_info info = { .nl_net = net, .skip_notify = skip_notify }; return __ip6_del_rt(rt, &info); } static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) goto out_put; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); skb = NULL; } else info->skip_notify = 1; } /* 'rt' points to the first sibling route. If it is not the * leaf, then we do not need to send a notification. Otherwise, * we need to check if the last sibling has a next route or not * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; last_sibling = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); replace_rt = rcu_dereference_protected( last_sibling->fib6_next, lockdep_is_held(&table->tb6_lock)); if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); else call_fib6_multipath_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, rt->fib6_nsiblings, NULL); } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; } } err = fib6_del(rt, info); out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); } return err; } static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) { int rc = -ESRCH; if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) goto out; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) goto out; rc = rt6_remove_exception_rt(rt); out: return rc; } static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt, struct fib6_nh *nh) { struct fib6_result res = { .f6i = rt, .nh = nh, }; struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src); if (rt_cache) return __ip6_del_cached_rt(rt_cache, cfg); return 0; } struct fib6_nh_del_cached_rt_arg { struct fib6_config *cfg; struct fib6_info *f6i; }; static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_del_cached_rt_arg *arg = _arg; int rc; rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh); return rc != -ESRCH ? rc : 0; } static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i) { struct fib6_nh_del_cached_rt_arg arg = { .cfg = cfg, .f6i = f6i }; return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg); } static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); if (!table) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; } rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, &cfg->fc_src, cfg->fc_src_len, !(cfg->fc_flags & RTF_CACHE)); if (fn) { for_each_fib6_node_rt_rcu(fn) { struct fib6_nh *nh; if (rt->nh && cfg->fc_nh_id && rt->nh->id != cfg->fc_nh_id) continue; if (cfg->fc_flags & RTF_CACHE) { int rc = 0; if (rt->nh) { rc = ip6_del_cached_rt_nh(cfg, rt); } else if (cfg->fc_nh_id) { continue; } else { nh = rt->fib6_nh; rc = ip6_del_cached_rt(cfg, rt, nh); } if (rc != -ESRCH) { rcu_read_unlock(); return rc; } continue; } if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; if (rt->nh) { if (!fib6_info_hold_safe(rt)) continue; rcu_read_unlock(); return __ip6_del_rt(rt, &cfg->fc_nlinfo); } if (cfg->fc_nh_id) continue; nh = rt->fib6_nh; if (cfg->fc_ifindex && (!nh->fib_nh_dev || nh->fib_nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6)) continue; if (!fib6_info_hold_safe(rt)) continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) return __ip6_del_rt(rt, &cfg->fc_nlinfo); return __ip6_del_rt_siblings(rt, cfg); } } rcu_read_unlock(); return err; } static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; struct fib6_result res = {}; struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } msg = (struct rd_msg *)icmp6_hdr(skb); if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; } in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; if (READ_ONCE(in6_dev->cnf.forwarding) || !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: * The IP source address of the Redirect MUST be the same as the current * first-hop router for the specified ICMP Destination Address. */ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } lladdr = NULL; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, skb->dev); if (!lladdr) { net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); return; } } rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; } /* Redirect received -> path was valid. * Look, redirects are sent only in response to data packets, * so that this nexthop apparently is reachable. --ANK */ dst_confirm_neigh(&rt->dst, &ipv6_hdr(skb)->saddr); neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; /* * We have finally decided to accept it. */ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); rcu_read_lock(); res.f6i = rcu_dereference(rt->from); if (!res.f6i) goto out; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst->dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev. Should be impossible */ if (!arg.match) goto out; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL); if (!nrt) goto out; nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE; if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, &res)) { dst_release_immediate(&nrt->dst); goto out; } netevent.old = &rt->dst; netevent.new = &nrt->dst; netevent.daddr = &msg->dest; netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: rcu_read_unlock(); neigh_release(neigh); } #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* these routes do not use nexthops */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex) continue; if (!(rt->fib6_flags & RTF_ROUTEINFO) || !rt->fib6_nh->fib_nh_gw_family) continue; if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr)) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { struct fib6_config cfg = { .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; struct fib6_info *rt; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) continue; nh = rt->fib6_nh; if (dev == nh->fib_nh_dev && ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&nh->fib_nh_gw6, addr)) break; } if (rt && !fib6_info_hold_safe(rt)) rt = NULL; rcu_read_unlock(); return rt; } struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); if (table) table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } return rt6_get_dflt_router(net, gwaddr, dev); } static void __rt6_purge_dflt_routers(struct net *net, struct fib6_table *table) { struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct net_device *dev = fib6_info_nh_dev(rt); struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!idev || idev->cnf.accept_ra != 2) && fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt, false); goto restart; } } rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } void rt6_purge_dflt_routers(struct net *net) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) __rt6_purge_dflt_routers(net, table); } } rcu_read_unlock(); } static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) { *cfg = (struct fib6_config){ .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, .fc_flags = rtmsg->rtmsg_flags, .fc_type = rtmsg->rtmsg_type, .fc_nlinfo.nl_net = net, .fc_dst = rtmsg->rtmsg_dst, .fc_src = rtmsg->rtmsg_src, .fc_gateway = rtmsg->rtmsg_gateway, }; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) { struct fib6_config cfg; int err; if (cmd != SIOCADDRT && cmd != SIOCDELRT) return -EINVAL; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtmsg_to_fib6_config(net, rtmsg, &cfg); rtnl_lock(); switch (cmd) { case SIOCADDRT: /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); break; } rtnl_unlock(); return err; } /* * Drop the packet on the floor */ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); int type; if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else idev = ip6_dst_idev(dst); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { SKB_DR_SET(reason, IP_INADDRERRORS); IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } SKB_DR_SET(reason, IP_INNOROUTES); fallthrough; case IPSTATS_MIB_OUTNOROUTES: SKB_DR_OR(reason, IP_OUTNOROUTES); IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; } /* Start over by dropping the dst for l3mdev case */ if (netif_is_l3_master(skb->dev)) skb_dst_drop(skb); icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb_reason(skb, reason); return 0; } static int ip6_pkt_discard(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } /* * Allocate a dst for local (unicast / anycast) address. */ struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL, .fc_ifindex = idev->dev->ifindex, .fc_flags = RTF_UP | RTF_NONEXTHOP, .fc_dst = *addr, .fc_dst_len = 128, .fc_protocol = RTPROT_KERNEL, .fc_nlinfo.nl_net = net, .fc_ignore_dev_down = true, }; struct fib6_info *f6i; if (anycast) { cfg.fc_type = RTN_ANYCAST; cfg.fc_flags |= RTF_ANYCAST; } else { cfg.fc_type = RTN_LOCAL; cfg.fc_flags |= RTF_LOCAL; } f6i = ip6_route_info_create(&cfg, gfp_flags, extack); if (!IS_ERR(f6i)) { f6i->dst_nocount = true; if (!anycast && (READ_ONCE(net->ipv6.devconf_all->disable_policy) || READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; } return f6i; } /* remove deleted ip from prefsrc entries */ struct arg_dev_net_ip { struct net *net; struct in6_addr *addr; }; static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; if (!rt->nh && rt != net->ipv6.fib6_null_entry && ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) && !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; spin_unlock_bh(&rt6_exception_lock); } return 0; } void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); struct arg_dev_net_ip adni = { .net = net, .addr = &ifp->addr, }; fib6_clean_all(net, fib6_remove_prefsrc, &adni); } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) return 0; nh = rt->fib6_nh; if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6)) return -1; /* Further clean up cached routes in exception table. * This is needed because cached route may have a different * gateway than its 'parent' in the case of an ip redirect. */ fib6_nh_exceptions_clean_tohost(nh, gateway); return 0; } void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) { fib6_clean_all(net, fib6_clean_tohost, gateway); } struct arg_netdev_event { const struct net_device *dev; union { unsigned char nh_flags; unsigned long event; }; }; static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } /* only called for fib entries with builtin fib6_nh */ static bool rt6_is_dead(const struct fib6_info *rt) { if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD || (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN && ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev))) return true; return false; } static int rt6_multipath_total_weight(const struct fib6_info *rt) { struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) total += rt->fib6_nh->fib_nh_weight; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) total += iter->fib6_nh->fib_nh_weight; } return total; } static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { *weight += rt->fib6_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound); } static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } void rt6_multipath_rebalance(struct fib6_info *rt) { struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to * make sure upper bounds are assigned from the first sibling * onwards. */ first = rt6_multipath_first_sibling(rt); if (WARN_ON_ONCE(!first)) return; total = rt6_multipath_total_weight(first); rt6_multipath_upper_bound_set(first, total); } static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; struct net *net = dev_net(arg->dev); if (rt != net->ipv6.fib6_null_entry && !rt->nh && rt->fib6_nh->fib_nh_dev == arg->dev) { rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags; fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } return 0; } void rt6_sync_up(struct net_device *dev, unsigned char nh_flags) { struct arg_netdev_event arg = { .dev = dev, { .nh_flags = nh_flags, }, }; if (nh_flags & RTNH_F_DEAD && netif_carrier_ok(dev)) arg.nh_flags |= RTNH_F_LINKDOWN; fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } /* only called for fib entries with inline fib6_nh */ static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) return true; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) return true; return false; } static void rt6_multipath_flush(struct fib6_info *rt) { struct fib6_info *iter; rt->should_flush = 1; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { struct fib6_info *iter; unsigned int dead = 0; if (rt->fib6_nh->fib_nh_dev == down_dev || rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == down_dev || iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; return dead; } static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned char nh_flags) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) rt->fib6_nh->fib_nh_flags |= nh_flags; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) iter->fib6_nh->fib_nh_flags |= nh_flags; } /* called with write lock held for table with rt */ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; struct net *net = dev_net(dev); if (rt == net->ipv6.fib6_null_entry || rt->nh) return 0; switch (arg->event) { case NETDEV_UNREGISTER: return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; if (!rt->fib6_nsiblings) return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: if (rt->fib6_nh->fib_nh_dev != dev || rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } return 0; } void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { struct arg_netdev_event arg = { .dev = dev, { .event = event, }, }; struct net *net = dev_net(dev); if (net->ipv6.sysctl.skip_notify_on_dev_down) fib6_clean_all_skip_notify(net, fib6_ifdown, &arg); else fib6_clean_all(net, fib6_ifdown, &arg); } void rt6_disable_ip(struct net_device *dev, unsigned long event) { rt6_sync_down_dev(dev, event); rt6_uncached_list_flush_dev(dev); neigh_ifdown(&nd_tbl, dev); } struct rt6_mtu_change_arg { struct net_device *dev; unsigned int mtu; struct fib6_info *f6i; }; static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg; struct fib6_info *f6i = arg->f6i; /* For administrative MTU increase, there is no way to discover * IPv6 PMTU increase, so PMTU increase should be updated here. * Since RFC 1981 doesn't include administrative MTU increase * update PMTU increase is a MUST. (i.e. jumbo frame) */ if (nh->fib_nh_dev == arg->dev) { struct inet6_dev *idev = __in6_dev_get(arg->dev); u32 mtu = f6i->fib6_pmtu; if (mtu >= arg->mtu || (mtu < arg->mtu && mtu == idev->cnf.mtu6)) fib6_metric_set(f6i, RTAX_MTU, arg->mtu); spin_lock_bh(&rt6_exception_lock); rt6_exceptions_update_pmtu(idev, nh, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; } static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. We still use this lock to block changes caused by addrconf/ndisc. */ idev = __in6_dev_get(arg->dev); if (!idev) return 0; if (fib6_metric_locked(f6i, RTAX_MTU)) return 0; arg->f6i = f6i; if (f6i->nh) { /* fib6_nh_mtu_change only returns 0, so this is safe */ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change, arg); } return fib6_nh_mtu_change(f6i->fib6_nh, arg); } void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { struct rt6_mtu_change_arg arg = { .dev = dev, .mtu = mtu, }; fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; unsigned int pref; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_tos) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): option not available for IPv6"); goto errout; } *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, .fc_src_len = rtm->rtm_src_len, .fc_flags = RTF_UP, .fc_protocol = rtm->rtm_protocol, .fc_type = rtm->rtm_type, .fc_nlinfo.portid = NETLINK_CB(skb).portid, .fc_nlinfo.nlh = nlh, .fc_nlinfo.nl_net = sock_net(skb->sk), }; if (rtm->rtm_type == RTN_UNREACHABLE || rtm->rtm_type == RTN_BLACKHOLE || rtm->rtm_type == RTN_PROHIBIT || rtm->rtm_type == RTN_THROW) cfg->fc_flags |= RTF_REJECT; if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; if (rtm->rtm_flags & RTM_F_CLONED) cfg->fc_flags |= RTF_CACHE; cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK); if (tb[RTA_NH_ID]) { if (tb[RTA_GATEWAY] || tb[RTA_OIF] || tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); goto errout; } cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]); } if (tb[RTA_GATEWAY]) { cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } if (tb[RTA_VIA]) { NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); goto errout; } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; if (nla_len(tb[RTA_DST]) < plen) goto errout; nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } if (tb[RTA_SRC]) { int plen = (rtm->rtm_src_len + 7) >> 3; if (nla_len(tb[RTA_SRC]) < plen) goto errout; nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } if (tb[RTA_PREFSRC]) cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]); if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_PRIORITY]) cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); if (tb[RTA_METRICS]) { cfg->fc_mx = nla_data(tb[RTA_METRICS]); cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack); if (err < 0) goto errout; } if (tb[RTA_PREF]) { pref = nla_get_u8(tb[RTA_PREF]); if (pref != ICMPV6_ROUTER_PREF_LOW && pref != ICMPV6_ROUTER_PREF_HIGH) pref = ICMPV6_ROUTER_PREF_MEDIUM; cfg->fc_flags |= RTF_PREF(pref); } if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); if (addrconf_finite_timeout(timeout)) { cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); cfg->fc_flags |= RTF_EXPIRES; } } err = 0; errout: return err; } struct rt6_nh { struct fib6_info *fib6_info; struct fib6_config r_cfg; struct list_head next; }; static int ip6_route_info_append(struct net *net, struct list_head *rt6_nh_list, struct fib6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { /* check if fib6_info already exists */ if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return err; } nh = kzalloc(sizeof(*nh), GFP_KERNEL); if (!nh) return -ENOMEM; nh->fib6_info = rt; memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->next, rt6_nh_list); return 0; } static void ip6_route_mpath_notify(struct fib6_info *rt, struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { /* if this is an APPEND route, then rt points to the first route * inserted and rt_last points to last route inserted. Userspace * wants a consistent dump of the route which starts at the first * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ rcu_read_lock(); if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { rt = list_first_or_null_rcu(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) { bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool should_notify = false; struct fib6_info *leaf; struct fib6_node *fn; rcu_read_lock(); fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; leaf = rcu_dereference(fn->leaf); if (!leaf) goto out; if (rt == leaf || (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf))) should_notify = true; out: rcu_read_unlock(); return should_notify; } static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla, struct netlink_ext_ack *extack) { if (nla_len(nla) < sizeof(*gw)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); return -EINVAL; } *gw = nla_get_in6_addr(nla); return 0; } static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct fib6_config r_cfg; struct rtnexthop *rtnh; struct fib6_info *rt; struct rt6_nh *err_nh; struct rt6_nh *nh, *nh_safe; __u16 nlflags; int remaining; int attrlen; int err = 1; int nhn = 0; int replace = (cfg->fc_nlinfo.nlh && (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); LIST_HEAD(rt6_nh_list); nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE; if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); if (err) goto cleanup; r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); /* RTA_ENCAP_TYPE length checked in * lwtunnel_valid_encap_type_attr */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } if (!rt6_qualify_for_ecmp(rt)) { err = -EINVAL; NL_SET_ERR_MSG(extack, "Device only routes can not be added for IPv6 using the multipath API."); fib6_info_release(rt); goto cleanup; } rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(info->nl_net, &rt6_nh_list, rt, &r_cfg); if (err) { fib6_info_release(rt); goto cleanup; } rtnh = rtnh_next(rtnh, &remaining); } if (list_empty(&rt6_nh_list)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops"); return -EINVAL; } /* for add and replace send one notification with all nexthops. * Skip the notification in fib6_add_rt2node and send one with * the full route when done */ info->skip_notify = 1; /* For add and replace, send one notification with all nexthops. For * append, send one notification with all appended nexthops. */ info->skip_notify_kernel = 1; err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, "multipath route replace failed (check consistency of installed routes)"); err_nh = nh; goto add_errout; } /* save reference to last route successfully inserted */ rt_last = nh->fib6_info; /* save reference to first route for notification */ if (!rt_notif) rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: * fib6_add_rt2node() has rejected it; when replacing, old * nexthops have been replaced by first new, the rest should * be added to it. */ if (cfg->fc_nlinfo.nlh) { cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; } nhn++; } /* An in-kernel notification should only be sent in case the new * multipath route is added as the first route in the node, or if * it was appended to it. We pass 'rt_notif' since it is the first * sibling and might allow us to skip some checks in the replace case. */ if (ip6_route_mpath_should_notify(rt_notif)) { enum fib_event_type fib_event; if (rt_notif->fib6_nsiblings != nhn - 1) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_multipath_entry_notifiers(info->nl_net, fib_event, rt_notif, nhn - 1, extack); if (err) { /* Delete all the siblings that were just added */ err_nh = NULL; goto add_errout; } } /* success ... tell user about new route */ ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); goto cleanup; add_errout: /* send notification for routes that were added so that * the delete notifications sent by ip6_route_del are * coherent */ if (rt_notif) ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); /* Delete routes that were already added */ list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } return err; } static int ip6_route_multipath_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; int last_err = 0; int remaining; int attrlen; int err; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); if (err) { last_err = err; goto next_rtnh; } r_cfg.fc_flags |= RTF_GATEWAY; } } err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; next_rtnh: rtnh = rtnh_next(rtnh, &remaining); } return last_err; } static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_nh_id && !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); return -EINVAL; } if (cfg.fc_mp) return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; return ip6_route_del(&cfg, extack); } } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else return ip6_route_add(&cfg, GFP_KERNEL, extack); } /* add the overhead of this fib6_nh to nexthop_len */ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) { int *nexthop_len = arg; *nexthop_len += nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16); /* RTA_GATEWAY */ if (nh->fib_nh_lws) { /* RTA_ENCAP_TYPE */ *nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); /* RTA_ENCAP */ *nexthop_len += nla_total_size(2); } return 0; } static size_t rt6_nlmsg_size(struct fib6_info *f6i) { int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { struct fib6_nh *nh = f6i->fib6_nh; struct fib6_info *sibling; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); rcu_read_lock(); list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } rcu_read_unlock(); } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ + nla_total_size(16) /* RTA_GATEWAY */ + nla_total_size(16) /* RTA_PREFSRC */ + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_IIF */ + nla_total_size(4) /* RTA_OIF */ + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ + nexthop_len; } static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh, unsigned char *flags) { if (nexthop_is_multipath(nh)) { struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (nexthop_mpath_fill_node(skb, nh, AF_INET6)) goto nla_put_failure; nla_nest_end(skb, mp); } else { struct fib6_nh *fib6_nh; fib6_nh = nexthop_fib6_nh(nh); if (fib_nexthop_info(skb, &fib6_nh->nh_common, AF_INET6, flags, false) < 0) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; struct nlmsghdr *nlh; struct rtmsg *rtm; long expires = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; if (rt6) { rt6_dst = &rt6->rt6i_dst; rt6_src = &rt6->rt6i_src; rt6_flags = rt6->rt6i_flags; } else { rt6_dst = &rt->fib6_dst; rt6_src = &rt->fib6_src; rt6_flags = rt->fib6_flags; } rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt6_dst->plen; rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { if (nla_put_in6_addr(skb, RTA_SRC, src)) goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) return 0; if (err < 0) goto nla_put_failure; } else #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ if (rt6) { if (rt6_flags & RTF_GATEWAY && nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) goto nla_put_failure; if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) goto nla_put_failure; if (dst->lwtstate && lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, rt->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) goto nla_put_failure; rcu_read_lock(); list_for_each_entry_rcu(sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) { rcu_read_unlock(); goto nla_put_failure; } } rcu_read_unlock(); nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) goto nla_put_failure; if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } else { if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common, AF_INET6, &nh_flags, false) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } if (!dst) { if (READ_ONCE(rt->offload)) rtm->rtm_flags |= RTM_F_OFFLOAD; if (READ_ONCE(rt->trap)) rtm->rtm_flags |= RTM_F_TRAP; if (READ_ONCE(rt->offload_failed)) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg) { const struct net_device *dev = arg; if (nh->fib_nh_dev == dev) return 1; return 0; } static bool fib6_info_uses_dev(const struct fib6_info *f6i, const struct net_device *dev) { if (f6i->nh) { struct net_device *_dev = (struct net_device *)dev; return !!nexthop_for_each_fib6_nh(f6i->nh, fib6_info_nh_uses_dev, _dev); } if (f6i->fib6_nh->fib_nh_dev == dev) return true; if (f6i->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; list_for_each_entry_safe(sibling, next_sibling, &f6i->fib6_siblings, fib6_siblings) { if (sibling->fib6_nh->fib_nh_dev == dev) return true; } } return false; } struct fib6_nh_exception_dump_walker { struct rt6_rtnl_dump_arg *dump; struct fib6_info *rt; unsigned int flags; unsigned int skip; unsigned int count; }; static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_nh_exception_dump_walker *w = arg; struct rt6_rtnl_dump_arg *dump = w->dump; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i, err; bucket = fib6_nh_get_excptn_bucket(nh, NULL); if (!bucket) return 0; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (w->skip) { w->skip--; continue; } /* Expiration of entries doesn't bump sernum, insertion * does. Removal is triggered by insertion, so we can * rely on the fact that if entries change between two * partial dumps, this node is scanned again completely, * see rt6_insert_exception() and fib6_dump_table(). * * Count expired entries we go through as handled * entries that we'll skip next time, in case of partial * node dump. Otherwise, if entries expire meanwhile, * we'll skip the wrong amount. */ if (rt6_check_expired(rt6_ex->rt6i)) { w->count++; continue; } err = rt6_fill_node(dump->net, dump->skb, w->rt, &rt6_ex->rt6i->dst, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(dump->cb->skb).portid, dump->cb->nlh->nlmsg_seq, w->flags); if (err) return err; w->count++; } bucket++; } return 0; } /* Return -1 if done with node, number of handled routes on partial dump */ int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct fib_dump_filter *filter = &arg->filter; unsigned int flags = NLM_F_MULTI; struct net *net = arg->net; int count = 0; if (rt == net->ipv6.fib6_null_entry) return -1; if ((filter->flags & RTM_F_PREFIX) && !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return -1; } if (filter->filter_set && ((filter->rt_type && rt->fib6_type != filter->rt_type) || (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) || (filter->protocol && rt->fib6_protocol != filter->protocol))) { return -1; } if (filter->filter_set || !filter->dump_routes || !filter->dump_exceptions) { flags |= NLM_F_DUMP_FILTERED; } if (filter->dump_routes) { if (skip) { skip--; } else { if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, flags)) { return 0; } count++; } } if (filter->dump_exceptions) { struct fib6_nh_exception_dump_walker w = { .dump = arg, .rt = rt, .flags = flags, .skip = skip, .count = 0 }; int err; rcu_read_lock(); if (rt->nh) { err = nexthop_for_each_fib6_nh(rt->nh, rt6_nh_dump_exceptions, &w); } else { err = rt6_nh_dump_exceptions(rt->fib6_nh, &w); } rcu_read_unlock(); if (err) return count + w.count; } return -1; } static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_IIF: case RTA_OIF: case RTA_MARK: case RTA_UID: case RTA_SPORT: case RTA_DPORT: case RTA_IP_PROTO: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6 = {}; bool fibmatch; err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0); fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_MARK]) fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); if (tb[RTA_UID]) fl6.flowi6_uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); if (tb[RTA_SPORT]) fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &fl6.flowi6_proto, AF_INET6, extack); if (err) goto errout; } if (iif) { struct net_device *dev; int flags = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) { rcu_read_unlock(); err = -ENODEV; goto errout; } fl6.flowi6_iif = iif; if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; dst = ip6_route_output(net, NULL, &fl6); } rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } if (rt == net->ipv6.ip6_null_entry) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); err = -ENOBUFS; goto errout; } skb_dst_set(skb, &rt->dst); rcu_read_lock(); from = rcu_dereference(rt->from); if (from) { if (fibmatch) err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } else { err = -ENETUNREACH; } rcu_read_unlock(); if (err < 0) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct sk_buff *skb; struct net *net = info->nl_net; u32 seq; int err; err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, event, info->portid, seq, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed) { struct sk_buff *skb; int err; if (READ_ONCE(f6i->offload) == offload && READ_ONCE(f6i->trap) == trap && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload, offload); WRITE_ONCE(f6i->trap, trap); /* 2 means send notifications only if offload_failed was changed. */ if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload_failed, offload_failed); if (!rcu_access_pointer(f6i->fib6_node)) /* The route was removed from the tree, do not send * notification. */ return; if (!net->ipv6.sysctl.fib_notify_on_flag_change) return; skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } EXPORT_SYMBOL(fib6_info_hw_flags_set); static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (!(dev->flags & IFF_LOOPBACK)) return NOTIFY_OK; if (event == NETDEV_REGISTER) { net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry->dst.dev = dev; net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif } else if (event == NETDEV_UNREGISTER && dev->reg_state != NETREG_UNREGISTERED) { /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } return NOTIFY_OK; } /* * /proc */ #ifdef CONFIG_PROC_FS static int rt6_stats_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int delay; int ret; if (!write) return -EINVAL; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } static struct ctl_table ipv6_route_table_template[] = { { .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv6_sysctl_rtcache_flush }, { .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_route_table_template, sizeof(ipv6_route_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.ip6_rt_max_size; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.flush_delay; table[2].extra1 = net; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down; } return table; } size_t ipv6_route_sysctl_table_size(struct net *net) { /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) return 1; return ARRAY_SIZE(ipv6_route_table_template); } #endif static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true); if (!net->ipv6.fib6_null_entry) goto out_ip6_dst_entries; memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template, sizeof(*net->ipv6.fib6_null_entry)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_has_custom_rules = false; net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, sizeof(*net->ipv6.ip6_prohibit_entry), GFP_KERNEL); if (!net->ipv6.ip6_prohibit_entry) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), GFP_KERNEL); if (!net->ipv6.ip6_blk_hole_entry) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_SUBTREES net->ipv6.fib6_routes_require_src = 0; #endif #endif net->ipv6.sysctl.flush_delay = 0; net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: return ret; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_ip6_prohibit_entry: kfree(net->ipv6.ip6_prohibit_entry); out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_fib6_null_entry: kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } static void __net_exit ip6_route_net_exit(struct net *net) { kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif dst_entries_destroy(&net->ipv6.ip6_dst_ops); } static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, sizeof(struct ipv6_route_iter))) return -ENOMEM; if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, rt6_stats_seq_show, NULL)) { remove_proc_entry("ipv6_route", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ipv6_route", net->proc_net); remove_proc_entry("rt6_stats", net->proc_net); #endif } static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, }; static int __net_init ipv6_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv6.peers = bp; return 0; } static void __net_exit ipv6_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv6.peers; net->ipv6.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, }; static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; void __init ip6_route_init_special_entries(void) { /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #endif } #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt) BTF_ID_LIST(btf_fib6_info_id) BTF_ID(struct, fib6_info) static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), }; static struct bpf_iter_reg ipv6_route_reg_info = { .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) { ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id; return bpf_iter_reg_target(&ipv6_route_reg_info); } static void bpf_iter_unregister(void) { bpf_iter_unreg_target(&ipv6_route_reg_info); } #endif #endif static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE, .doit = inet6_rtm_newroute}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE, .doit = inet6_rtm_delroute}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; int __init ip6_route_init(void) { int ret; int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; ret = register_pernet_subsys(&ip6_route_net_ops); if (ret) goto out_register_inetpeer; ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; ret = fib6_init(); if (ret) goto out_register_subsys; ret = xfrm6_init(); if (ret) goto out_fib6_init; ret = fib6_rules_init(); if (ret) goto xfrm6_init; ret = register_pernet_subsys(&ip6_route_net_late_ops); if (ret) goto fib6_rules_init; ret = rtnl_register_many(ip6_route_rtnl_msg_handlers); if (ret < 0) goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); if (ret) goto out_register_late_subsys; #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) ret = bpf_iter_register(); if (ret) goto out_register_late_subsys; #endif #endif for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } out: return ret; out_register_late_subsys: rtnl_unregister_all(PF_INET6); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_init: fib6_rules_cleanup(); xfrm6_init: xfrm6_fini(); out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); out_register_inetpeer: unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; } void ip6_route_cleanup(void) { #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_unregister(); #endif #endif unregister_netdevice_notifier(&ip6_route_dev_notifier); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } |
| 122 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/ptrace.h * * Copyright (C) 1996-2003 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PTRACE_H #define __ASM_PTRACE_H #include <asm/cpufeature.h> #include <uapi/asm/ptrace.h> /* Current Exception Level values, as contained in CurrentEL */ #define CurrentEL_EL1 (1 << 2) #define CurrentEL_EL2 (2 << 2) #define INIT_PSTATE_EL1 \ (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL1h) #define INIT_PSTATE_EL2 \ (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL2h) #include <linux/irqchip/arm-gic-v3-prio.h> #define GIC_PRIO_IRQON GICV3_PRIO_UNMASKED #define GIC_PRIO_IRQOFF GICV3_PRIO_IRQ #define GIC_PRIO_PSR_I_SET GICV3_PRIO_PSR_I_SET /* Additional SPSR bits not exposed in the UABI */ #define PSR_MODE_THREAD_BIT (1 << 0) #define PSR_IL_BIT (1 << 20) /* AArch32-specific ptrace requests */ #define COMPAT_PTRACE_GETREGS 12 #define COMPAT_PTRACE_SETREGS 13 #define COMPAT_PTRACE_GET_THREAD_AREA 22 #define COMPAT_PTRACE_SET_SYSCALL 23 #define COMPAT_PTRACE_GETVFPREGS 27 #define COMPAT_PTRACE_SETVFPREGS 28 #define COMPAT_PTRACE_GETHBPREGS 29 #define COMPAT_PTRACE_SETHBPREGS 30 /* SPSR_ELx bits for exceptions taken from AArch32 */ #define PSR_AA32_MODE_MASK 0x0000001f #define PSR_AA32_MODE_USR 0x00000010 #define PSR_AA32_MODE_FIQ 0x00000011 #define PSR_AA32_MODE_IRQ 0x00000012 #define PSR_AA32_MODE_SVC 0x00000013 #define PSR_AA32_MODE_ABT 0x00000017 #define PSR_AA32_MODE_HYP 0x0000001a #define PSR_AA32_MODE_UND 0x0000001b #define PSR_AA32_MODE_SYS 0x0000001f #define PSR_AA32_T_BIT 0x00000020 #define PSR_AA32_F_BIT 0x00000040 #define PSR_AA32_I_BIT 0x00000080 #define PSR_AA32_A_BIT 0x00000100 #define PSR_AA32_E_BIT 0x00000200 #define PSR_AA32_PAN_BIT 0x00400000 #define PSR_AA32_SSBS_BIT 0x00800000 #define PSR_AA32_DIT_BIT 0x01000000 #define PSR_AA32_Q_BIT 0x08000000 #define PSR_AA32_V_BIT 0x10000000 #define PSR_AA32_C_BIT 0x20000000 #define PSR_AA32_Z_BIT 0x40000000 #define PSR_AA32_N_BIT 0x80000000 #define PSR_AA32_IT_MASK 0x0600fc00 /* If-Then execution state mask */ #define PSR_AA32_GE_MASK 0x000f0000 #ifdef CONFIG_CPU_BIG_ENDIAN #define PSR_AA32_ENDSTATE PSR_AA32_E_BIT #else #define PSR_AA32_ENDSTATE 0 #endif /* AArch32 CPSR bits, as seen in AArch32 */ #define COMPAT_PSR_DIT_BIT 0x00200000 /* * These are 'magic' values for PTRACE_PEEKUSR that return info about where a * process is located in memory. */ #define COMPAT_PT_TEXT_ADDR 0x10000 #define COMPAT_PT_DATA_ADDR 0x10004 #define COMPAT_PT_TEXT_END_ADDR 0x10008 /* * If pt_regs.syscallno == NO_SYSCALL, then the thread is not executing * a syscall -- i.e., its most recent entry into the kernel from * userspace was not via SVC, or otherwise a tracer cancelled the syscall. * * This must have the value -1, for ABI compatibility with ptrace etc. */ #define NO_SYSCALL (-1) #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/types.h> #include <asm/stacktrace/frame.h> /* sizeof(struct user) for AArch32 */ #define COMPAT_USER_SZ 296 /* Architecturally defined mapping between AArch32 and AArch64 registers */ #define compat_usr(x) regs[(x)] #define compat_fp regs[11] #define compat_sp regs[13] #define compat_lr regs[14] #define compat_sp_hyp regs[15] #define compat_lr_irq regs[16] #define compat_sp_irq regs[17] #define compat_lr_svc regs[18] #define compat_sp_svc regs[19] #define compat_lr_abt regs[20] #define compat_sp_abt regs[21] #define compat_lr_und regs[22] #define compat_sp_und regs[23] #define compat_r8_fiq regs[24] #define compat_r9_fiq regs[25] #define compat_r10_fiq regs[26] #define compat_r11_fiq regs[27] #define compat_r12_fiq regs[28] #define compat_sp_fiq regs[29] #define compat_lr_fiq regs[30] static inline unsigned long compat_psr_to_pstate(const unsigned long psr) { unsigned long pstate; pstate = psr & ~COMPAT_PSR_DIT_BIT; if (psr & COMPAT_PSR_DIT_BIT) pstate |= PSR_AA32_DIT_BIT; return pstate; } static inline unsigned long pstate_to_compat_psr(const unsigned long pstate) { unsigned long psr; psr = pstate & ~PSR_AA32_DIT_BIT; if (pstate & PSR_AA32_DIT_BIT) psr |= COMPAT_PSR_DIT_BIT; return psr; } /* * This struct defines the way the registers are stored on the stack during an * exception. struct user_pt_regs must form a prefix of struct pt_regs. */ struct pt_regs { union { struct user_pt_regs user_regs; struct { u64 regs[31]; u64 sp; u64 pc; u64 pstate; }; }; u64 orig_x0; s32 syscallno; u32 pmr; u64 sdei_ttbr1; struct frame_record_meta stackframe; /* Only valid for some EL1 exceptions. */ u64 lockdep_hardirqs; u64 exit_rcu; }; /* For correct stack alignment, pt_regs has to be a multiple of 16 bytes. */ static_assert(IS_ALIGNED(sizeof(struct pt_regs), 16)); static inline bool in_syscall(struct pt_regs const *regs) { return regs->syscallno != NO_SYSCALL; } static inline void forget_syscall(struct pt_regs *regs) { regs->syscallno = NO_SYSCALL; } #define MAX_REG_OFFSET offsetof(struct pt_regs, pstate) #define arch_has_single_step() (1) #ifdef CONFIG_COMPAT #define compat_thumb_mode(regs) \ (((regs)->pstate & PSR_AA32_T_BIT)) #else #define compat_thumb_mode(regs) (0) #endif #define user_mode(regs) \ (((regs)->pstate & PSR_MODE_MASK) == PSR_MODE_EL0t) #define compat_user_mode(regs) \ (((regs)->pstate & (PSR_MODE32_BIT | PSR_MODE_MASK)) == \ (PSR_MODE32_BIT | PSR_MODE_EL0t)) #define processor_mode(regs) \ ((regs)->pstate & PSR_MODE_MASK) #define irqs_priority_unmasked(regs) \ (system_uses_irq_prio_masking() ? \ (regs)->pmr == GIC_PRIO_IRQON : \ true) #define interrupts_enabled(regs) \ (!((regs)->pstate & PSR_I_BIT) && irqs_priority_unmasked(regs)) #define fast_interrupts_enabled(regs) \ (!((regs)->pstate & PSR_F_BIT)) static inline unsigned long user_stack_pointer(struct pt_regs *regs) { if (compat_user_mode(regs)) return regs->compat_sp; return regs->sp; } extern int regs_query_register_offset(const char *name); extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten * @offset: offset of the register. * * regs_get_register returns the value of a register whose offset from @regs. * The @offset is the offset of the register in struct pt_regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset) { u64 val = 0; WARN_ON(offset & 7); offset >>= 3; switch (offset) { case 0 ... 30: val = regs->regs[offset]; break; case offsetof(struct pt_regs, sp) >> 3: val = regs->sp; break; case offsetof(struct pt_regs, pc) >> 3: val = regs->pc; break; case offsetof(struct pt_regs, pstate) >> 3: val = regs->pstate; break; default: val = 0; } return val; } /* * Read a register given an architectural register index r. * This handles the common case where 31 means XZR, not SP. */ static inline unsigned long pt_regs_read_reg(const struct pt_regs *regs, int r) { return (r == 31) ? 0 : regs->regs[r]; } /* * Write a register given an architectural register index r. * This handles the common case where 31 means XZR, not SP. */ static inline void pt_regs_write_reg(struct pt_regs *regs, int r, unsigned long val) { if (r != 31) regs->regs[r] = val; } /* Valid only for Kernel mode traps. */ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline unsigned long regs_return_value(struct pt_regs *regs) { unsigned long val = regs->regs[0]; /* * Audit currently uses regs_return_value() instead of * syscall_get_return_value(). Apply the same sign-extension here until * audit is updated to use syscall_get_return_value(). */ if (compat_user_mode(regs)) val = sign_extend64(val, 31); return val; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->regs[0] = rc; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * * Note that this chooses the most likely register mapping. In very rare * cases this may not return correct data, for example, if one of the * function parameters is 16 bytes or bigger. In such cases, we cannot * get access the parameter correctly and the register assignment of * subsequent parameters will be shifted. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { #define NR_REG_ARGUMENTS 8 if (n < NR_REG_ARGUMENTS) return pt_regs_read_reg(regs, n); return 0; } /* We must avoid circular header include via sched.h */ struct task_struct; int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); static inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->pc; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->pc = val; } static inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->regs[29]; } #define procedure_link_pointer(regs) ((regs)->regs[30]) static inline void procedure_link_pointer_set(struct pt_regs *regs, unsigned long val) { procedure_link_pointer(regs) = val; } extern unsigned long profile_pc(struct pt_regs *regs); #endif /* __ASSEMBLY__ */ #endif |
| 225 224 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset); static void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 /* Reclaim directly, bypass the slot cache and don't touch device lock */ #define TTRS_DIRECT 0x8 static bool swap_is_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct address_space *address_space = swap_address_space(entry); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; folio = filemap_get_folio(address_space, swap_cache_index(entry)); if (IS_ERR(folio)) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; /* offset could point to the middle of a large folio */ entry = folio->swap; offset = swp_offset(entry); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = lock_cluster_or_swap_info(si, offset); need_reclaim = swap_is_has_cache(si, offset, nr_pages); unlock_cluster_or_swap_info(si, ci); if (!need_reclaim) goto out_unlock; if (!(flags & TTRS_DIRECT)) { /* Free through slot cache */ delete_from_swap_cache(folio); folio_set_dirty(folio); ret = nr_pages; goto out_unlock; } xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(folio, entry, NULL); xa_unlock_irq(&address_space->i_pages); folio_ref_sub(folio, nr_pages); folio_set_dirty(folio); spin_lock(&si->lock); /* Only sinple page folio can be backed by zswap */ if (nr_pages == 1) zswap_invalidate(entry); swap_entry_range_free(si, entry, nr_pages); spin_unlock(&si->lock); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = swp_swap_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { unsigned int idx = cluster_index(si, ci); /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); list_move_tail(&ci->list, &si->discard_clusters); ci->flags = 0; schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); if (ci->flags) list_move_tail(&ci->list, &si->free_clusters); else list_add_tail(&ci->list, &si->free_clusters); ci->flags = CLUSTER_FLAG_FREE; ci->order = 0; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; unsigned int idx; while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); spin_lock(&ci->lock); __free_cluster(si, ci); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); spin_unlock(&ci->lock); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static void inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; if (!cluster_info) return; ci = cluster_info + idx; ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); } /* * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0, * which means no page in the cluster is in use, we can optionally discard * the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *ci, int nr_pages) { if (!si->cluster_info) return; VM_BUG_ON(ci->count < nr_pages); VM_BUG_ON(cluster_is_free(ci)); lockdep_assert_held(&si->lock); lockdep_assert_held(&ci->lock); ci->count -= nr_pages; if (!ci->count) { free_cluster(si, ci); return; } if (!(ci->flags & CLUSTER_FLAG_NONFULL)) { VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &si->nonfull_clusters[ci->order]); ci->flags = CLUSTER_FLAG_NONFULL; } } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset; spin_unlock(&ci->lock); spin_unlock(&si->lock); for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0) continue; goto out; default: goto out; } } out: spin_lock(&si->lock); spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; bool need_reclaim = false; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; need_reclaim = true; continue; default: return false; } } if (need_reclaim) return cluster_reclaim_range(si, ci, start, end); return true; } static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; if (!(si->flags & SWP_WRITEOK)) return false; if (cluster_is_free(ci)) { if (nr_pages < SWAPFILE_CLUSTER) { list_move_tail(&ci->list, &si->nonfull_clusters[order]); ci->flags = CLUSTER_FLAG_NONFULL; } ci->order = order; } memset(si->swap_map + start, usage, nr_pages); swap_range_alloc(si, start, nr_pages); ci->count += nr_pages; if (ci->count == SWAPFILE_CLUSTER) { VM_BUG_ON(!(ci->flags & (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG))); if (ci->flags & CLUSTER_FLAG_FRAG) si->frag_cluster_nr[ci->order]--; list_move_tail(&ci->list, &si->full_clusters); ci->flags = CLUSTER_FLAG_FULL; } return true; } static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset, unsigned int *foundp, unsigned int order, unsigned char usage) { unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; struct swap_cluster_info *ci; if (end < nr_pages) return SWAP_NEXT_INVALID; end -= nr_pages; ci = lock_cluster(si, offset); if (ci->count + nr_pages > SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; goto done; } while (offset <= end) { if (cluster_scan_range(si, ci, offset, nr_pages)) { if (!cluster_alloc_range(si, ci, offset, usage, order)) { offset = SWAP_NEXT_INVALID; goto done; } *foundp = offset; if (ci->count == SWAPFILE_CLUSTER) { offset = SWAP_NEXT_INVALID; goto done; } offset += nr_pages; break; } offset += nr_pages; } if (offset > end) offset = SWAP_NEXT_INVALID; done: unlock_cluster(ci); return offset; } /* Return true if reclaimed a whole cluster */ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim; if (force) to_scan = si->inuse_pages / SWAPFILE_CLUSTER; while (!list_empty(&si->full_clusters)) { ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list); list_move_tail(&ci->list, &si->full_clusters); offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; spin_unlock(&si->lock); while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } spin_lock(&si->lock); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); spin_lock(&si->lock); swap_reclaim_full_clusters(si, true); spin_unlock(&si->lock); } /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU * too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned int offset, found = 0; new_cluster: lockdep_assert_held(&si->lock); cluster = this_cpu_ptr(si->percpu_cluster); offset = cluster->next[order]; if (offset) { offset = alloc_swap_scan_cluster(si, offset, &found, order, usage); if (found) goto done; } if (!list_empty(&si->free_clusters)) { ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); /* * Either we didn't touch the cluster due to swapoff, * or the allocation must success. */ VM_BUG_ON((si->flags & SWP_WRITEOK) && !found); goto done; } /* Try reclaim from full clusters if free clusters list is drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { unsigned int frags = 0; while (!list_empty(&si->nonfull_clusters[order])) { ci = list_first_entry(&si->nonfull_clusters[order], struct swap_cluster_info, list); list_move_tail(&ci->list, &si->frag_clusters[order]); ci->flags = CLUSTER_FLAG_FRAG; si->frag_cluster_nr[order]++; offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); frags++; if (found) break; } if (!found) { /* * Nonfull clusters are moved to frag tail if we reached * here, count them too, don't over scan the frag list. */ while (frags < si->frag_cluster_nr[order]) { ci = list_first_entry(&si->frag_clusters[order], struct swap_cluster_info, list); /* * Rotate the frag list to iterate, they were all failing * high order allocation or moved here due to per-CPU usage, * this help keeping usable cluster ahead. */ list_move_tail(&ci->list, &si->frag_clusters[order]); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage); frags++; if (found) break; } } } if (found) goto done; if (!list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); goto new_cluster; } if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ while (!list_empty(&si->frag_clusters[o])) { ci = list_first_entry(&si->frag_clusters[o], struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); if (found) goto done; } while (!list_empty(&si->nonfull_clusters[o])) { ci = list_first_entry(&si->nonfull_clusters[o], struct swap_cluster_info, list); offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, 0, usage); if (found) goto done; } } done: cluster->next[order] = offset; return found; } static void __del_from_avail_list(struct swap_info_struct *si) { int nid; assert_spin_locked(&si->lock); for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *si) { spin_lock(&swap_avail_lock); __del_from_avail_list(si); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); if (si->cluster_info && vm_swap_full()) schedule_work(&si->reclaim_work); } } static void add_to_avail_list(struct swap_info_struct *si) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) clear_bit(offset + i, si->zeromap); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static bool swap_offset_available_and_locked(struct swap_info_struct *si, unsigned long offset) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); return true; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); return true; } return false; } static int cluster_alloc_swap(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { int n_ret = 0; VM_BUG_ON(!si->cluster_info); si->flags += SWP_SCANNING; while (n_ret < nr) { unsigned long offset = cluster_alloc_swap_entry(si, order, usage); if (!offset) break; slots[n_ret++] = swp_entry(si->type, offset); } si->flags -= SWP_SCANNING; return n_ret; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; unsigned int nr_pages = 1 << order; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ if (order > 0) { /* * Should not even be attempting large allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP) || nr_pages > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return 0; } /* * Swapfile is not block device or not using clusters so unable * to allocate large entries. */ if (!(si->flags & SWP_BLKDEV) || !si->cluster_info) return 0; } if (si->cluster_info) return cluster_alloc_swap(si, usage, nr, slots, order); si->flags += SWP_SCANNING; /* For HDD, sequential access is more important. */ scan_base = si->cluster_next; offset = scan_base; if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed > 0) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { if (!n_ret) goto scan; else goto done; } memset(si->swap_map + offset, usage, nr_pages); swap_range_alloc(si, offset, nr_pages); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: if (order == 0) set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: VM_WARN_ON(order > 0); spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; } offset = si->lowest_bit; while (offset < scan_base) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) { int order = swap_entry_order(entry_order); unsigned long size = 1 << order; struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries, order); spin_unlock(&si->lock); if (n_ret || size > 1) goto check_out; cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *si, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else WRITE_ONCE(si->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(si, offset); usage = __swap_entry_free_locked(si, offset, 1); unlock_cluster_or_swap_info(si, ci); if (!usage) free_swap_slot(entry); return usage; } static bool __swap_entries_free(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); unsigned int type = swp_type(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1 || swap_count(data_race(si->swap_map[offset])) != 1) goto fallback; /* cross into another cluster */ if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER) goto fallback; ci = lock_cluster_or_swap_info(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { unlock_cluster_or_swap_info(si, ci); goto fallback; } for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); unlock_cluster_or_swap_info(si, ci); if (!has_cache) { for (i = 0; i < nr; i++) zswap_invalidate(swp_entry(si->type, offset + i)); spin_lock(&si->lock); swap_entry_range_free(si, entry, nr); spin_unlock(&si->lock); } return has_cache; fallback: for (i = 0; i < nr; i++) { if (data_race(si->swap_map[offset + i])) { count = __swap_entry_free(si, swp_entry(type, offset + i)); if (count == SWAP_HAS_CACHE) has_cache = true; } else { WARN_ON_ONCE(1); } } return has_cache; } /* * Drop the last HAS_CACHE flag of swap entries, caller have to * ensure all entries belong to the same cgroup. */ static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); do { VM_BUG_ON(*map != SWAP_HAS_CACHE); *map = 0; } while (++map < map_end); dec_cluster_info_page(si, ci, nr_pages); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); } static void cluster_swap_free_nr(struct swap_info_struct *si, unsigned long offset, int nr_pages, unsigned char usage) { struct swap_cluster_info *ci; DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 }; int i, nr; ci = lock_cluster_or_swap_info(si, offset); while (nr_pages) { nr = min(BITS_PER_LONG, nr_pages); for (i = 0; i < nr; i++) { if (!__swap_entry_free_locked(si, offset + i, usage)) bitmap_set(to_free, i, 1); } if (!bitmap_empty(to_free, BITS_PER_LONG)) { unlock_cluster_or_swap_info(si, ci); for_each_set_bit(i, to_free, BITS_PER_LONG) free_swap_slot(swp_entry(si->type, offset + i)); if (nr == nr_pages) return; bitmap_clear(to_free, 0, BITS_PER_LONG); ci = lock_cluster_or_swap_info(si, offset); } offset += nr; nr_pages -= nr; } unlock_cluster_or_swap_info(si, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); cluster_swap_free_nr(sis, offset, nr, 1); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size > 1 && swap_is_has_cache(si, offset, size)) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); swap_entry_range_free(si, entry, size); spin_unlock(&si->lock); return; } for (int i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_range_free(p, entries[i], 1); prev = p; } if (p) spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(si, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; if (non_swap_entry(entry)) return; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = __swap_entries_free(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. This is * more efficient for large folios because we will only try to reclaim * the swap once per folio in the common case. If we do * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the * latter will get a reference and lock the folio for every individual * page but will only succeed once the swap slot for every subpage is * zero. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { si->flags |= SWP_WRITEOK; atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* add to available list iff swap device is not full */ if (si->highest_bit) add_to_avail_list(si); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } bool has_usable_swap(void) { bool ret; spin_lock(&swap_lock); ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(READ_ONCE(si->inuse_pages)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } si->lowest_bit = 1; si->cluster_next = 1; si->cluster_nr = 0; maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } si->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages, sector_t *span) { unsigned int nr_good_pages; unsigned long i; int nr_extents; nr_good_pages = maxpages - 1; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; } } if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; si->max = maxpages; si->pages = nr_good_pages; nr_extents = setup_swap_extents(si, span); if (nr_extents < 0) return nr_extents; nr_good_pages = si->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return nr_extents; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = si->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; struct swap_cluster_info *cluster_info; unsigned long i, j, k, idx; int cpu, err = -ENOMEM; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); si->cluster_next_cpu = alloc_percpu(unsigned int); if (!si->cluster_next_cpu) goto err_free; /* Random start position to help with wear leveling */ for_each_possible_cpu(cpu) per_cpu(*si->cluster_next_cpu, cpu) = get_random_u32_inclusive(1, si->highest_bit); si->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!si->percpu_cluster) goto err_free; for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(si->percpu_cluster, cpu); for (i = 0; i < SWAP_NR_ORDERS; i++) cluster->next[i] = SWAP_NEXT_INVALID; } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map_and_extents(): header page, bad pages, * and the EOF part of the last cluster. */ inc_cluster_info_page(si, cluster_info, 0); for (i = 0; i < swap_header->info.nr_badpages; i++) inc_cluster_info_page(si, cluster_info, swap_header->info.badpages[i]); for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(si, cluster_info, i); INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); si->frag_cluster_nr[i] = 0; } /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { struct swap_cluster_info *ci; idx = i * SWAP_CLUSTER_COLS + j; ci = cluster_info + idx; if (idx >= nr_clusters) continue; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); continue; } ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: kvfree(cluster_info); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = init_swap_address_space(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = zswap_swapon(si->type, maxpages); if (error) goto free_swap_address_space; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); free_swap_address_space: exit_swap_address_space(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(si->percpu_cluster); si->percpu_cluster = NULL; free_percpu(si->cluster_next_cpu); si->cluster_next_cpu = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swp_swap_info(entry); offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = lock_cluster_or_swap_info(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: unlock_cluster_or_swap_info(si, ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return swp_swap_info(folio->swap)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __folio_swap_cache_index(struct folio *folio) { return swap_cache_index(folio->swap); } EXPORT_SYMBOL_GPL(__folio_swap_cache_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 210 211 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. */ /* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #include <linux/kernel_read_file.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/signal.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/perf_event.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> #include <linux/utsname.h> #include <linux/pid_namespace.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> #include <linux/kmod.h> #include <linux/fsnotify.h> #include <linux/fs_struct.h> #include <linux/oom.h> #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> #include <linux/time_namespace.h> #include <linux/user_events.h> #include <linux/rseq.h> #include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlb.h> #include <trace/events/task.h> #include "internal.h" #include <trace/events/sched.h> static int bprm_creds_from_file(struct linux_binprm *bprm); int suid_dumpable = 0; static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt) { write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt) { module_put(fmt->module); } bool path_noexec(const struct path *path) { return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } #ifdef CONFIG_USELIB /* * Note that a shared library must be both readable and executable due to * security reasons. * * Also note that we take the address to load from the file itself. */ SYSCALL_DEFINE1(uselib, const char __user *, library) { struct linux_binfmt *fmt; struct file *file; struct filename *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY, .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if (IS_ERR(tmp)) goto out; file = do_filp_open(AT_FDCWD, tmp, &uselib_flags); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) goto out; /* * Check do_open_execat() for an explanation. */ error = -EACCES; if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || path_noexec(&file->f_path)) goto exit; error = -ENOEXEC; read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!fmt->load_shlib) continue; if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); error = fmt->load_shlib(file); read_lock(&binfmt_lock); put_binfmt(fmt); if (error != -ENOEXEC) break; } read_unlock(&binfmt_lock); exit: fput(file); out: return error; } #endif /* #ifdef CONFIG_USELIB */ #ifdef CONFIG_MMU /* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); if (!mm || !diff) return; bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff); } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; struct vm_area_struct *vma = bprm->vma; struct mm_struct *mm = bprm->mm; int ret; /* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it * by hand ahead of time. */ if (write && pos < vma->vm_start) { mmap_write_lock(mm); ret = expand_downwards(vma, pos); if (unlikely(ret < 0)) { mmap_write_unlock(mm); return NULL; } mmap_write_downgrade(mm); } else mmap_read_lock(mm); /* * We are doing an exec(). 'current' is the process * doing the exec and 'mm' is the new process's mm. */ ret = get_user_pages_remote(mm, pos, 1, write ? FOLL_WRITE : 0, &page, NULL); mmap_read_unlock(mm); if (ret <= 0) return NULL; if (write) acct_arg_size(bprm, vma_pages(vma)); return page; } static void put_arg_page(struct page *page) { put_page(page); } static void free_arg_pages(struct linux_binprm *bprm) { } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { flush_cache_page(bprm->vma, pos, page_to_pfn(page)); } static int __bprm_mm_init(struct linux_binprm *bprm) { int err; struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; vma_set_anonymous(vma); if (mmap_write_lock_killable(mm)) { err = -EINTR; goto err_free; } /* * Need to be called with mmap write lock * held, to avoid race with ksmd. */ err = ksm_execve(mm); if (err) goto err_ksm; /* * Place the stack at the largest stack address the architecture * supports. Later, we'll move this to an appropriate place. We don't * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); err = insert_vm_struct(mm, vma); if (err) goto err; mm->stack_vm = mm->total_vm = 1; mmap_write_unlock(mm); bprm->p = vma->vm_end - sizeof(void *); return 0; err: ksm_exit(mm); err_ksm: mmap_write_unlock(mm); err_free: bprm->vma = NULL; vm_area_free(vma); return err; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= MAX_ARG_STRLEN; } #else static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; } return page; } static void put_arg_page(struct page *page) { } static void free_arg_page(struct linux_binprm *bprm, int i) { if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; } } static void free_arg_pages(struct linux_binprm *bprm) { int i; for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i); } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { } static int __bprm_mm_init(struct linux_binprm *bprm) { bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); return 0; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= bprm->p; } #endif /* CONFIG_MMU */ /* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err; /* Save current stack limit for all calculations made during exec. */ task_lock(current->group_leader); bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader); err = __bprm_mm_init(bprm); if (err) goto err; return 0; err: if (mm) { bprm->mm = NULL; mmdrop(mm); } return err; } struct user_arg_ptr { #ifdef CONFIG_COMPAT bool is_compat; #endif union { const char __user *const __user *native; #ifdef CONFIG_COMPAT const compat_uptr_t __user *compat; #endif } ptr; }; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { const char __user *native; #ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat; if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT); return compat_ptr(compat); } #endif if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); return native; } /* * count() counts the number of strings in array ARGV. */ static int count(struct user_arg_ptr argv, int max) { int i = 0; if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); if (!p) break; if (IS_ERR(p)) return -EFAULT; if (i >= max) return -E2BIG; ++i; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i; } static int count_strings_kernel(const char *const *argv) { int i; if (!argv) return 0; for (i = 0; argv[i]; ++i) { if (i >= MAX_ARG_STRINGS) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return i; } static inline int bprm_set_stack_limit(struct linux_binprm *bprm, unsigned long limit) { #ifdef CONFIG_MMU /* Avoid a pathological bprm->p. */ if (bprm->p < limit) return -E2BIG; bprm->argmin = bprm->p - limit; #endif return 0; } static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm) { #ifdef CONFIG_MMU return bprm->p < bprm->argmin; #else return false; #endif } /* * Calculate bprm->argmin from: * - _STK_LIM * - ARG_MAX * - bprm->rlim_stack.rlim_cur * - bprm->argc * - bprm->envc * - bprm->p */ static int bprm_stack_limits(struct linux_binprm *bprm) { unsigned long limit, ptr_size; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, bprm->rlim_stack.rlim_cur / 4); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); /* Reject totally pathological counts. */ if (bprm->argc < 0 || bprm->envc < 0) return -E2BIG; /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. * * In the case of argc = 0, make sure there is space for adding a * empty string (which will bump argc to 1), to ensure confused * userspace programs don't start processing from argv[1], thinking * argc can never be 0, to keep them from walking envp by accident. * See do_execveat_common(). */ if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) || check_mul_overflow(ptr_size, sizeof(void *), &ptr_size)) return -E2BIG; if (limit <= ptr_size) return -E2BIG; limit -= ptr_size; return bprm_set_stack_limit(bprm, limit); } /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret; while (argc-- > 0) { const char __user *str; int len; unsigned long pos; ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out; len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out; ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out; /* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; if (bprm_hit_stack_limit(bprm)) goto out; while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy; len -= bytes_to_copy; if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page; page = get_arg_page(bprm, pos, 1); if (!page) { ret = -E2BIG; goto out; } if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } } } ret = 0; out: if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret; } /* * Copy and argument/environment string from the kernel to the processes stack. */ int copy_string_kernel(const char *arg, struct linux_binprm *bprm) { int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */; unsigned long pos = bprm->p; if (len == 0) return -EFAULT; if (!valid_arg_len(bprm, len)) return -E2BIG; /* We're going to work our way backwards. */ arg += len; bprm->p -= len; if (bprm_hit_stack_limit(bprm)) return -E2BIG; while (len > 0) { unsigned int bytes_to_copy = min_t(unsigned int, len, min_not_zero(offset_in_page(pos), PAGE_SIZE)); struct page *page; pos -= bytes_to_copy; arg -= bytes_to_copy; len -= bytes_to_copy; page = get_arg_page(bprm, pos, 1); if (!page) return -E2BIG; flush_arg_page(bprm, pos & PAGE_MASK, page); memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy); put_arg_page(page); } return 0; } EXPORT_SYMBOL(copy_string_kernel); static int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm) { while (argc-- > 0) { int ret = copy_string_kernel(argv[argc], bprm); if (ret < 0) return ret; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return 0; } #ifdef CONFIG_MMU /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. */ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { unsigned long ret; unsigned long stack_shift; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = bprm->vma; struct vm_area_struct *prev = NULL; unsigned long vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; struct mmu_gather tlb; struct vma_iterator vmi; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ stack_base = bprm->rlim_stack.rlim_max; stack_base = calc_max_stack_size(stack_base); /* Add space for stack randomization. */ if (current->flags & PF_RANDOMIZE) stack_base += (STACK_RND_MASK << PAGE_SHIFT); /* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) return -ENOMEM; stack_base = PAGE_ALIGN(stack_top - stack_base); stack_shift = vma->vm_start - stack_base; mm->arg_start = bprm->p - stack_shift; bprm->p = vma->vm_end - stack_shift; #else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top); if (unlikely(stack_top < mmap_min_addr) || unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) return -ENOMEM; stack_shift = vma->vm_end - stack_top; bprm->p -= stack_shift; mm->arg_start = bprm->p; #endif if (bprm->loader) bprm->loader -= stack_shift; bprm->exec -= stack_shift; if (mmap_write_lock_killable(mm)) return -EINTR; vm_flags = VM_STACK_FLAGS; /* * Adjust stack execute permissions; explicitly enable for * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone * (arch default) otherwise. */ if (unlikely(executable_stack == EXSTACK_ENABLE_X)) vm_flags |= VM_EXEC; else if (executable_stack == EXSTACK_DISABLE_X) vm_flags &= ~VM_EXEC; vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; vma_iter_init(&vmi, mm, vma->vm_start); tlb_gather_mmu(&tlb, mm); ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); tlb_finish_mmu(&tlb); if (ret) goto out_unlock; BUG_ON(prev != vma); if (unlikely(vm_flags & VM_EXEC)) { pr_warn_once("process '%pD4' started with executable stack\n", bprm->file); } /* Move stack pages down in memory. */ if (stack_shift) { /* * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once * the binfmt code determines where the new stack should reside, we shift it to * its final location. */ ret = relocate_vma_down(vma, stack_shift); if (ret) goto out_unlock; } /* mprotect_fixup is overkill to remove the temporary stack flags */ vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP); stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; /* * Align this down to a page boundary as expand_stack * will align it up. */ rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK; stack_expand = min(rlim_stack, stack_size + stack_expand); #ifdef CONFIG_STACK_GROWSUP stack_base = vma->vm_start + stack_expand; #else stack_base = vma->vm_end - stack_expand; #endif current->mm->start_stack = bprm->p; ret = expand_stack_locked(vma, stack_base); if (ret) ret = -EFAULT; out_unlock: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(setup_arg_pages); #else /* * Transfer the program arguments and environment from the holding pages * onto the stack. The provided stack pointer is adjusted accordingly. */ int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location) { unsigned long index, stop, sp; int ret = 0; stop = bprm->p >> PAGE_SHIFT; sp = *sp_location; for (index = MAX_ARG_PAGES - 1; index >= stop; index--) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; char *src = kmap_local_page(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; kunmap_local(src); if (ret) goto out; } bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: return ret; } EXPORT_SYMBOL(transfer_args_to_stack); #endif /* CONFIG_MMU */ /* * On success, caller must call do_close_execat() on the returned * struct file to close it. */ static struct file *do_open_execat(int fd, struct filename *name, int flags) { int err; struct file *file __free(fput) = NULL; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) open_exec_flags.lookup_flags |= LOOKUP_EMPTY; file = do_filp_open(fd, name, &open_exec_flags); if (IS_ERR(file)) return file; /* * In the past the regular type check was here. It moved to may_open() in * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is * an invariant that all non-regular files error out before we get here. */ if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || path_noexec(&file->f_path)) return ERR_PTR(-EACCES); err = deny_write_access(file); if (err) return ERR_PTR(err); return no_free_ptr(file); } /** * open_exec - Open a path name for execution * * @name: path name to open with the intent of executing it. * * Returns ERR_PTR on failure or allocated struct file on success. * * As this is a wrapper for the internal do_open_execat(), callers * must call allow_write_access() before fput() on release. Also see * do_close_execat(). */ struct file *open_exec(const char *name) { struct filename *filename = getname_kernel(name); struct file *f = ERR_CAST(filename); if (!IS_ERR(filename)) { f = do_open_execat(AT_FDCWD, filename, 0); putname(filename); } return f; } EXPORT_SYMBOL(open_exec); #if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC) ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) { ssize_t res = vfs_read(file, (void __user *)addr, len, &pos); if (res > 0) flush_icache_user_range(addr, addr + len); return res; } EXPORT_SYMBOL(read_code); #endif /* * Maps the mm_struct mm into the current task struct. * On success, this function returns with exec_update_lock * held for writing. */ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); ret = down_write_killable(&tsk->signal->exec_update_lock); if (ret) return ret; if (old_mm) { /* * If there is a pending fatal signal perhaps a signal * whose default action is to create a coredump get * out and die instead of going through with the exec. */ ret = mmap_read_lock_killable(old_mm); if (ret) { up_write(&tsk->signal->exec_update_lock); return ret; } } task_lock(tsk); membarrier_exec_mmap(mm); local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; mm_init_cid(mm, tsk); /* * This prevents preemption while active_mm is being loaded and * it and mm are being updated, which could cause problems for * lazy tlb mm refcounting when these are updated by context * switches. Not all architectures can handle irqs off over * activate_mm yet. */ if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); activate_mm(active_mm, mm); if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); lru_gen_add_mm(mm); task_unlock(tsk); lru_gen_use_mm(mm); if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm); mm_update_next_owner(old_mm); mmput(old_mm); return 0; } mmdrop_lazy_tlb(active_mm); return 0; } static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. */ spin_lock_irq(lock); if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); return -EAGAIN; } sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; while (sig->notify_count) { __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); if (__fatal_signal_pending(tsk)) goto killed; spin_lock_irq(lock); } spin_unlock_irq(lock); /* * At this point all other threads have exited, all we have to * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader; for (;;) { cgroup_threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); schedule(); if (__fatal_signal_pending(tsk)) goto killed; } /* * The only record we have of the real-time age of a * process, regardless of execs it's done, is start_time. * All the past CPU time is accumulated in signal_struct * from sister threads now dead. But in this non-leader * exec, nothing survives from the original leader thread, * whose birth marks the true age of this process now. * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; tsk->start_boottime = leader->start_boottime; BUG_ON(!same_thread_group(leader, tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */ /* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. */ exchange_tids(tsk, leader); transfer_pid(leader, tsk, PIDTYPE_TGID); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); list_replace_rcu(&leader->tasks, &tsk->tasks); list_replace_init(&leader->sibling, &tsk->sibling); tsk->group_leader = tsk; leader->group_leader = tsk; tsk->exit_signal = SIGCHLD; leader->exit_signal = -1; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees * the tracer won't block again waiting for this thread. */ if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); release_task(leader); } sig->group_exec_task = NULL; sig->notify_count = 0; no_thread_group: /* we have changed execution domain */ tsk->exit_signal = SIGCHLD; BUG_ON(!thread_group_leader(tsk)); return 0; killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); sig->group_exec_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN; } /* * This function makes sure the current process has its own signal table, * so that flush_signal_handlers can later reset the handlers without * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ static int unshare_sighand(struct task_struct *me) { struct sighand_struct *oldsighand = me->sighand; if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND * but not CLONE_THREAD task, switch to the new one. */ newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); if (!newsighand) return -ENOMEM; refcount_set(&newsighand->count, 1); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); rcu_assign_pointer(me->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); __cleanup_sighand(oldsighand); } return 0; } /* * These functions flushes out all traces of the currently running executable * so that a new one can be started */ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); strscpy_pad(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk, exec); } /* * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal * signal (via de_thread() or coredump), or will have SEGV raised * (after exec_mmap()) by search_binary_handler (see below). */ int begin_new_exec(struct linux_binprm * bprm) { struct task_struct *me = current; int retval; /* Once we are committed compute the creds */ retval = bprm_creds_from_file(bprm); if (retval) return retval; /* * This tracepoint marks the point before flushing the old exec where * the current task is still unchanged, but errors are fatal (point of * no return). The later "sched_process_exec" tracepoint is called after * the current task has successfully switched to the new exec. */ trace_sched_prepare_exec(current, bprm); /* * Ensure all future errors are fatal. */ bprm->point_of_no_return = true; /* * Make this the only thread in the thread group. */ retval = de_thread(me); if (retval) goto out; /* * Cancel any io_uring activity across execve */ io_uring_task_cancel(); /* Ensure the files table is not shared. */ retval = unshare_files(); if (retval) goto out; /* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. Doing it here also ensures * we don't race against replace_mm_exe_file(). */ retval = set_mm_exe_file(bprm->mm, bprm->file); if (retval) goto out; /* If the binary is not readable then enforce mm->dumpable=0 */ would_dump(bprm, bprm->file); if (bprm->have_execfd) would_dump(bprm, bprm->executable); /* * Release all of the old mmap stuff */ acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) goto out; bprm->mm = NULL; retval = exec_task_namespaces(); if (retval) goto out_unlock; #ifdef CONFIG_POSIX_TIMERS spin_lock_irq(&me->sighand->siglock); posix_cpu_timers_exit(me); spin_unlock_irq(&me->sighand->siglock); exit_itimers(me); flush_itimer_signals(); #endif /* * Make the signal table private. */ retval = unshare_sighand(me); if (retval) goto out_unlock; me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); me->personality &= ~bprm->per_clear; clear_syscall_work_syscall_user_dispatch(me); /* * We have to apply CLOEXEC before we change whether the process is * dumpable (in setup_new_exec) to avoid a race with a process in userspace * trying to access the should-be-closed file descriptors of a process * undergoing exec(2). */ do_close_on_exec(me->files); if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0; /* * For secureexec, reset the stack limit to sane default to * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ if (bprm->rlim_stack.rlim_cur > _STK_LIM) bprm->rlim_stack.rlim_cur = _STK_LIM; } me->sas_ss_sp = me->sas_ss_size = 0; /* * Figure out dumpability. Note that this checking only of current * is wrong, but userspace depends on it. This should be testing * bprm->secureexec instead. */ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || !(uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))) set_dumpable(current->mm, suid_dumpable); else set_dumpable(current->mm, SUID_DUMP_USER); perf_event_exec(); __set_task_comm(me, kbasename(bprm->filename), true); /* An exec changes our domain. We are no longer part of the thread group */ WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); flush_signal_handlers(me, 0); retval = set_cred_ucounts(bprm->cred); if (retval < 0) goto out_unlock; /* * install the new credentials for this executable */ security_bprm_committing_creds(bprm); commit_creds(bprm->cred); bprm->cred = NULL; /* * Disable monitoring for regular users * when executing setuid binaries. Must * wait until new credentials are committed * by commit_creds() above */ if (get_dumpable(me->mm) != SUID_DUMP_USER) perf_event_exit_task(me); /* * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); /* Pass the opened binary to the interpreter. */ if (bprm->have_execfd) { retval = get_unused_fd_flags(0); if (retval < 0) goto out_unlock; fd_install(retval, bprm->executable); bprm->executable = NULL; bprm->execfd = retval; } return 0; out_unlock: up_write(&me->signal->exec_update_lock); if (!bprm->cred) mutex_unlock(&me->signal->cred_guard_mutex); out: return retval; } EXPORT_SYMBOL(begin_new_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); struct mnt_idmap *idmap = file_mnt_idmap(file); if (inode_permission(idmap, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; /* Ensure mm->user_ns contains the executable */ user_ns = old = bprm->mm->user_ns; while ((user_ns != &init_user_ns) && !privileged_wrt_inode_uidgid(user_ns, idmap, inode)) user_ns = user_ns->parent; if (old != user_ns) { bprm->mm->user_ns = get_user_ns(user_ns); put_user_ns(old); } } } EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { /* Setup things that can depend upon the personality */ struct task_struct *me = current; arch_pick_mmap_layout(me->mm, &bprm->rlim_stack); arch_setup_new_exec(); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on * some architectures like powerpc */ me->mm->task_size = TASK_SIZE; up_write(&me->signal->exec_update_lock); mutex_unlock(&me->signal->cred_guard_mutex); } EXPORT_SYMBOL(setup_new_exec); /* Runs immediately before start_thread() takes over. */ void finalize_exec(struct linux_binprm *bprm) { /* Store any stack rlimit changes before starting thread. */ task_lock(current->group_leader); current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack; task_unlock(current->group_leader); } EXPORT_SYMBOL(finalize_exec); /* * Prepare credentials and lock ->cred_guard_mutex. * setup_new_exec() commits the new creds and drops the lock. * Or, if exec fails before, free_bprm() should release ->cred * and unlock. */ static int prepare_bprm_creds(struct linux_binprm *bprm) { if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM; } /* Matches do_open_execat() */ static void do_close_execat(struct file *file) { if (!file) return; allow_write_access(file); fput(file); } static void free_bprm(struct linux_binprm *bprm) { if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); } free_arg_pages(bprm); if (bprm->cred) { mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } do_close_execat(bprm->file); if (bprm->executable) fput(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); kfree(bprm->fdpath); kfree(bprm); } static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags) { struct linux_binprm *bprm; struct file *file; int retval = -ENOMEM; file = do_open_execat(fd, filename, flags); if (IS_ERR(file)) return ERR_CAST(file); bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) { do_close_execat(file); return ERR_PTR(-ENOMEM); } bprm->file = file; if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { if (filename->name[0] == '\0') bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); else bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); if (!bprm->fdpath) goto out_free; /* * Record that a name derived from an O_CLOEXEC fd will be * inaccessible after exec. This allows the code in exec to * choose to fail when the executable is not mmaped into the * interpreter and an open file descriptor is not passed to * the interpreter. This makes for a better user experience * than having the interpreter start and then immediately fail * when it finds the executable is inaccessible. */ if (get_close_on_exec(fd)) bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE; bprm->filename = bprm->fdpath; } bprm->interp = bprm->filename; retval = bprm_mm_init(bprm); if (!retval) return bprm; out_free: free_bprm(bprm); return ERR_PTR(retval); } int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); bprm->interp = kstrdup(interp, GFP_KERNEL); if (!bprm->interp) return -ENOMEM; return 0; } EXPORT_SYMBOL(bprm_change_interp); /* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH or seccomp thread-sync */ static void check_unsafe_exec(struct linux_binprm *bprm) { struct task_struct *p = current, *t; unsigned n_fs; if (p->ptrace) bprm->unsafe |= LSM_UNSAFE_PTRACE; /* * This isn't strictly necessary, but it makes it harder for LSMs to * mess up. */ if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; /* * If another task is sharing our fs, we cannot safely * suid exec because the differently privileged task * will be able to manipulate the current directory, etc. * It would be nice to force an unshare instead... */ n_fs = 1; spin_lock(&p->fs->lock); rcu_read_lock(); for_other_threads(p, t) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock(); /* "users" and "in_exec" locked for copy_fs() */ if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else p->fs->in_exec = 1; spin_unlock(&p->fs->lock); } static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) { /* Handle suid and sgid on files */ struct mnt_idmap *idmap; struct inode *inode = file_inode(file); unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; int err; if (!mnt_may_suid(file->f_path.mnt)) return; if (task_no_new_privs(current)) return; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; idmap = file_mnt_idmap(file); /* Be careful if suid/sgid is set */ inode_lock(inode); /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode); /* Did the exec bit vanish out from under us? Give up. */ if (err) return; /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) return; if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = vfsuid_into_kuid(vfsuid); } if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = vfsgid_into_kgid(vfsgid); } } /* * Compute brpm->cred based upon the final binary. */ static int bprm_creds_from_file(struct linux_binprm *bprm) { /* Compute creds based on which file? */ struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file; bprm_fill_uid(bprm, file); return security_bprm_creds_from_file(bprm, file); } /* * Fill the binprm structure from the inode. * Read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */ static int prepare_binprm(struct linux_binprm *bprm) { loff_t pos = 0; memset(bprm->buf, 0, BINPRM_BUF_SIZE); return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos); } /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after * the first '\0' encountered. */ int remove_arg_zero(struct linux_binprm *bprm) { unsigned long offset; char *kaddr; struct page *page; if (!bprm->argc) return 0; do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); if (!page) return -EFAULT; kaddr = kmap_local_page(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); bprm->p++; bprm->argc--; return 0; } EXPORT_SYMBOL(remove_arg_zero); #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ static int search_binary_handler(struct linux_binprm *bprm) { bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; retval = prepare_binprm(bprm); if (retval < 0) return retval; retval = security_bprm_check(bprm); if (retval) return retval; retval = -ENOENT; retry: read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); retval = fmt->load_binary(bprm); read_lock(&binfmt_lock); put_binfmt(fmt); if (bprm->point_of_no_return || (retval != -ENOEXEC)) { read_unlock(&binfmt_lock); return retval; } } read_unlock(&binfmt_lock); if (need_retry) { if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && printable(bprm->buf[2]) && printable(bprm->buf[3])) return retval; if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) return retval; need_retry = false; goto retry; } return retval; } /* binfmt handlers will call back into begin_new_exec() on success. */ static int exec_binprm(struct linux_binprm *bprm) { pid_t old_pid, old_vpid; int ret, depth; /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; rcu_read_lock(); old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); /* This allows 4 levels of binfmt rewrites before failing hard. */ for (depth = 0;; depth++) { struct file *exec; if (depth > 5) return -ELOOP; ret = search_binary_handler(bprm); if (ret < 0) return ret; if (!bprm->interpreter) break; exec = bprm->file; bprm->file = bprm->interpreter; bprm->interpreter = NULL; allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); return -ENOEXEC; } bprm->executable = exec; } else fput(exec); } audit_bprm(bprm); trace_sched_process_exec(current, old_pid, bprm); ptrace_event(PTRACE_EVENT_EXEC, old_vpid); proc_exec_connector(current); return 0; } static int bprm_execve(struct linux_binprm *bprm) { int retval; retval = prepare_bprm_creds(bprm); if (retval) return retval; /* * Check for unsafe execution states before exec_binprm(), which * will call back into begin_new_exec(), into bprm_creds_from_file(), * where setuid-ness is evaluated. */ check_unsafe_exec(bprm); current->in_execve = 1; sched_mm_cid_before_execve(current); sched_exec(); /* Set the unchanging part of bprm->cred */ retval = security_bprm_creds_for_exec(bprm); if (retval) goto out; retval = exec_binprm(bprm); if (retval < 0) goto out; sched_mm_cid_after_execve(current); /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; rseq_execve(current); user_events_execve(current); acct_update_integrals(current); task_numa_free(current, false); return retval; out: /* * If past the point of no return ensure the code never * returns to the userspace process. Use an existing fatal * signal if present otherwise terminate the process with * SIGSEGV. */ if (bprm->point_of_no_return && !fatal_signal_pending(current)) force_fatal_sig(SIGSEGV); sched_mm_cid_after_execve(current); current->fs->in_exec = 0; current->in_execve = 0; return retval; } static int do_execveat_common(int fd, struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp, int flags) { struct linux_binprm *bprm; int retval; if (IS_ERR(filename)) return PTR_ERR(filename); /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs * don't check setuid() return code. Here we additionally recheck * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { retval = -EAGAIN; goto out_ret; } /* We're below the limit (still or again), so we don't want to make * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED; bprm = alloc_bprm(fd, filename, flags); if (IS_ERR(bprm)) { retval = PTR_ERR(bprm); goto out_ret; } retval = count(argv, MAX_ARG_STRINGS); if (retval == 0) pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", current->comm, bprm->filename); if (retval < 0) goto out_free; bprm->argc = retval; retval = count(envp, MAX_ARG_STRINGS); if (retval < 0) goto out_free; bprm->envc = retval; retval = bprm_stack_limits(bprm); if (retval < 0) goto out_free; retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out_free; bprm->exec = bprm->p; retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) goto out_free; retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) goto out_free; /* * When argv is empty, add an empty string ("") as argv[0] to * ensure confused userspace programs that start processing * from argv[1] won't end up walking envp. See also * bprm_stack_limits(). */ if (bprm->argc == 0) { retval = copy_string_kernel("", bprm); if (retval < 0) goto out_free; bprm->argc = 1; } retval = bprm_execve(bprm); out_free: free_bprm(bprm); out_ret: putname(filename); return retval; } int kernel_execve(const char *kernel_filename, const char *const *argv, const char *const *envp) { struct filename *filename; struct linux_binprm *bprm; int fd = AT_FDCWD; int retval; /* It is non-sense for kernel threads to call execve */ if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return -EINVAL; filename = getname_kernel(kernel_filename); if (IS_ERR(filename)) return PTR_ERR(filename); bprm = alloc_bprm(fd, filename, 0); if (IS_ERR(bprm)) { retval = PTR_ERR(bprm); goto out_ret; } retval = count_strings_kernel(argv); if (WARN_ON_ONCE(retval == 0)) retval = -EINVAL; if (retval < 0) goto out_free; bprm->argc = retval; retval = count_strings_kernel(envp); if (retval < 0) goto out_free; bprm->envc = retval; retval = bprm_stack_limits(bprm); if (retval < 0) goto out_free; retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out_free; bprm->exec = bprm->p; retval = copy_strings_kernel(bprm->envc, envp, bprm); if (retval < 0) goto out_free; retval = copy_strings_kernel(bprm->argc, argv, bprm); if (retval < 0) goto out_free; retval = bprm_execve(bprm); out_free: free_bprm(bprm); out_ret: putname(filename); return retval; } static int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int do_execveat(int fd, struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp, int flags) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(fd, filename, argv, envp, flags); } #ifdef CONFIG_COMPAT static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int compat_do_execveat(int fd, struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp, int flags) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(fd, filename, argv, envp, flags); } #endif void set_binfmt(struct linux_binfmt *new) { struct mm_struct *mm = current->mm; if (mm->binfmt) module_put(mm->binfmt->module); mm->binfmt = new; if (new) __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); /* * set_dumpable stores three-value SUID_DUMP_* into mm->flags. */ void set_dumpable(struct mm_struct *mm, int value) { if (WARN_ON((unsigned)value > SUID_DUMP_ROOT)) return; set_mask_bits(&mm->flags, MMF_DUMPABLE_MASK, value); } SYSCALL_DEFINE3(execve, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp) { return do_execve(getname(filename), argv, envp); } SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp, int, flags) { return do_execveat(fd, getname_uflags(filename, flags), argv, envp, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp) { return compat_do_execve(getname(filename), argv, envp); } COMPAT_SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp, int, flags) { return compat_do_execveat(fd, getname_uflags(filename, flags), argv, envp, flags); } #endif #ifdef CONFIG_SYSCTL static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!error) validate_coredump_safety(); return error; } static struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, }; static int __init init_fs_exec_sysctls(void) { register_sysctl_init("fs", fs_exec_sysctls); return 0; } fs_initcall(init_fs_exec_sysctls); #endif /* CONFIG_SYSCTL */ #ifdef CONFIG_EXEC_KUNIT_TEST #include "tests/exec_kunit.c" #endif |
| 107 208 648 1 167 97 371 26 205 78 125 176 35 372 373 19 17 177 339 206 7 68 168 586 177 177 177 177 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the pageflags directly. Use the PageFoo macros. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_writeback, /* Page is under writeback */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_head, /* Must be in bit 6 */ PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, /* Anonymous memory (and shmem) */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Some filesystems */ PG_checked = PG_owner_priv_1, /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped * THP), PG_anon_exclusive may be set only for the head page or for * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ PG_anon_exclusive = PG_owner_2, /* * Set if all buffer heads in the folio are mapped. * Filesystems which do not use BHs can use it for their own purpose. */ PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, #ifdef CONFIG_MEMORY_HOTPLUG /* For self-hosted memmap pages */ PG_vmemmap_self_hosted = PG_owner_priv_1, #endif /* * Flags only valid for compound pages. Stored in first tail page's * flags word. Cannot use the first 8 flags or any flag marked as * PF_ANY. */ /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) #ifndef __GENERATING_BOUNDS_H #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); /* * Return the real head page struct iff the @page is a fake head page, otherwise * return the @page itself. See Documentation/mm/vmemmap_dedup.rst. */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) return page; /* * Only addresses aligned with PAGE_SIZE of struct page may be fake head * struct page. The alignment check aims to avoid access the fields ( * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) * cold cacheline in some cases. */ if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && test_bit(PG_head, &page->flags)) { /* * We can safely access the field of the @page[1] with PG_head * because the @page is a compound page composed with at least * two contiguous pages. */ unsigned long head = READ_ONCE(page[1].compound_head); if (likely(head & 1)) return (const struct page *)(head - 1); } return page; } #else static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } #endif static __always_inline int page_is_fake_head(const struct page *page) { return page_fixed_fake_head(page) != page; } static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) /** * page_folio - Converts from page to folio. * @p: The page. * * Every page is part of a folio. This function cannot be called on a * NULL pointer. * * Context: No reference, nor lock is required on @page. If the caller * does not hold a reference, this call may race with a folio split, so * it should re-check the folio still contains this page after gaining * a reference on the folio. * Return: The folio which contains this page. */ #define page_folio(p) (_Generic((p), \ const struct page *: (const struct folio *)_compound_head(p), \ struct page *: (struct folio *)_compound_head(p))) /** * folio_page - Return a page from a folio. * @folio: The folio. * @n: The page number to return. * * @n is relative to the start of the folio. This function does not * check that the page number lies within @folio; the caller is presumed * to have a reference to the page. */ #define folio_page(folio, n) nth_page(&(folio)->page, n) static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags) || READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif static const unsigned long *const_folio_flags(const struct folio *folio, unsigned n) { const struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* Which page is the flag stored in */ #define FOLIO_PF_ANY 0 #define FOLIO_PF_HEAD 0 #define FOLIO_PF_NO_TAIL 0 #define FOLIO_PF_NO_COMPOUND 0 #define FOLIO_PF_SECOND 1 #define FOLIO_HEAD_PAGE 0 #define FOLIO_SECOND_PAGE 1 /* * Macros to create function definitions for page flags */ #define FOLIO_TEST_FLAG(name, page) \ static __always_inline bool folio_test_##name(const struct folio *folio) \ { return test_bit(PG_##name, const_folio_flags(folio, page)); } #define FOLIO_SET_FLAG(name, page) \ static __always_inline void folio_set_##name(struct folio *folio) \ { set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void folio_clear_##name(struct folio *folio) \ { clear_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_SET_FLAG(name, page) \ static __always_inline void __folio_set_##name(struct folio *folio) \ { __set_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void __folio_clear_##name(struct folio *folio) \ { __clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_SET_FLAG(name, page) \ static __always_inline bool folio_test_set_##name(struct folio *folio) \ { return test_and_set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_CLEAR_FLAG(name, page) \ static __always_inline bool folio_test_clear_##name(struct folio *folio) \ { return test_and_clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_FLAG(name, page) \ FOLIO_TEST_FLAG(name, page) \ FOLIO_SET_FLAG(name, page) \ FOLIO_CLEAR_FLAG(name, page) #define TESTPAGEFLAG(uname, lname, policy) \ FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ static __always_inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ __FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ __FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define FOLIO_TEST_FLAG_FALSE(name) \ static inline bool folio_test_##name(const struct folio *folio) \ { return false; } #define FOLIO_SET_FLAG_NOOP(name) \ static inline void folio_set_##name(struct folio *folio) { } #define FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void folio_clear_##name(struct folio *folio) { } #define __FOLIO_SET_FLAG_NOOP(name) \ static inline void __folio_set_##name(struct folio *folio) { } #define __FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void __folio_clear_##name(struct folio *folio) { } #define FOLIO_TEST_SET_FLAG_FALSE(name) \ static inline bool folio_test_set_##name(struct folio *folio) \ { return false; } #define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ static inline bool folio_test_clear_##name(struct folio *folio) \ { return false; } #define FOLIO_FLAG_FALSE(name) \ FOLIO_TEST_FLAG_FALSE(name) \ FOLIO_SET_FLAG_NOOP(name) \ FOLIO_CLEAR_FLAG_NOOP(name) #define TESTPAGEFLAG_FALSE(uname, lname) \ FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ __FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) #define TESTSCFLAG_FALSE(uname, lname) \ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) FOLIO_FLAG(active, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f)) #else PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { return folio_test_swapbacked(folio) && test_bit(PG_swapcache, const_folio_flags(folio, 0)); } FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(swapcache) #endif FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(mlocked) __FOLIO_CLEAR_FLAG_NOOP(mlocked) FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif #ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif /* See page_idle.h for !64BIT workaround */ #else /* !CONFIG_PAGE_IDLE_FLAG */ FOLIO_FLAG_FALSE(young) FOLIO_TEST_CLEAR_FLAG_FALSE(young) FOLIO_FLAG_FALSE(idle) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #ifdef CONFIG_MEMORY_HOTPLUG PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) #else PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* * On an anonymous folio mapped into a user virtual memory area, * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then folio->mapping points to a struct movable_operations. * * Please note that, confusingly, "folio_mapping" refers to the inode * address_space which maps the folio from disk; whereas "folio_mapped" * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its * internal states, the folio->mapping does not exist as such, nor do * these flags below. So in order to avoid testing non-existent bits, * please make sure that folio_test_slab(folio) actually evaluates to * false before calling the following functions (e.g., folio_test_anon). * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) /* * Different with flags above, this flag is used only for fsdax mode. It * indicates that this page->mapping is now under reflink case. */ #define PAGE_MAPPING_DAX_SHARED ((void *)0x1) static __always_inline bool folio_mapping_flags(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline bool PageAnonNotKsm(const struct page *page) { unsigned long flags = (unsigned long)page_folio(page)->mapping; return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON; } static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } static __always_inline bool __folio_test_movable(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline bool folio_test_ksm(const struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } #else FOLIO_TEST_FLAG_FALSE(ksm) #endif u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. * @folio: The folio. * @mask: Bits set in this word will be changed. * * This must only be used for flags which are changed with the folio * lock held. For example, it is unsafe to use for PG_dirty as that * can be set without the folio lock held. It can also only be used * on flags which are in the range 0-6 as some of the implementations * only affect those bits. * * Return: Whether there are tasks waiting on the folio. */ static inline bool folio_xor_flags_has_waiters(struct folio *folio, unsigned long mask) { return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0)); } /** * folio_test_uptodate - Is this folio up to date? * @folio: The folio. * * The uptodate flag is set on a folio when every byte in the folio is * at least as new as the corresponding bytes on storage. Anonymous * and CoW folios are always uptodate. If the folio is not uptodate, * some of the bytes in it may be; see the is_partially_uptodate() * address_space operation. */ static inline bool folio_test_uptodate(const struct folio *folio) { bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0)); /* * Must ensure that the data we read out of the folio is loaded * _after_ we've loaded folio->flags to check the uptodate bit. * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } static __always_inline void __folio_mark_uptodate(struct folio *folio) { smp_wmb(); __set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void folio_mark_uptodate(struct folio *folio) { /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the folio * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void __SetPageUptodate(struct page *page) { __folio_mark_uptodate((struct folio *)page); } static __always_inline void SetPageUptodate(struct page *page) { folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) void __folio_start_writeback(struct folio *folio, bool keep_write); void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) static __always_inline bool folio_test_head(const struct folio *folio) { return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY)); } static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); } __SETPAGEFLAG(Head, head, PF_ANY) __CLEARPAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. * * Return: True if the folio is larger than one page. */ static inline bool folio_test_large(const struct folio *folio) { return folio_test_head(folio); } static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE) /* * PG_partially_mapped is protected by deferred_split split_queue_lock, * so its safe to use non-atomic set/clear. */ __FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE) __FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) FOLIO_TEST_FLAG_FALSE(partially_mapped) __FOLIO_SET_FLAG_NOOP(partially_mapped) __FOLIO_CLEAR_FLAG_NOOP(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(const struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } /* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransTail(const struct page *page) { return PageTail(page); } #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) TESTPAGEFLAG_FALSE(TransTail, transtail) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) /* * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the * compound page. * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) #else PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* * For pages that do not use mapcount, page_type may be used. * The low 24 bits of pagetype may be used for your own purposes, as long * as you are careful to not affect the top 8 bits. The low bits of * pagetype will be overwritten when you clear the page_type from the page. */ enum pagetype { /* 0x00-0x7f are positive numbers, ie mapcount */ /* Reserve 0x80-0xef for mapcount overflow. */ PGTY_buddy = 0xf0, PGTY_offline = 0xf1, PGTY_table = 0xf2, PGTY_guard = 0xf3, PGTY_hugetlb = 0xf4, PGTY_slab = 0xf5, PGTY_zsmalloc = 0xf6, PGTY_unaccepted = 0xf7, PGTY_mapcount_underflow = 0xff }; static inline bool page_type_has_type(int page_type) { return page_type < (PGTY_mapcount_underflow << 24); } /* This takes a mapcount which is one more than page->_mapcount */ static inline bool page_mapcount_is_type(unsigned int mapcount) { return page_type_has_type(mapcount - 1); } static inline bool page_has_type(const struct page *page) { return page_mapcount_is_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ if (folio_test_##fname(folio)) \ return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ if (folio->page.page_type == UINT_MAX) \ return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ if (Page##uname(page)) \ return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ if (page->page_type == UINT_MAX) \ return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * When a memory block gets onlined, all pages are initialized with a * refcount of 1 and PageOffline(). generic_online_page() will * take care of clearing PageOffline(). * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free (unmanaged) * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require not giving them to the buddy via generic_online_page(). * * Memory offlining code will not adjust the managed page count for any * PageOffline() pages, treating them like they were never exposed to the * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random * pages should check PageOffline() and synchronize with such drivers using * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline, offline) extern void page_offline_freeze(void); extern void page_offline_thaw(void); extern void page_offline_begin(void); extern void page_offline_end(void); /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table, pgtable) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard, guard) FOLIO_TYPE_OPS(slab, slab) /** * PageSlab - Determine if the page belongs to the slab allocator * @page: The page to test. * * Context: Any context. * Return: True for slab pages, false for any other kind of page. */ static inline bool PageSlab(const struct page *page) { return folio_test_slab(page_folio(page)); } #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) /* * Mark pages that has to be accepted before touched for the first time. * * Serialized with zone lock. */ PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. * * Context: Any context. * Return: True for hugetlbfs pages, false for anon pages or pages * belonging to other filesystems. */ static inline bool PageHuge(const struct page *page) { return folio_test_hugetlb(page_folio(page)); } /* * Check if a page is currently marked HWPoisoned. Note that this check is * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ static inline bool is_page_hwpoison(const struct page *page) { const struct folio *folio; if (PageHWPoison(page)) return true; folio = page_folio(page); return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); /* * HugeTLB stores this information on the head page; THP keeps it per * page */ if (PageHuge(page)) page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void SetPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void __ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) /* * Flags stored in the second page of a compound page. They may overlap * the CHECK_AT_FREE flags above, so need to be cleared. */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * folio_has_private - Determine if folio has private stuff * @folio: The folio to be checked * * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ static inline int folio_has_private(const struct folio *folio) { return !!(folio->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 1 1 1 2 2 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 | /* * llc_station.c - station component of LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <net/llc.h> #include <net/llc_sap.h> #include <net/llc_conn.h> #include <net/llc_c_ac.h> #include <net/llc_s_ac.h> #include <net/llc_c_ev.h> #include <net/llc_c_st.h> #include <net/llc_s_ev.h> #include <net/llc_s_st.h> #include <net/llc_pdu.h> static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) { u8 mac_da[ETH_ALEN], dsap; int rc = 1; struct sk_buff *nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, sizeof(struct llc_xid_info)); if (!nskb) goto out; llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_ssap(skb, &dsap); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, 0, dsap, LLC_PDU_RSP); llc_pdu_init_as_xid_rsp(nskb, LLC_XID_NULL_CLASS_2, 127); rc = llc_mac_hdr_init(nskb, skb->dev->dev_addr, mac_da); if (unlikely(rc)) goto free; dev_queue_xmit(nskb); out: return rc; free: kfree_skb(nskb); goto out; } static int llc_station_ac_send_test_r(struct sk_buff *skb) { u8 mac_da[ETH_ALEN], dsap; int rc = 1; u32 data_size; struct sk_buff *nskb; if (skb->mac_len < ETH_HLEN) goto out; /* The test request command is type U (llc_len = 3) */ data_size = ntohs(eth_hdr(skb)->h_proto) - 3; nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size); if (!nskb) goto out; llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_ssap(skb, &dsap); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, 0, dsap, LLC_PDU_RSP); llc_pdu_init_as_test_rsp(nskb, skb); rc = llc_mac_hdr_init(nskb, skb->dev->dev_addr, mac_da); if (unlikely(rc)) goto free; dev_queue_xmit(nskb); out: return rc; free: kfree_skb(nskb); goto out; } /** * llc_station_rcv - send received pdu to the station state machine * @skb: received frame. * * Sends data unit to station state machine. */ static void llc_station_rcv(struct sk_buff *skb) { if (llc_stat_ev_rx_null_dsap_xid_c(skb)) llc_station_ac_send_xid_r(skb); else if (llc_stat_ev_rx_null_dsap_test_c(skb)) llc_station_ac_send_test_r(skb); kfree_skb(skb); } void __init llc_station_init(void) { llc_set_station_handler(llc_station_rcv); } void llc_station_exit(void) { llc_set_station_handler(NULL); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NETFILTER_NETDEV_H_ #define _NETFILTER_NETDEV_H_ #include <linux/netfilter.h> #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) return false; #endif return rcu_access_pointer(skb->dev->nf_hooks_ingress); } /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; /* Must recheck the ingress hook head, in the event it became NULL * after the check in nf_hook_ingress_active evaluated to true. */ if (unlikely(!e)) return 0; nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; return ret; } #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) { return 0; } static inline int nf_hook_ingress(struct sk_buff *skb) { return 0; } #endif /* CONFIG_NETFILTER_INGRESS */ #ifdef CONFIG_NETFILTER_EGRESS static inline bool nf_hook_egress_active(void) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) return false; #endif return true; } /** * nf_hook_egress - classify packets before transmission * @skb: packet to be classified * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * * Returns @skb on success or %NULL if the packet was consumed or filtered. * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. * On egress, the order is reversed for symmetry. Conceptually, tc and * netfilter can be thought of as layers, with netfilter layered above tc: * When tc redirects a packet to another interface, netfilter is not applied * because the packet is on the tc layer. * * The nf_skip_egress flag controls whether netfilter is applied on egress. * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the * packet passes through tc and netfilter. Because __dev_queue_xmit() may be * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { struct nf_hook_entries *e; struct nf_hook_state state; int ret; #ifdef CONFIG_NETFILTER_SKIP_EGRESS if (skb->nf_skip_egress) return skb; #endif e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); /* nf assumes rcu_read_lock, not just read_lock_bh */ rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); rcu_read_unlock(); if (ret == 1) { return skb; } else if (ret < 0) { *rc = NET_XMIT_DROP; return NULL; } else { /* ret == 0 */ *rc = NET_XMIT_SUCCESS; return NULL; } } #else /* CONFIG_NETFILTER_EGRESS */ static inline bool nf_hook_egress_active(void) { return false; } static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { return skb; } #endif /* CONFIG_NETFILTER_EGRESS */ static inline void nf_skip_egress(struct sk_buff *skb, bool skip) { #ifdef CONFIG_NETFILTER_SKIP_EGRESS skb->nf_skip_egress = skip; #endif } static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif #ifdef CONFIG_NETFILTER_EGRESS RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); #endif } #endif /* _NETFILTER_NETDEV_H_ */ |
| 41 96 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 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> #include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> #include <linux/smp_types.h> #include <linux/pid_types.h> #include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> #include <linux/mutex_types.h> #include <linux/plist_types.h> #include <linux/hrtimer_types.h> #include <linux/timer_types.h> #include <linux/seccomp_types.h> #include <linux/nodemask_types.h> #include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> #include <uapi/linux/rseq.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> #include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; struct task_struct; struct user_event_mm; #include <linux/sched/ext.h> /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->__state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->__state: */ #define TASK_RUNNING 0x00000000 #define TASK_INTERRUPTIBLE 0x00000001 #define TASK_UNINTERRUPTIBLE 0x00000002 #define __TASK_STOPPED 0x00000004 #define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x00000010 #define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->__state again: */ #define TASK_PARKED 0x00000040 #define TASK_DEAD 0x00000080 #define TASK_WAKEKILL 0x00000100 #define TASK_WAKING 0x00000200 #define TASK_NOLOAD 0x00000400 #define TASK_NEW 0x00000800 #define TASK_RTLOCK_WAIT 0x00001000 #define TASK_FREEZABLE 0x00002000 #define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) #define TASK_FROZEN 0x00008000 #define TASK_STATE_MAX 0x00010000 #define TASK_ANY (TASK_STATE_MAX-1) /* * DO NOT ADD ANY NEW USERS ! */ #define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->__state. * * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* * Define the task command name length as enum, then it can be visible to * BPF programs. */ enum { TASK_COMM_LEN = 16, }; extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif struct sched_param { int sched_priority; }; struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; unsigned int util_est; } ____cacheline_aligned; /* * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est at dequeue time. * Since max value of util_est for a task is 1024 (PELT util_avg for a task) * it is safe to use MSB. */ #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; s64 sum_block_runtime; s64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; #endif #endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; u64 deadline; u64 min_vruntime; u64 min_slice; struct list_head group_node; unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; unsigned char custom_slice; /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; s64 vlag; u64 slice; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif #ifdef CONFIG_SMP /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; #endif }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. * * @dl_server tells if this is a server entity. * * @dl_defer tells if this is a deferred or regular server. For * now only defer server exists. * * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; /* * Bits for DL-server functionality. Also see the comment near * dl_server_update(). * * @rq the runqueue this server is for * * @server_has_tasks() returns true if @server_pick return a * runnable task. */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; /* saved state for "spinlock sleepers" */ unsigned int saved_state; /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_MEM_ALLOC_PROFILING struct alloc_tag *alloc_tag; #endif #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; #endif int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; #ifdef CONFIG_SCHED_CLASS_EXT struct sched_ext_entity scx; #endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP unsigned short migration_disabled; #endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; int rcu_tasks_exit_cpu; struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; struct list_head trc_holdout_list; struct list_head trc_blkd_node; int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; struct list_head tasks; #ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; #endif struct mm_struct *mm; struct mm_struct *active_mm; struct address_space *faults_disabled_mapping; int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; #ifdef CONFIG_RT_MUTEXES unsigned sched_rt_mutex:1; #endif /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN /* whether the LRU algorithm may apply to this access */ unsigned in_lru_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_KTHREAD | PF_IO_WORKER */ void *worker_private; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized begin_new_exec() * - set it with set_task_comm() * - strscpy_pad() to ensure it is always NUL-terminated and * zero-padded * - task_lock() to ensure the operation is atomic and the name is * fully updated. */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES /* Mutex deadlock detection: */ struct mutex_waiter *blocked_on; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; /* Stack plugging: */ struct blk_plug *plug; /* VM state: */ struct reclaim_state *reclaim_state; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_RSEQ struct rseq __user *rseq; u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically * with respect to preemption. */ unsigned long rseq_event_mask; #endif #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ int last_mm_cid; /* Most recent cid in mm */ int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #ifdef CONFIG_KCSAN_WEAK_MEMORY int kcsan_stack_depth; #endif #endif #ifdef CONFIG_KMSAN struct kmsan_ctx kmsan_ctx; #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; #endif #ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif struct rcu_head rcu; refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_RETHOOK struct llist_head rethooks; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif #ifdef CONFIG_RV /* * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. * If we find justification for more monitors, we can think * about adding more or developing a dynamic method. So far, * none of these are justified. */ union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end /* CPU-specific state of this task: */ struct thread_struct thread; /* * WARNING: on x86, 'thread_struct' contains a variable-sized * structure. It *MUST* be at the end of 'task_struct'. * * Do not put anything below here! */ }; #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int __task_state_index(unsigned int tsk_state, unsigned int tsk_exit_state) { unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if ((tsk_state & TASK_IDLE) == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. */ if (tsk_state & TASK_RTLOCK_WAIT) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline unsigned int task_state_index(struct task_struct *tsk) { return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF__HOLE__00800000 0x00800000 #define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); #else return true; #endif } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task * @p: the task * @new_mask: CPU affinity mask * * Return: zero if successful, or a negative error code */ extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { if (src->user_cpus_ptr) return -EINVAL; return 0; } static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) { return 0; } #endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { struct task_struct task; #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) #else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); static inline void set_task_comm(struct task_struct *tsk, const char *from) { __set_task_comm(tsk, from, false); } /* * - Why not use task_lock()? * User space can randomly change their names anyway, so locking for readers * doesn't make sense. For writers, locking is probably necessary, as a race * condition could lead to long-term mixed results. * The strscpy_pad() in __set_task_comm() can ensure that the task comm is * always NUL-terminated and zero-padded. Therefore the race condition between * reader and writer is not an issue. * * - BUILD_BUG_ON() can help prevent the buf from being truncated. * Since the callers don't perform any return value checks, this safeguard is * necessary. */ #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ strscpy_pad(buf, (tsk)->comm); \ buf; \ }) #ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } #else static inline void scheduler_ipi(void) { } #endif extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) void sched_dynamic_klp_enable(void); void sched_dynamic_klp_disable(void); DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) { return dynamic_cond_resched(); } #else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { klp_sched_try_switch(); return __cond_resched(); } #endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ #else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ static inline int _cond_resched(void) { klp_sched_try_switch(); return 0; } #endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) #ifndef CONFIG_PREEMPT_RT /* * Non RT kernels have an elevated preempt count due to the held lock, * but are not allowed to be inside a RCU read side critical section */ # define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET #else /* * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in * cond_resched*lock() has to take that into account because it checks for * preempt_count() and rcu_preempt_depth(). */ # define PREEMPT_LOCK_RESCHED_OFFSETS \ (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) #endif #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_write(lock); \ }) static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { return READ_ONCE(task_thread_info(p)->cpu); } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ static inline bool task_is_runnable(struct task_struct *p) { return p->on_rq && !p->se.sched_delayed; } extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); #include <linux/spinlock.h> /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif #ifdef CONFIG_SMP static inline bool owner_on_cpu(struct task_struct *owner) { /* * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); extern int sched_core_idle_cpu(int cpu); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } #endif extern void sched_set_stop_task(int cpu, struct task_struct *stop); #ifdef CONFIG_MEM_ALLOC_PROFILING static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) { swap(current->alloc_tag, tag); return tag; } static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) { #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); #endif current->alloc_tag = old; } #else #define alloc_tag_save(_tag) NULL #define alloc_tag_restore(_tag, _old) do {} while (0) #endif #endif |
| 23 23 23 23 253 87 86 55 87 87 179 179 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/tlbflush.h * * Copyright (C) 1999-2003 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_TLBFLUSH_H #define __ASM_TLBFLUSH_H #ifndef __ASSEMBLY__ #include <linux/bitfield.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <linux/mmu_notifier.h> #include <asm/cputype.h> #include <asm/mmu.h> /* * Raw TLBI operations. * * Where necessary, use the __tlbi() macro to avoid asm() * boilerplate. Drivers and most kernel code should use the TLB * management routines in preference to the macro below. * * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending * on whether a particular TLBI operation takes an argument or * not. The macros handles invoking the asm with or without the * register argument as appropriate. */ #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE \ "tlbi " #op "\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op, \ ARM64_WORKAROUND_REPEAT_TLBI, \ CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : ) #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE \ "tlbi " #op ", %0\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op ", %0", \ ARM64_WORKAROUND_REPEAT_TLBI, \ CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : "r" (arg)) #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg) #define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0) #define __tlbi_user(op, arg) do { \ if (arm64_kernel_unmapped_at_el0()) \ __tlbi(op, (arg) | USER_ASID_FLAG); \ } while (0) /* This macro creates a properly formatted VA operand for the TLBI */ #define __TLBI_VADDR(addr, asid) \ ({ \ unsigned long __ta = (addr) >> 12; \ __ta &= GENMASK_ULL(43, 0); \ __ta |= (unsigned long)(asid) << 48; \ __ta; \ }) /* * Get translation granule of the system, which is decided by * PAGE_SIZE. Used by TTL. * - 4KB : 1 * - 16KB : 2 * - 64KB : 3 */ #define TLBI_TTL_TG_4K 1 #define TLBI_TTL_TG_16K 2 #define TLBI_TTL_TG_64K 3 static inline unsigned long get_trans_granule(void) { switch (PAGE_SIZE) { case SZ_4K: return TLBI_TTL_TG_4K; case SZ_16K: return TLBI_TTL_TG_16K; case SZ_64K: return TLBI_TTL_TG_64K; default: return 0; } } /* * Level-based TLBI operations. * * When ARMv8.4-TTL exists, TLBI operations take an additional hint for * the level at which the invalidation must take place. If the level is * wrong, no invalidation may take place. In the case where the level * cannot be easily determined, the value TLBI_TTL_UNKNOWN will perform * a non-hinted invalidation. Any provided level outside the hint range * will also cause fall-back to non-hinted invalidation. * * For Stage-2 invalidation, use the level values provided to that effect * in asm/stage2_pgtable.h. */ #define TLBI_TTL_MASK GENMASK_ULL(47, 44) #define TLBI_TTL_UNKNOWN INT_MAX #define __tlbi_level(op, addr, level) do { \ u64 arg = addr; \ \ if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) && \ level >= 0 && level <= 3) { \ u64 ttl = level & 3; \ ttl |= get_trans_granule() << 2; \ arg &= ~TLBI_TTL_MASK; \ arg |= FIELD_PREP(TLBI_TTL_MASK, ttl); \ } \ \ __tlbi(op, arg); \ } while(0) #define __tlbi_user_level(op, arg, level) do { \ if (arm64_kernel_unmapped_at_el0()) \ __tlbi_level(op, (arg | USER_ASID_FLAG), level); \ } while (0) /* * This macro creates a properly formatted VA operand for the TLB RANGE. The * value bit assignments are: * * +----------+------+-------+-------+-------+----------------------+ * | ASID | TG | SCALE | NUM | TTL | BADDR | * +-----------------+-------+-------+-------+----------------------+ * |63 48|47 46|45 44|43 39|38 37|36 0| * * The address range is determined by below formula: [BADDR, BADDR + (NUM + 1) * * 2^(5*SCALE + 1) * PAGESIZE) * * Note that the first argument, baddr, is pre-shifted; If LPA2 is in use, BADDR * holds addr[52:16]. Else BADDR holds page number. See for example ARM DDI * 0487J.a section C5.5.60 "TLBI VAE1IS, TLBI VAE1ISNXS, TLB Invalidate by VA, * EL1, Inner Shareable". * */ #define TLBIR_ASID_MASK GENMASK_ULL(63, 48) #define TLBIR_TG_MASK GENMASK_ULL(47, 46) #define TLBIR_SCALE_MASK GENMASK_ULL(45, 44) #define TLBIR_NUM_MASK GENMASK_ULL(43, 39) #define TLBIR_TTL_MASK GENMASK_ULL(38, 37) #define TLBIR_BADDR_MASK GENMASK_ULL(36, 0) #define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl) \ ({ \ unsigned long __ta = 0; \ unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0; \ __ta |= FIELD_PREP(TLBIR_BADDR_MASK, baddr); \ __ta |= FIELD_PREP(TLBIR_TTL_MASK, __ttl); \ __ta |= FIELD_PREP(TLBIR_NUM_MASK, num); \ __ta |= FIELD_PREP(TLBIR_SCALE_MASK, scale); \ __ta |= FIELD_PREP(TLBIR_TG_MASK, get_trans_granule()); \ __ta |= FIELD_PREP(TLBIR_ASID_MASK, asid); \ __ta; \ }) /* These macros are used by the TLBI RANGE feature. */ #define __TLBI_RANGE_PAGES(num, scale) \ ((unsigned long)((num) + 1) << (5 * (scale) + 1)) #define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3) /* * Generate 'num' values from -1 to 31 with -1 rejected by the * __flush_tlb_range() loop below. Its return value is only * significant for a maximum of MAX_TLBI_RANGE_PAGES pages. If * 'pages' is more than that, you must iterate over the overall * range. */ #define __TLBI_RANGE_NUM(pages, scale) \ ({ \ int __pages = min((pages), \ __TLBI_RANGE_PAGES(31, (scale))); \ (__pages >> (5 * (scale) + 1)) - 1; \ }) /* * TLB Invalidation * ================ * * This header file implements the low-level TLB invalidation routines * (sometimes referred to as "flushing" in the kernel) for arm64. * * Every invalidation operation uses the following template: * * DSB ISHST // Ensure prior page-table updates have completed * TLBI ... // Invalidate the TLB * DSB ISH // Ensure the TLB invalidation has completed * if (invalidated kernel mappings) * ISB // Discard any instructions fetched from the old mapping * * * The following functions form part of the "core" TLB invalidation API, * as documented in Documentation/core-api/cachetlb.rst: * * flush_tlb_all() * Invalidate the entire TLB (kernel + user) on all CPUs * * flush_tlb_mm(mm) * Invalidate an entire user address space on all CPUs. * The 'mm' argument identifies the ASID to invalidate. * * flush_tlb_range(vma, start, end) * Invalidate the virtual-address range '[start, end)' on all * CPUs for the user address space corresponding to 'vma->mm'. * Note that this operation also invalidates any walk-cache * entries associated with translations for the specified address * range. * * flush_tlb_kernel_range(start, end) * Same as flush_tlb_range(..., start, end), but applies to * kernel mappings rather than a particular user address space. * Whilst not explicitly documented, this function is used when * unmapping pages from vmalloc/io space. * * flush_tlb_page(vma, addr) * Invalidate a single user mapping for address 'addr' in the * address space corresponding to 'vma->mm'. Note that this * operation only invalidates a single, last-level page-table * entry and therefore does not affect any walk-caches. * * * Next, we have some undocumented invalidation routines that you probably * don't want to call unless you know what you're doing: * * local_flush_tlb_all() * Same as flush_tlb_all(), but only applies to the calling CPU. * * __flush_tlb_kernel_pgtable(addr) * Invalidate a single kernel mapping for address 'addr' on all * CPUs, ensuring that any walk-cache entries associated with the * translation are also invalidated. * * __flush_tlb_range(vma, start, end, stride, last_level, tlb_level) * Invalidate the virtual-address range '[start, end)' on all * CPUs for the user address space corresponding to 'vma->mm'. * The invalidation operations are issued at a granularity * determined by 'stride' and only affect any walk-cache entries * if 'last_level' is equal to false. tlb_level is the level at * which the invalidation must take place. If the level is wrong, * no invalidation may take place. In the case where the level * cannot be easily determined, the value TLBI_TTL_UNKNOWN will * perform a non-hinted invalidation. * * * Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented * on top of these routines, since that is our interface to the mmu_gather * API as used by munmap() and friends. */ static inline void local_flush_tlb_all(void) { dsb(nshst); __tlbi(vmalle1); dsb(nsh); isb(); } static inline void flush_tlb_all(void) { dsb(ishst); __tlbi(vmalle1is); dsb(ish); isb(); } static inline void flush_tlb_mm(struct mm_struct *mm) { unsigned long asid; dsb(ishst); asid = __TLBI_VADDR(0, ASID(mm)); __tlbi(aside1is, asid); __tlbi_user(aside1is, asid); dsb(ish); mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } static inline void __flush_tlb_page_nosync(struct mm_struct *mm, unsigned long uaddr) { unsigned long addr; dsb(ishst); addr = __TLBI_VADDR(uaddr, ASID(mm)); __tlbi(vale1is, addr); __tlbi_user(vale1is, addr); mmu_notifier_arch_invalidate_secondary_tlbs(mm, uaddr & PAGE_MASK, (uaddr & PAGE_MASK) + PAGE_SIZE); } static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, unsigned long uaddr) { return __flush_tlb_page_nosync(vma->vm_mm, uaddr); } static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { flush_tlb_page_nosync(vma, uaddr); dsb(ish); } static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) { /* * TLB flush deferral is not required on systems which are affected by * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation * will have two consecutive TLBI instructions with a dsb(ish) in between * defeating the purpose (i.e save overall 'dsb ish' cost). */ if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI)) return false; return true; } static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, struct mm_struct *mm, unsigned long uaddr) { __flush_tlb_page_nosync(mm, uaddr); } /* * If mprotect/munmap/etc occurs during TLB batched flushing, we need to * synchronise all the TLBI issued with a DSB to avoid the race mentioned in * flush_tlb_batched_pending(). */ static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) { dsb(ish); } /* * To support TLB batched flush for multiple pages unmapping, we only send * the TLBI for each page in arch_tlbbatch_add_pending() and wait for the * completion at the end in arch_tlbbatch_flush(). Since we've already issued * TLBI for each page so only a DSB is needed to synchronise its effect on the * other CPUs. * * This will save the time waiting on DSB comparing issuing a TLBI;DSB sequence * for each page. */ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { dsb(ish); } /* * This is meant to avoid soft lock-ups on large TLB flushing ranges and not * necessarily a performance improvement. */ #define MAX_DVM_OPS PTRS_PER_PTE /* * __flush_tlb_range_op - Perform TLBI operation upon a range * * @op: TLBI instruction that operates on a range (has 'r' prefix) * @start: The start address of the range * @pages: Range as the number of pages from 'start' * @stride: Flush granularity * @asid: The ASID of the task (0 for IPA instructions) * @tlb_level: Translation Table level hint, if known * @tlbi_user: If 'true', call an additional __tlbi_user() * (typically for user ASIDs). 'flase' for IPA instructions * @lpa2: If 'true', the lpa2 scheme is used as set out below * * When the CPU does not support TLB range operations, flush the TLB * entries one by one at the granularity of 'stride'. If the TLB * range ops are supported, then: * * 1. If FEAT_LPA2 is in use, the start address of a range operation must be * 64KB aligned, so flush pages one by one until the alignment is reached * using the non-range operations. This step is skipped if LPA2 is not in * use. * * 2. The minimum range granularity is decided by 'scale', so multiple range * TLBI operations may be required. Start from scale = 3, flush the largest * possible number of pages ((num+1)*2^(5*scale+1)) that fit into the * requested range, then decrement scale and continue until one or zero pages * are left. We must start from highest scale to ensure 64KB start alignment * is maintained in the LPA2 case. * * 3. If there is 1 page remaining, flush it through non-range operations. Range * operations can only span an even number of pages. We save this for last to * ensure 64KB start alignment is maintained for the LPA2 case. */ #define __flush_tlb_range_op(op, start, pages, stride, \ asid, tlb_level, tlbi_user, lpa2) \ do { \ int num = 0; \ int scale = 3; \ int shift = lpa2 ? 16 : PAGE_SHIFT; \ unsigned long addr; \ \ while (pages > 0) { \ if (!system_supports_tlb_range() || \ pages == 1 || \ (lpa2 && start != ALIGN(start, SZ_64K))) { \ addr = __TLBI_VADDR(start, asid); \ __tlbi_level(op, addr, tlb_level); \ if (tlbi_user) \ __tlbi_user_level(op, addr, tlb_level); \ start += stride; \ pages -= stride >> PAGE_SHIFT; \ continue; \ } \ \ num = __TLBI_RANGE_NUM(pages, scale); \ if (num >= 0) { \ addr = __TLBI_VADDR_RANGE(start >> shift, asid, \ scale, num, tlb_level); \ __tlbi(r##op, addr); \ if (tlbi_user) \ __tlbi_user(r##op, addr); \ start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \ pages -= __TLBI_RANGE_PAGES(num, scale); \ } \ scale--; \ } \ } while (0) #define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \ __flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled()); static inline bool __flush_tlb_range_limit_excess(unsigned long start, unsigned long end, unsigned long pages, unsigned long stride) { /* * When the system does not support TLB range based flush * operation, (MAX_DVM_OPS - 1) pages can be handled. But * with TLB range based operation, MAX_TLBI_RANGE_PAGES * pages can be handled. */ if ((!system_supports_tlb_range() && (end - start) >= (MAX_DVM_OPS * stride)) || pages > MAX_TLBI_RANGE_PAGES) return true; return false; } static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long stride, bool last_level, int tlb_level) { unsigned long asid, pages; start = round_down(start, stride); end = round_up(end, stride); pages = (end - start) >> PAGE_SHIFT; if (__flush_tlb_range_limit_excess(start, end, pages, stride)) { flush_tlb_mm(vma->vm_mm); return; } dsb(ishst); asid = ASID(vma->vm_mm); if (last_level) __flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true, lpa2_is_enabled()); else __flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true, lpa2_is_enabled()); mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long stride, bool last_level, int tlb_level) { __flush_tlb_range_nosync(vma, start, end, stride, last_level, tlb_level); dsb(ish); } static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { /* * We cannot use leaf-only invalidation here, since we may be invalidating * table entries as part of collapsing hugepages or moving page tables. * Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough * information here. */ __flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN); } static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) { const unsigned long stride = PAGE_SIZE; unsigned long pages; start = round_down(start, stride); end = round_up(end, stride); pages = (end - start) >> PAGE_SHIFT; if (__flush_tlb_range_limit_excess(start, end, pages, stride)) { flush_tlb_all(); return; } dsb(ishst); __flush_tlb_range_op(vaale1is, start, pages, stride, 0, TLBI_TTL_UNKNOWN, false, lpa2_is_enabled()); dsb(ish); isb(); } /* * Used to invalidate the TLB (walk caches) corresponding to intermediate page * table levels (pgd/pud/pmd). */ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr) { unsigned long addr = __TLBI_VADDR(kaddr, 0); dsb(ishst); __tlbi(vaae1is, addr); dsb(ish); isb(); } #endif #endif |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ #include <linux/list.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/selftests.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/if_hsr.h> #include <net/dcbnl.h> #include <linux/netpoll.h> #include <linux/string.h> #include "conduit.h" #include "dsa.h" #include "netlink.h" #include "port.h" #include "switch.h" #include "tag.h" #include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; struct net_device *orig_dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and * SWITCHDEV_FDB_DEL_TO_DEVICE */ unsigned char addr[ETH_ALEN]; u16 vid; bool host_addr; }; enum dsa_standalone_event { DSA_UC_ADD, DSA_UC_DEL, DSA_MC_ADD, DSA_MC_DEL, }; struct dsa_standalone_event_work { struct work_struct work; struct net_device *dev; enum dsa_standalone_event event; unsigned char addr[ETH_ALEN]; u16 vid; }; struct dsa_host_vlan_rx_filtering_ctx { struct net_device *dev; const unsigned char *addr; enum dsa_standalone_event event; }; static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) { return ds->ops->port_mdb_add && ds->ops->port_mdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; int err; switch (standalone_work->event) { case DSA_UC_ADD: err = dsa_port_standalone_host_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_UC_DEL: err = dsa_port_standalone_host_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; case DSA_MC_ADD: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_add(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to mdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_MC_DEL: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_del(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from mdb: %d\n", dp->index, addr, vid, err); } break; } kfree(standalone_work); } static int dsa_user_schedule_standalone_work(struct net_device *dev, enum dsa_standalone_event event, const unsigned char *addr, u16 vid) { struct dsa_standalone_event_work *standalone_work; standalone_work = kzalloc(sizeof(*standalone_work), GFP_ATOMIC); if (!standalone_work) return -ENOMEM; INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; ether_addr_copy(standalone_work->addr, addr); standalone_work->vid = vid; dsa_schedule_work(&standalone_work->work); return 0; } static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } static int dsa_user_vlan_for_each(struct net_device *dev, int (*cb)(void *arg, int vid), void *arg) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; lockdep_assert_held(&dev->addr_list_lock); err = cb(arg, 0); if (err) return err; list_for_each_entry(v, &dp->user_vlans, list) { err = cb(arg, v->vid); if (err) return err; } return 0; } static int dsa_user_sync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_sync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } void dsa_user_sync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } void dsa_user_unsync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } /* user mii_bus handling ***************************************************/ static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_read(ds, addr, reg); return 0xffff; } static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_write(ds, addr, reg, val); return 0; } void dsa_user_mii_bus_init(struct dsa_switch *ds) { ds->user_mii_bus->priv = (void *)ds; ds->user_mii_bus->name = "dsa user smi"; ds->user_mii_bus->read = dsa_user_phy_read; ds->user_mii_bus->write = dsa_user_phy_write; snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); ds->user_mii_bus->parent = ds->dev; ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; if (dsa_switch_supports_uc_filtering(ds)) { err = dsa_port_standalone_host_fdb_add(dp, addr, 0); if (err) goto out; } if (!ether_addr_equal(addr, conduit->dev_addr)) { err = dev_uc_add(conduit, addr); if (err < 0) goto del_host_addr; } return 0; del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, addr, 0); out: return err; } void dsa_user_host_uc_uninstall(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); } static int dsa_user_open(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); int err; err = dev_open(conduit, NULL); if (err < 0) { netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } err = dsa_user_host_uc_install(dev, dev->dev_addr); if (err) goto out; err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto out_del_host_uc; return 0; out_del_host_uc: dsa_user_host_uc_uninstall(dev); out: return err; } static int dsa_user_close(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); dsa_port_disable_rt(dp); dsa_user_host_uc_uninstall(dev); return 0; } static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } static void dsa_user_change_rx_flags(struct net_device *dev, int change) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) dsa_user_manage_host_flood(dev); } static void dsa_user_set_rx_mode(struct net_device *dev) { __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } static int dsa_user_set_mac_address(struct net_device *dev, void *a) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (ds->ops->port_set_mac_address) { err = ds->ops->port_set_mac_address(ds, dp->index, addr->sa_data); if (err) return err; } /* If the port is down, the address isn't synced yet to hardware or * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; err = dsa_user_host_uc_install(dev, addr->sa_data); if (err) return err; dsa_user_host_uc_uninstall(dev); out_change_dev_addr: eth_hw_addr_set(dev, addr->sa_data); return 0; } struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; static int dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct dsa_user_dump_ctx *dump = data; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; if (dump->idx < dump->cb->args[2]) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, sizeof(*ndm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dump->dev->ifindex; ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); skip: dump->idx++; return 0; nla_put_failure: nlmsg_cancel(dump->skb, nlh); return -EMSGSIZE; } static int dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; int err; err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; /* Pass through to switch driver if it supports timestamping */ switch (cmd) { case SIOCGHWTSTAMP: if (ds->ops->port_hwtstamp_get) return ds->ops->port_hwtstamp_get(ds, port, ifr); break; case SIOCSHWTSTAMP: if (ds->ops->port_hwtstamp_set) return ds->ops->port_hwtstamp_set(ds, port, ifr); break; } return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) return 0; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_PORT_MST_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_mst_state(dp, &attr->u.mst_state, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_BRIDGE_MST: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_mst_enable(dp, attr->u.mst, extack); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_VLAN_MSTI: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_msti(dp, &attr->u.vlan_msti); break; default: ret = -EOPNOTSUPP; break; } return ret; } /* Must be called under rcu_read_lock() */ static int dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) continue; vid = vlan_dev_vlan_id(upper_dev); if (vid == vlan->vid) return -EBUSY; } return 0; } static int dsa_user_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, "Port already has a VLAN upper with this VID"); return err; } } return dsa_port_vlan_add(dp, vlan, extack); } /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ static int dsa_user_host_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); /* Even though drivers often handle CPU membership in special ways, * it doesn't make sense to program a PVID, so clear this flag. */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; return dsa_port_host_vlan_add(dp, &vlan, extack); } static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_add(dev, obj, extack); else err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static int dsa_user_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_vlan_del(dp, vlan); } static int dsa_user_host_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_host_vlan_del(dp, vlan); } static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_del(dev, obj); else err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) return; if (!ds->ops->port_txtstamp) return; ds->ops->port_txtstamp(ds, p->dp->index, skb); } netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) { /* SKB for netpoll still need to be mangled with the protocol-specific * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); memset(skb->cb, 0, sizeof(skb->cb)); /* Handle tx timestamp if any */ dsa_skb_tx_timestamp(p, skb); if (skb_ensure_writable_head_tail(skb, dev)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* needed_tailroom should still be 'warm' in the cache line from * skb_ensure_writable_head_tail(), which has also ensured that * padding is safe. */ if (dev->needed_tailroom) eth_skb_pad(skb); /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ nskb = p->xmit(skb, dev); if (!nskb) { kfree_skb(skb); return NETDEV_TX_OK; } return dsa_enqueue_skb(nskb, dev); } /* ethtool operations *******************************************************/ static void dsa_user_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_user_get_regs_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } static void dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } static int dsa_user_nway_reset(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } static int dsa_user_get_eeprom_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; if (ds->ops->get_eeprom_len) return ds->ops->get_eeprom_len(ds); return 0; } static int dsa_user_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static int dsa_user_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static void dsa_user_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { ethtool_puts(&data, "tx_packets"); ethtool_puts(&data, "tx_bytes"); ethtool_puts(&data, "rx_packets"); ethtool_puts(&data, "rx_bytes"); if (ds->ops->get_strings) ds->ops->get_strings(ds, dp->index, stringset, data); } else if (stringset == ETH_SS_TEST) { net_selftest_get_strings(data); } } static void dsa_user_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; for_each_possible_cpu(i) { u64 tx_packets, tx_bytes, rx_packets, rx_bytes; s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin(&s->syncp); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); } while (u64_stats_fetch_retry(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; data[2] += rx_packets; data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_user_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count = 0; if (ds->ops->get_sset_count) { count = ds->ops->get_sset_count(ds, dp->index, sset); if (count < 0) return count; } return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } return -EOPNOTSUPP; } static void dsa_user_get_eth_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } static void dsa_user_get_eth_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); } static void dsa_user_get_eth_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); } static void dsa_user_get_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { ds->ops->self_test(ds, dp->index, etest, buf); return; } net_selftest(ndev, etest, buf); } static int dsa_user_get_mm(struct net_device *dev, struct ethtool_mm_state *state) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) return -EOPNOTSUPP; return ds->ops->get_mm(ds, dp->index, state); } static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) return -EOPNOTSUPP; return ds->ops->set_mm(ds, dp->index, cfg, extack); } static void dsa_user_get_mm_stats(struct net_device *dev, struct ethtool_mm_stats *stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; phylink_ethtool_set_wol(dp->pl, w); if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_get_eee(dp->pl, e); } static int dsa_user_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } static int dsa_user_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } static void dsa_user_get_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } static void dsa_user_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } static int dsa_user_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER static int dsa_user_netpoll_setup(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); if (!netpoll) return -ENOMEM; err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; } p->netpoll = netpoll; out: return err; } static void dsa_user_netpoll_cleanup(struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) return; p->netpoll = NULL; __netpoll_free(netpoll); } static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) if (mall_tc_entry->cookie == cookie) return mall_tc_entry; return NULL; } static int dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress, bool ingress_target) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; struct dsa_port *to_dp; int err; if (cls->common.protocol != htons(ETH_P_ALL)) { NL_SET_ERR_MSG_MOD(extack, "Can only offload \"protocol all\" matchall filter"); return -EOPNOTSUPP; } if (!ds->ops->port_mirror_add) { NL_SET_ERR_MSG_MOD(extack, "Switch does not support mirroring operation"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; if (!act->dev) return -EINVAL; if (dsa_user_dev_check(act->dev)) { if (ingress_target) { /* We can only fulfill this using software assist */ if (cls->common.skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Can only mirred to ingress of DSA user port if filter also runs in software"); return -EOPNOTSUPP; } to_dp = dp->cpu_dp; } else { to_dp = dsa_user_to_port(act->dev); } } else { /* Handle mirroring to foreign target ports as a mirror towards * the CPU. The software tc rule will take the packets from * there. */ if (cls->common.skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Can only mirred to CPU if filter also runs in software"); return -EOPNOTSUPP; } to_dp = dp->cpu_dp; } if (dp->ds != to_dp->ds) { NL_SET_ERR_MSG_MOD(extack, "Cross-chip mirroring not implemented"); return -EOPNOTSUPP; } mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; mirror->to_local_port = to_dp->index; mirror->ingress = ingress; err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress, extack); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall_police(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; int err; if (!ds->ops->port_policer_add) { NL_SET_ERR_MSG_MOD(extack, "Policing offload not implemented"); return -EOPNOTSUPP; } if (!ingress) { NL_SET_ERR_MSG_MOD(extack, "Only supported on ingress qdisc"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { NL_SET_ERR_MSG_MOD(extack, "Only one port policer allowed"); return -EEXIST; } } act = &cls->rule->action.entries[0]; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_POLICER; policer = &mall_tc_entry->policer; policer->rate_bytes_per_sec = act->police.rate_bytes_ps; policer->burst = act->police.burst; err = ds->ops->port_policer_add(ds, dp->index, policer); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { const struct flow_action *action = &cls->rule->action; struct netlink_ext_ack *extack = cls->common.extack; if (!flow_offload_has_one_action(action)) { NL_SET_ERR_MSG_MOD(extack, "Cannot offload matchall filter with more than one action"); return -EOPNOTSUPP; } switch (action->entries[0].id) { case FLOW_ACTION_MIRRED: return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, false); case FLOW_ACTION_MIRRED_INGRESS: return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, true); case FLOW_ACTION_POLICE: return dsa_user_add_cls_matchall_police(dev, cls, ingress); default: NL_SET_ERR_MSG_MOD(extack, "Unknown action"); break; } return -EOPNOTSUPP; } static void dsa_user_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; list_del(&mall_tc_entry->list); switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: if (ds->ops->port_mirror_del) ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; case DSA_PORT_MALL_POLICER: if (ds->ops->port_policer_del) ds->ops->port_policer_del(ds, dp->index); break; default: WARN_ON(1); } kfree(mall_tc_entry); } static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_add_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_add) return -EOPNOTSUPP; return ds->ops->cls_flower_add(ds, port, cls, ingress); } static int dsa_user_del_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_del) return -EOPNOTSUPP; return ds->ops->cls_flower_del(ds, port, cls, ingress); } static int dsa_user_stats_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_stats) return -EOPNOTSUPP; return ds->ops->cls_flower_stats(ds, port, cls, ingress); } static int dsa_user_setup_tc_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; if (!tc_can_offload(dev)) return -EOPNOTSUPP; switch (type) { case TC_SETUP_CLSMATCHALL: return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } static LIST_HEAD(dsa_user_block_cb_list); static int dsa_user_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, void *type_data) { struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } if (!ds->ops->port_setup_tc) return -EOPNOTSUPP; return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } static int dsa_user_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_user_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; return ds->ops->set_rxnfc(ds, dp->index, nfc); } static int dsa_user_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) return -EOPNOTSUPP; return ds->ops->get_ts_info(ds, p->dp->index, ts); } static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int ret; /* User port... */ ret = dsa_port_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); return ret; } /* And CPU port... */ ret = dsa_port_host_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, extack._msg); return ret; } if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { ret = -ENOMEM; goto rollback; } netif_addr_lock_bh(dev); v->vid = vid; list_add_tail(&v->list, &dp->user_vlans); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; rollback: dsa_port_host_vlan_del(dp, &vlan); dsa_port_vlan_del(dp, &vlan); return ret; } static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; err = dsa_port_host_vlan_del(dp, &vlan); if (err) return err; if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; netif_addr_lock_bh(dev); v = dsa_vlan_find(&dp->user_vlans, &vlan); if (!v) { netif_addr_unlock_bh(dev); return -ENOENT; } list_del(&v->list); kfree(v); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; } static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_add_vid(arg, proto, vid); } static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN * filtering is enabled. The baseline is that only ports that offload a * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, * but there are exceptions for quirky hardware. * * If ds->vlan_filtering_is_global = true, then standalone ports which share * the same switch with other ports that offload a VLAN-aware bridge are also * inevitably VLAN-aware. * * To summarize, a DSA switch port offloads: * * - If standalone (this includes software bridge, software LAG): * - if ds->needs_standalone_vlan_filtering = true, OR if * (ds->vlan_filtering_is_global = true AND there are bridges spanning * this switch chip which have vlan_filtering=1) * - the 8021q upper VLANs * - else (standalone VLAN filtering is not needed, VLAN filtering is not * global, or it is, but no port is under a VLAN-aware bridge): * - no VLAN (any 8021q upper is a software VLAN) * * - If under a vlan_filtering=0 bridge which it offload: * - if ds->configure_vlan_while_not_filtering = true (default): * - the bridge VLANs. These VLANs are committed to hardware but inactive. * - else (deprecated): * - no VLAN. The bridge VLANs are not restored when VLAN awareness is * enabled, so this behavior is broken and discouraged. * * - If under a vlan_filtering=1 bridge which it offload: * - the bridge VLANs * - the 8021q upper VLANs */ int dsa_user_manage_vlan_filtering(struct net_device *user, bool vlan_filtering) { int err; if (vlan_filtering) { user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { vlan_for_each(user, dsa_user_clear_vlan, user); user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; } struct dsa_hw_port { struct list_head list; struct net_device *dev; int old_mtu; }; static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) { const struct dsa_hw_port *p; int err; list_for_each_entry(p, hw_port_list, list) { if (p->dev->mtu == mtu) continue; err = dev_set_mtu(p->dev, mtu); if (err) goto rollback; } return 0; rollback: list_for_each_entry_continue_reverse(p, hw_port_list, list) { if (p->dev->mtu == p->old_mtu) continue; if (dev_set_mtu(p->dev, p->old_mtu)) netdev_err(p->dev, "Failed to restore MTU\n"); } return err; } static void dsa_hw_port_list_free(struct list_head *hw_port_list) { struct dsa_hw_port *p, *n; list_for_each_entry_safe(p, n, hw_port_list, list) kfree(p); } /* Make the hardware datapath to/from @dev limited to a common MTU */ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) { struct list_head hw_port_list; struct dsa_switch_tree *dst; int min_mtu = ETH_MAX_MTU; struct dsa_port *other_dp; int err; if (!dp->ds->mtu_enforcement_ingress) return; if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); /* Populate the list of ports that are part of the same bridge * as the newly added/modified port */ list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; if (!dsa_port_bridge_same(dp, other_dp)) continue; if (!other_dp->ds->mtu_enforcement_ingress) continue; user = other_dp->user; if (min_mtu > user->mtu) min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; hw_port->dev = user; hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } } /* Attempt to configure the entire hardware bridge to the newly added * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; /* Clearly that didn't work out so well, so just set the minimum MTU on * all hardware bridge ports now. If this fails too, then all ports will * still have their old MTU rolled back anyway. */ dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); out: dsa_hw_port_list_free(&hw_port_list); } int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; int new_conduit_mtu; int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { int user_mtu; /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) user_mtu = new_mtu; else user_mtu = other_dp->user->mtu; if (largest_mtu < user_mtu) largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); old_conduit_mtu = conduit->mtu; new_conduit_mtu = largest_mtu + overhead; if (new_conduit_mtu > mtu_limit) return -ERANGE; /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ if (new_conduit_mtu != old_conduit_mtu) { err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. */ err = dsa_port_mtu_change(cpu_dp, cpu_mtu); if (err) goto out_cpu_failed; } err = ds->ops->port_change_mtu(ds, dp->index, new_mtu); if (err) goto out_port_failed; WRITE_ONCE(dev->mtu, new_mtu); dsa_bridge_mtu_normalization(dp); return 0; out_port_failed: if (new_conduit_mtu != old_conduit_mtu) dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: if (new_conduit_mtu != old_conduit_mtu) |